Data

yield <- read.csv("D:/Onedrive/Data Science/Forecasting Financial Market/data/TVC_ID10Y, 1D_64448.csv")
yield$time <- as.Date(yield$time, "%Y-%m-%d")
yield <- yield %>% 
  select(time, close)

yield
##            time  close
## 1    2011-11-29 6.8820
## 2    2011-11-30 6.8820
## 3    2011-12-01 6.4150
## 4    2011-12-02 6.1570
## 5    2011-12-05 6.1570
## 6    2011-12-06 6.0300
## 7    2011-12-07 6.0290
## 8    2011-12-08 6.0600
## 9    2011-12-09 6.2190
## 10   2011-12-12 6.2500
## 11   2011-12-13 6.2310
## 12   2011-12-14 6.1850
## 13   2011-12-15 6.3130
## 14   2011-12-16 6.2160
## 15   2011-12-19 6.2160
## 16   2011-12-20 6.2150
## 17   2011-12-21 6.2150
## 18   2011-12-22 6.1490
## 19   2011-12-23 6.0620
## 20   2011-12-27 6.0850
## 21   2011-12-28 6.0840
## 22   2011-12-29 6.0830
## 23   2011-12-30 6.0190
## 24   2012-01-02 6.1460
## 25   2012-01-03 6.0820
## 26   2012-01-04 6.0820
## 27   2012-01-05 6.1450
## 28   2012-01-06 6.2020
## 29   2012-01-09 6.1530
## 30   2012-01-10 6.1430
## 31   2012-01-11 6.1110
## 32   2012-01-12 6.1100
## 33   2012-01-13 6.1090
## 34   2012-01-16 6.1090
## 35   2012-01-17 6.1080
## 36   2012-01-18 5.7600
## 37   2012-01-19 5.6200
## 38   2012-01-20 5.6030
## 39   2012-01-24 5.5720
## 40   2012-01-25 5.5710
## 41   2012-01-26 5.5640
## 42   2012-01-27 5.5690
## 43   2012-01-30 5.5680
## 44   2012-01-31 5.3070
## 45   2012-02-01 5.2640
## 46   2012-02-02 5.2520
## 47   2012-02-03 5.2420
## 48   2012-02-06 5.2220
## 49   2012-02-07 5.1410
## 50   2012-02-08 5.1400
## 51   2012-02-09 5.1090
## 52   2012-02-10 5.0950
## 53   2012-02-13 5.1300
## 54   2012-02-14 5.1470
## 55   2012-02-15 5.1370
## 56   2012-02-16 5.2450
## 57   2012-02-17 5.2740
## 58   2012-02-20 5.2330
## 59   2012-02-21 5.2740
## 60   2012-02-22 5.2480
## 61   2012-02-23 5.3130
## 62   2012-02-24 5.4510
## 63   2012-02-27 5.4500
## 64   2012-02-28 5.6860
## 65   2012-02-29 5.6160
## 66   2012-03-01 5.5340
## 67   2012-03-02 5.5370
## 68   2012-03-05 5.5090
## 69   2012-03-06 5.6910
## 70   2012-03-07 5.6360
## 71   2012-03-08 5.6350
## 72   2012-03-09 5.6350
## 73   2012-03-12 5.8410
## 74   2012-03-13 5.8510
## 75   2012-03-14 5.9700
## 76   2012-03-15 6.0650
## 77   2012-03-16 5.9380
## 78   2012-03-19 5.8750
## 79   2012-03-20 5.9380
## 80   2012-03-21 5.8750
## 81   2012-03-22 5.9370
## 82   2012-03-26 5.9370
## 83   2012-03-27 5.9370
## 84   2012-03-28 5.8980
## 85   2012-03-29 5.9040
## 86   2012-03-30 5.9170
## 87   2012-04-02 5.8720
## 88   2012-04-03 5.9350
## 89   2012-04-04 5.9030
## 90   2012-04-05 5.9030
## 91   2012-04-09 5.9340
## 92   2012-04-10 5.9340
## 93   2012-04-11 5.9590
## 94   2012-04-12 6.0610
## 95   2012-04-13 6.0220
## 96   2012-04-16 6.0610
## 97   2012-04-17 6.0600
## 98   2012-04-18 5.9640
## 99   2012-04-19 5.9000
## 100  2012-04-20 5.8370
## 101  2012-04-23 5.9190
## 102  2012-04-24 5.8930
## 103  2012-04-25 5.8980
## 104  2012-04-26 5.8550
## 105  2012-04-27 5.9240
## 106  2012-04-30 5.9620
## 107  2012-05-01 5.9620
## 108  2012-05-02 6.0580
## 109  2012-05-03 6.0580
## 110  2012-05-04 6.0700
## 111  2012-05-07 6.0900
## 112  2012-05-08 6.1150
## 113  2012-05-09 6.1870
## 114  2012-05-10 6.2050
## 115  2012-05-11 6.2060
## 116  2012-05-14 6.3180
## 117  2012-05-15 6.4370
## 118  2012-05-16 6.5850
## 119  2012-05-21 6.4830
## 120  2012-05-22 6.4100
## 121  2012-05-23 6.4090
## 122  2012-05-24 6.5640
## 123  2012-05-25 6.5500
## 124  2012-05-28 6.5160
## 125  2012-05-29 6.5160
## 126  2012-05-30 6.4890
## 127  2012-05-31 6.5160
## 128  2012-06-01 6.4480
## 129  2012-06-04 6.5150
## 130  2012-06-05 6.5490
## 131  2012-06-06 6.5290
## 132  2012-06-07 6.4470
## 133  2012-06-08 6.5150
## 134  2012-06-11 6.4250
## 135  2012-06-12 6.4360
## 136  2012-06-13 6.4060
## 137  2012-06-14 6.3920
## 138  2012-06-15 6.3390
## 139  2012-06-18 6.3670
## 140  2012-06-19 6.4120
## 141  2012-06-20 6.2120
## 142  2012-06-21 6.0610
## 143  2012-06-22 6.0800
## 144  2012-06-25 6.3110
## 145  2012-06-26 6.2780
## 146  2012-06-27 6.2710
## 147  2012-06-28 6.2110
## 148  2012-06-29 6.1120
## 149  2012-07-02 6.0790
## 150  2012-07-03 6.1770
## 151  2012-07-04 6.0460
## 152  2012-07-05 5.9800
## 153  2012-07-06 6.0250
## 154  2012-07-09 6.0770
## 155  2012-07-10 6.1230
## 156  2012-07-11 6.0570
## 157  2012-07-12 6.1090
## 158  2012-07-13 6.0040
## 159  2012-07-16 5.9390
## 160  2012-07-17 5.9130
## 161  2012-07-18 5.7840
## 162  2012-07-19 5.7200
## 163  2012-07-20 5.7070
## 164  2012-07-23 5.8470
## 165  2012-07-24 5.8790
## 166  2012-07-25 5.8400
## 167  2012-07-26 5.7820
## 168  2012-07-27 5.7620
## 169  2012-07-30 5.7180
## 170  2012-07-31 5.6860
## 171  2012-08-01 5.6980
## 172  2012-08-02 5.6850
## 173  2012-08-03 5.6910
## 174  2012-08-06 5.6840
## 175  2012-08-07 5.7150
## 176  2012-08-08 5.7220
## 177  2012-08-09 5.7270
## 178  2012-08-10 5.7270
## 179  2012-08-13 5.9460
## 180  2012-08-14 5.9260
## 181  2012-08-15 5.9060
## 182  2012-08-16 5.9060
## 183  2012-08-21 5.9060
## 184  2012-08-22 5.9060
## 185  2012-08-23 5.9700
## 186  2012-08-24 6.1020
## 187  2012-08-27 6.1010
## 188  2012-08-28 6.1680
## 189  2012-08-29 6.2480
## 190  2012-08-30 6.3010
## 191  2012-08-31 6.2470
## 192  2012-09-03 6.0540
## 193  2012-09-04 6.0340
## 194  2012-09-05 6.0340
## 195  2012-09-06 6.0990
## 196  2012-09-07 6.0220
## 197  2012-09-10 5.9340
## 198  2012-09-11 5.9670
## 199  2012-09-12 5.9140
## 200  2012-09-13 5.9000
## 201  2012-09-14 5.7700
## 202  2012-09-17 5.8020
## 203  2012-09-18 5.8670
## 204  2012-09-19 5.8990
## 205  2012-09-20 5.9640
## 206  2012-09-21 5.9770
## 207  2012-09-24 5.9770
## 208  2012-09-25 5.9840
## 209  2012-09-26 6.0160
## 210  2012-09-27 6.0660
## 211  2012-09-28 5.9730
## 212  2012-10-01 5.8970
## 213  2012-10-02 5.8810
## 214  2012-10-03 5.8650
## 215  2012-10-04 5.8760
## 216  2012-10-05 5.8170
## 217  2012-10-08 5.8580
## 218  2012-10-09 5.8970
## 219  2012-10-10 5.9190
## 220  2012-10-11 5.8880
## 221  2012-10-12 5.8550
## 222  2012-10-15 5.8930
## 223  2012-10-16 5.8250
## 224  2012-10-17 5.7550
## 225  2012-10-18 5.7600
## 226  2012-10-19 5.7230
## 227  2012-10-22 5.7620
## 228  2012-10-23 5.7050
## 229  2012-10-24 5.7290
## 230  2012-10-25 5.7710
## 231  2012-10-29 5.7180
## 232  2012-10-30 5.7050
## 233  2012-10-31 5.7050
## 234  2012-11-01 5.6640
## 235  2012-11-02 5.6270
## 236  2012-11-05 5.6090
## 237  2012-11-06 5.6390
## 238  2012-11-07 5.5920
## 239  2012-11-08 5.6390
## 240  2012-11-09 5.5640
## 241  2012-11-12 5.5260
## 242  2012-11-13 5.4560
## 243  2012-11-14 5.3970
## 244  2012-11-15 5.3970
## 245  2012-11-19 5.4070
## 246  2012-11-20 5.4060
## 247  2012-11-21 5.4100
## 248  2012-11-22 5.4080
## 249  2012-11-23 5.4150
## 250  2012-11-26 5.4400
## 251  2012-11-27 5.4510
## 252  2012-11-28 5.4540
## 253  2012-11-29 5.4340
## 254  2012-11-30 5.4290
## 255  2012-12-03 5.5030
## 256  2012-12-04 5.4220
## 257  2012-12-05 5.4200
## 258  2012-12-06 5.4240
## 259  2012-12-07 5.4210
## 260  2012-12-10 5.4070
## 261  2012-12-11 5.4030
## 262  2012-12-12 5.2750
## 263  2012-12-13 5.2240
## 264  2012-12-14 5.2370
## 265  2012-12-17 5.2380
## 266  2012-12-18 5.2100
## 267  2012-12-19 5.1780
## 268  2012-12-20 5.1650
## 269  2012-12-21 5.1970
## 270  2012-12-26 5.1880
## 271  2012-12-27 5.2470
## 272  2012-12-28 5.1670
## 273  2013-01-01 5.1670
## 274  2013-01-02 5.1430
## 275  2013-01-03 5.1220
## 276  2013-01-04 5.0850
## 277  2013-01-07 5.0890
## 278  2013-01-08 5.0190
## 279  2013-01-09 5.1480
## 280  2013-01-10 5.2360
## 281  2013-01-11 5.2440
## 282  2013-01-14 5.2500
## 283  2013-01-15 5.2790
## 284  2013-01-16 5.2720
## 285  2013-01-18 5.2670
## 286  2013-01-21 5.2410
## 287  2013-01-22 5.2800
## 288  2013-01-23 5.2270
## 289  2013-01-25 5.1400
## 290  2013-01-28 5.1920
## 291  2013-01-29 5.2650
## 292  2013-01-30 5.3070
## 293  2013-01-31 5.3430
## 294  2013-02-01 5.3050
## 295  2013-02-04 5.2950
## 296  2013-02-06 5.2390
## 297  2013-02-07 5.2420
## 298  2013-02-08 5.2290
## 299  2013-02-11 5.2420
## 300  2013-02-12 5.2620
## 301  2013-02-13 5.2350
## 302  2013-02-14 5.3130
## 303  2013-02-15 5.2410
## 304  2013-02-18 5.2600
## 305  2013-02-19 5.2710
## 306  2013-02-20 5.2680
## 307  2013-02-21 5.2720
## 308  2013-02-25 5.2700
## 309  2013-02-26 5.2910
## 310  2013-02-27 5.2970
## 311  2013-02-28 5.4160
## 312  2013-03-01 5.4220
## 313  2013-03-05 5.4080
## 314  2013-03-06 5.3370
## 315  2013-03-07 5.3980
## 316  2013-03-08 5.3660
## 317  2013-03-11 5.4240
## 318  2013-03-13 5.4620
## 319  2013-03-14 5.4310
## 320  2013-03-15 5.4490
## 321  2013-03-18 5.4730
## 322  2013-03-19 5.5170
## 323  2013-03-20 5.4600
## 324  2013-03-21 5.4680
## 325  2013-03-22 5.5170
## 326  2013-03-25 5.4840
## 327  2013-03-26 5.5900
## 328  2013-03-27 5.6510
## 329  2013-03-28 5.5220
## 330  2013-04-01 5.5460
## 331  2013-04-02 5.5260
## 332  2013-04-03 5.5200
## 333  2013-04-04 5.5090
## 334  2013-04-05 5.5570
## 335  2013-04-08 5.6830
## 336  2013-04-09 5.6900
## 337  2013-04-10 5.6000
## 338  2013-04-11 5.6040
## 339  2013-04-12 5.5230
## 340  2013-04-15 5.5120
## 341  2013-04-16 5.4820
## 342  2013-04-17 5.4290
## 343  2013-04-18 5.4680
## 344  2013-04-19 5.4550
## 345  2013-04-22 5.4610
## 346  2013-04-23 5.5100
## 347  2013-04-24 5.4610
## 348  2013-04-25 5.5160
## 349  2013-04-26 5.4890
## 350  2013-04-29 5.4550
## 351  2013-04-30 5.4940
## 352  2013-05-01 5.5540
## 353  2013-05-02 5.5200
## 354  2013-05-03 5.6250
## 355  2013-05-06 5.5920
## 356  2013-05-07 5.5980
## 357  2013-05-08 5.4720
## 358  2013-05-10 5.5010
## 359  2013-05-13 5.4870
## 360  2013-05-14 5.4350
## 361  2013-05-15 5.5140
## 362  2013-05-16 5.5720
## 363  2013-05-17 5.6250
## 364  2013-05-20 5.6120
## 365  2013-05-21 5.6580
## 366  2013-05-22 5.7290
## 367  2013-05-23 5.7800
## 368  2013-05-24 5.8700
## 369  2013-05-27 5.8840
## 370  2013-05-28 5.9930
## 371  2013-05-29 5.9500
## 372  2013-05-30 5.9340
## 373  2013-05-31 6.0990
## 374  2013-06-03 6.0300
## 375  2013-06-04 6.0320
## 376  2013-06-05 6.1980
## 377  2013-06-06 6.1690
## 378  2013-06-10 6.2740
## 379  2013-06-11 6.5240
## 380  2013-06-12 6.4670
## 381  2013-06-13 6.4670
## 382  2013-06-14 6.4890
## 383  2013-06-18 6.5920
## 384  2013-06-19 6.5980
## 385  2013-06-20 6.7080
## 386  2013-06-21 6.8200
## 387  2013-06-24 6.9700
## 388  2013-06-26 7.2780
## 389  2013-06-27 7.2280
## 390  2013-06-28 7.1160
## 391  2013-07-01 7.1110
## 392  2013-07-02 7.2260
## 393  2013-07-03 7.3760
## 394  2013-07-04 7.3440
## 395  2013-07-05 7.3790
## 396  2013-07-08 7.4340
## 397  2013-07-09 7.7560
## 398  2013-07-10 7.9250
## 399  2013-07-11 7.8810
## 400  2013-07-12 7.9800
## 401  2013-07-15 8.2110
## 402  2013-07-16 8.2460
## 403  2013-07-17 8.1920
## 404  2013-07-18 8.0800
## 405  2013-07-19 7.9130
## 406  2013-07-22 7.8210
## 407  2013-07-23 7.4610
## 408  2013-07-24 7.6010
## 409  2013-07-25 7.8940
## 410  2013-07-26 7.9670
## 411  2013-07-29 7.9930
## 412  2013-07-30 8.0210
## 413  2013-07-31 7.8710
## 414  2013-08-01 7.6990
## 415  2013-08-02 7.6290
## 416  2013-08-05 7.6570
## 417  2013-08-06 7.6690
## 418  2013-08-07 7.6490
## 419  2013-08-08 7.6490
## 420  2013-08-12 7.7300
## 421  2013-08-13 7.8020
## 422  2013-08-14 7.8470
## 423  2013-08-15 7.9960
## 424  2013-08-16 8.1300
## 425  2013-08-19 8.3760
## 426  2013-08-20 8.4270
## 427  2013-08-21 8.4500
## 428  2013-08-22 8.4430
## 429  2013-08-23 8.4740
## 430  2013-08-26 8.4800
## 431  2013-08-27 8.5730
## 432  2013-08-28 8.8170
## 433  2013-08-29 8.8100
## 434  2013-08-30 8.6110
## 435  2013-09-02 8.4030
## 436  2013-09-03 8.5200
## 437  2013-09-04 8.7360
## 438  2013-09-05 8.7510
## 439  2013-09-06 8.8740
## 440  2013-09-09 8.9030
## 441  2013-09-10 8.8740
## 442  2013-09-11 8.7070
## 443  2013-09-12 8.6610
## 444  2013-09-13 8.4180
## 445  2013-09-16 8.1730
## 446  2013-09-17 8.1070
## 447  2013-09-18 8.2470
## 448  2013-09-19 8.1860
## 449  2013-09-20 7.8840
## 450  2013-09-23 7.8590
## 451  2013-09-24 7.9370
## 452  2013-09-25 7.9830
## 453  2013-09-26 8.0540
## 454  2013-09-27 8.2280
## 455  2013-09-30 8.4900
## 456  2013-10-01 8.3380
## 457  2013-10-02 8.1780
## 458  2013-10-03 8.1320
## 459  2013-10-04 8.1240
## 460  2013-10-07 8.1160
## 461  2013-10-08 8.0940
## 462  2013-10-09 8.0850
## 463  2013-10-10 8.0770
## 464  2013-10-11 8.0020
## 465  2013-10-16 8.0530
## 466  2013-10-17 7.8260
## 467  2013-10-18 7.5040
## 468  2013-10-21 7.4720
## 469  2013-10-22 7.3590
## 470  2013-10-23 7.1970
## 471  2013-10-24 7.1640
## 472  2013-10-25 7.1260
## 473  2013-10-28 6.9700
## 474  2013-10-29 7.0190
## 475  2013-10-30 7.1840
## 476  2013-10-31 7.4160
## 477  2013-11-01 7.5630
## 478  2013-11-04 7.8640
## 479  2013-11-05 7.8950
## 480  2013-11-06 7.9660
## 481  2013-11-07 7.9440
## 482  2013-11-08 7.8720
## 483  2013-11-11 8.1770
## 484  2013-11-12 8.4240
## 485  2013-11-13 8.3920
## 486  2013-11-14 8.4130
## 487  2013-11-15 8.4170
## 488  2013-11-18 8.4150
## 489  2013-11-19 8.3860
## 490  2013-11-20 8.3670
## 491  2013-11-21 8.5140
## 492  2013-11-22 8.6390
## 493  2013-11-25 8.5670
## 494  2013-11-26 8.5770
## 495  2013-11-27 8.5630
## 496  2013-11-28 8.5940
## 497  2013-11-29 8.6910
## 498  2013-12-02 8.6030
## 499  2013-12-03 8.5590
## 500  2013-12-04 8.5890
## 501  2013-12-05 8.8000
## 502  2013-12-06 8.7900
## 503  2013-12-09 8.7850
## 504  2013-12-10 8.8040
## 505  2013-12-11 8.7240
## 506  2013-12-12 8.7000
## 507  2013-12-13 8.6320
## 508  2013-12-16 8.5630
## 509  2013-12-17 8.4940
## 510  2013-12-18 8.4430
## 511  2013-12-19 8.4240
## 512  2013-12-20 8.4580
## 513  2013-12-23 8.4610
## 514  2013-12-24 8.4480
## 515  2013-12-25 8.4480
## 516  2013-12-27 8.5070
## 517  2013-12-30 8.4990
## 518  2013-12-31 8.4400
## 519  2014-01-02 8.4620
## 520  2014-01-03 8.5500
## 521  2014-01-06 9.1030
## 522  2014-01-07 9.1240
## 523  2014-01-08 9.0360
## 524  2014-01-09 9.0170
## 525  2014-01-10 8.8360
## 526  2014-01-13 8.6380
## 527  2014-01-14 8.6380
## 528  2014-01-15 8.5710
## 529  2014-01-16 8.4810
## 530  2014-01-17 8.4510
## 531  2014-01-20 8.4580
## 532  2014-01-21 8.4730
## 533  2014-01-22 8.5620
## 534  2014-01-23 8.6340
## 535  2014-01-24 8.7880
## 536  2014-01-27 9.1120
## 537  2014-01-28 9.0450
## 538  2014-01-29 8.8040
## 539  2014-01-30 8.8870
## 540  2014-02-03 9.0260
## 541  2014-02-04 9.0750
## 542  2014-02-05 9.0630
## 543  2014-02-06 9.0750
## 544  2014-02-07 9.0250
## 545  2014-02-10 9.0600
## 546  2014-02-11 9.0250
## 547  2014-02-12 8.8630
## 548  2014-02-13 8.7970
## 549  2014-02-14 8.7100
## 550  2014-02-17 8.5270
## 551  2014-02-18 8.5150
## 552  2014-02-19 8.3880
## 553  2014-02-20 8.3570
## 554  2014-02-21 8.3420
## 555  2014-02-24 8.4230
## 556  2014-02-25 8.4870
## 557  2014-02-26 8.4670
## 558  2014-02-27 8.4350
## 559  2014-02-28 8.3890
## 560  2014-03-03 8.2380
## 561  2014-03-04 8.2000
## 562  2014-03-05 7.9890
## 563  2014-03-06 8.0690
## 564  2014-03-07 8.0420
## 565  2014-03-10 8.0520
## 566  2014-03-11 8.0320
## 567  2014-03-12 8.0620
## 568  2014-03-13 8.0400
## 569  2014-03-14 8.0420
## 570  2014-03-17 8.0060
## 571  2014-03-18 7.9160
## 572  2014-03-19 7.8840
## 573  2014-03-20 8.0370
## 574  2014-03-21 8.0710
## 575  2014-03-24 8.0930
## 576  2014-03-25 8.1740
## 577  2014-03-26 8.2500
## 578  2014-03-27 8.0780
## 579  2014-03-28 7.9690
## 580  2014-04-01 7.8610
## 581  2014-04-02 7.8520
## 582  2014-04-03 7.8720
## 583  2014-04-04 7.8830
## 584  2014-04-07 7.8590
## 585  2014-04-08 7.8520
## 586  2014-04-09 7.8520
## 587  2014-04-10 7.8600
## 588  2014-04-11 7.8570
## 589  2014-04-14 7.8540
## 590  2014-04-15 7.8650
## 591  2014-04-16 7.8860
## 592  2014-04-17 7.9050
## 593  2014-04-21 7.9410
## 594  2014-04-22 8.0350
## 595  2014-04-23 8.0870
## 596  2014-04-24 8.0480
## 597  2014-04-25 7.9710
## 598  2014-04-28 7.8980
## 599  2014-04-29 7.8980
## 600  2014-04-30 7.9340
## 601  2014-05-02 7.9460
## 602  2014-05-05 7.9570
## 603  2014-05-06 7.9620
## 604  2014-05-07 8.0100
## 605  2014-05-08 8.0940
## 606  2014-05-09 8.0480
## 607  2014-05-12 8.0190
## 608  2014-05-13 8.0520
## 609  2014-05-14 8.0230
## 610  2014-05-16 7.9170
## 611  2014-05-19 7.8550
## 612  2014-05-20 7.9130
## 613  2014-05-21 8.0020
## 614  2014-05-22 8.0630
## 615  2014-05-23 8.0220
## 616  2014-05-26 8.0430
## 617  2014-05-28 8.0500
## 618  2014-05-30 8.0610
## 619  2014-06-02 8.0630
## 620  2014-06-03 8.0300
## 621  2014-06-04 8.0280
## 622  2014-06-05 8.0270
## 623  2014-06-06 8.0160
## 624  2014-06-09 7.9760
## 625  2014-06-10 8.0050
## 626  2014-06-11 8.0370
## 627  2014-06-12 8.0350
## 628  2014-06-13 8.0170
## 629  2014-06-16 8.0260
## 630  2014-06-17 8.0460
## 631  2014-06-18 8.0920
## 632  2014-06-19 8.1110
## 633  2014-06-20 8.1050
## 634  2014-06-23 8.1410
## 635  2014-06-24 8.1010
## 636  2014-06-25 8.2030
## 637  2014-06-26 8.2570
## 638  2014-06-27 8.2940
## 639  2014-06-30 8.2410
## 640  2014-07-01 8.1780
## 641  2014-07-02 8.1060
## 642  2014-07-03 8.0950
## 643  2014-07-04 8.1350
## 644  2014-07-07 8.1300
## 645  2014-07-08 8.0620
## 646  2014-07-09 8.0620
## 647  2014-07-10 8.0150
## 648  2014-07-11 8.0630
## 649  2014-07-14 8.1650
## 650  2014-07-15 8.1670
## 651  2014-07-16 8.1340
## 652  2014-07-17 8.0700
## 653  2014-07-18 8.0600
## 654  2014-07-21 7.9960
## 655  2014-07-22 8.0100
## 656  2014-07-23 8.0460
## 657  2014-07-24 8.0360
## 658  2014-07-25 8.0250
## 659  2014-07-31 8.0250
## 660  2014-08-01 8.0250
## 661  2014-08-04 8.0770
## 662  2014-08-05 8.1650
## 663  2014-08-06 8.2150
## 664  2014-08-07 8.2300
## 665  2014-08-08 8.2830
## 666  2014-08-11 8.2930
## 667  2014-08-12 8.2500
## 668  2014-08-13 8.2430
## 669  2014-08-14 8.2090
## 670  2014-08-15 8.2090
## 671  2014-08-18 8.2230
## 672  2014-08-19 8.2900
## 673  2014-08-20 8.3140
## 674  2014-08-21 8.3560
## 675  2014-08-22 8.2740
## 676  2014-08-25 8.2280
## 677  2014-08-26 8.2590
## 678  2014-08-27 8.2910
## 679  2014-08-28 8.2780
## 680  2014-08-29 8.2200
## 681  2014-09-01 8.1720
## 682  2014-09-02 8.1890
## 683  2014-09-03 8.1010
## 684  2014-09-04 8.0390
## 685  2014-09-05 7.9760
## 686  2014-09-08 7.9570
## 687  2014-09-09 8.0440
## 688  2014-09-10 8.1200
## 689  2014-09-11 8.1600
## 690  2014-09-12 8.1700
## 691  2014-09-15 8.2560
## 692  2014-09-16 8.3030
## 693  2014-09-17 8.2840
## 694  2014-09-18 8.2820
## 695  2014-09-19 8.1850
## 696  2014-09-22 8.1840
## 697  2014-09-23 8.1850
## 698  2014-09-24 8.1690
## 699  2014-09-25 8.1560
## 700  2014-09-26 8.2200
## 701  2014-09-29 8.4360
## 702  2014-09-30 8.3970
## 703  2014-10-01 8.5100
## 704  2014-10-02 8.4120
## 705  2014-10-03 8.4550
## 706  2014-10-06 8.4510
## 707  2014-10-07 8.4680
## 708  2014-10-08 8.4670
## 709  2014-10-09 8.4550
## 710  2014-10-10 8.3660
## 711  2014-10-13 8.3790
## 712  2014-10-14 8.3330
## 713  2014-10-15 8.2380
## 714  2014-10-16 8.2890
## 715  2014-10-17 8.3270
## 716  2014-10-20 8.0700
## 717  2014-10-21 8.0180
## 718  2014-10-22 8.0340
## 719  2014-10-23 8.0280
## 720  2014-10-24 8.0100
## 721  2014-10-27 8.0150
## 722  2014-10-28 8.0570
## 723  2014-10-29 8.1070
## 724  2014-10-30 8.1120
## 725  2014-10-31 8.0490
## 726  2014-11-03 8.0000
## 727  2014-11-04 7.9470
## 728  2014-11-05 7.9260
## 729  2014-11-06 7.9820
## 730  2014-11-07 7.9970
## 731  2014-11-10 8.0120
## 732  2014-11-11 7.9940
## 733  2014-11-12 7.9880
## 734  2014-11-13 7.9790
## 735  2014-11-14 7.9440
## 736  2014-11-17 7.9090
## 737  2014-11-18 7.8960
## 738  2014-11-19 7.8980
## 739  2014-11-20 7.8500
## 740  2014-11-21 7.8070
## 741  2014-11-24 7.7620
## 742  2014-11-25 7.7340
## 743  2014-11-26 7.7230
## 744  2014-11-27 7.6980
## 745  2014-11-28 7.6960
## 746  2014-12-01 7.6800
## 747  2014-12-02 7.6970
## 748  2014-12-03 7.7960
## 749  2014-12-04 7.8900
## 750  2014-12-05 7.8540
## 751  2014-12-08 7.8610
## 752  2014-12-09 7.9600
## 753  2014-12-10 7.9800
## 754  2014-12-11 8.0170
## 755  2014-12-12 8.0870
## 756  2014-12-15 8.3090
## 757  2014-12-16 8.4270
## 758  2014-12-17 8.3720
## 759  2014-12-18 8.1530
## 760  2014-12-19 8.1030
## 761  2014-12-22 8.0300
## 762  2014-12-23 7.9130
## 763  2014-12-24 7.8650
## 764  2014-12-29 7.8770
## 765  2014-12-30 7.8530
## 766  2014-12-31 7.7930
## 767  2015-01-02 7.8130
## 768  2015-01-05 7.9170
## 769  2015-01-06 7.9790
## 770  2015-01-07 7.9310
## 771  2015-01-08 7.8200
## 772  2015-01-09 7.7370
## 773  2015-01-12 7.6990
## 774  2015-01-13 7.7160
## 775  2015-01-14 7.6650
## 776  2015-01-15 7.6330
## 777  2015-01-16 7.6040
## 778  2015-01-19 7.6230
## 779  2015-01-20 7.6280
## 780  2015-01-21 7.2780
## 781  2015-01-22 7.1750
## 782  2015-01-23 7.1220
## 783  2015-01-26 7.1300
## 784  2015-01-27 7.1380
## 785  2015-01-28 7.0860
## 786  2015-01-29 7.0930
## 787  2015-01-30 7.0410
## 788  2015-02-02 6.9840
## 789  2015-02-03 6.9260
## 790  2015-02-04 6.9320
## 791  2015-02-05 7.0310
## 792  2015-02-06 7.0420
## 793  2015-02-09 7.0530
## 794  2015-02-10 7.0930
## 795  2015-02-11 7.2210
## 796  2015-02-12 7.3850
## 797  2015-02-13 7.4200
## 798  2015-02-16 7.3920
## 799  2015-02-17 7.1730
## 800  2015-02-18 7.0140
## 801  2015-02-19 7.0140
## 802  2015-02-20 7.0880
## 803  2015-02-23 7.0570
## 804  2015-02-24 7.0410
## 805  2015-02-25 7.0110
## 806  2015-02-26 6.9410
## 807  2015-02-27 6.9020
## 808  2015-03-02 6.9240
## 809  2015-03-03 6.9620
## 810  2015-03-04 7.1460
## 811  2015-03-05 7.3130
## 812  2015-03-06 7.3260
## 813  2015-03-09 7.3990
## 814  2015-03-10 7.5030
## 815  2015-03-11 7.6380
## 816  2015-03-12 7.6140
## 817  2015-03-13 7.4220
## 818  2015-03-16 7.3890
## 819  2015-03-17 7.4470
## 820  2015-03-18 7.4220
## 821  2015-03-19 7.3590
## 822  2015-03-20 7.3530
## 823  2015-03-23 7.4080
## 824  2015-03-24 7.2580
## 825  2015-03-25 7.2360
## 826  2015-03-26 7.2910
## 827  2015-03-27 7.3040
## 828  2015-03-30 7.3900
## 829  2015-03-31 7.4110
## 830  2015-04-01 7.4350
## 831  2015-04-02 7.3900
## 832  2015-04-06 7.3900
## 833  2015-04-07 7.3120
## 834  2015-04-08 7.3210
## 835  2015-04-09 7.2610
## 836  2015-04-10 7.2320
## 837  2015-04-13 7.2410
## 838  2015-04-14 7.2690
## 839  2015-04-15 7.3600
## 840  2015-04-16 7.4190
## 841  2015-04-17 7.5400
## 842  2015-04-20 7.5240
## 843  2015-04-21 7.5270
## 844  2015-04-22 7.4800
## 845  2015-04-23 7.5430
## 846  2015-04-24 7.5210
## 847  2015-04-27 7.6000
## 848  2015-04-28 7.7350
## 849  2015-04-29 7.7620
## 850  2015-04-30 7.6920
## 851  2015-05-04 7.7330
## 852  2015-05-05 7.8260
## 853  2015-05-06 7.9560
## 854  2015-05-07 8.0430
## 855  2015-05-08 8.2010
## 856  2015-05-11 8.1180
## 857  2015-05-12 8.2510
## 858  2015-05-13 8.0860
## 859  2015-05-15 8.0910
## 860  2015-05-18 7.9670
## 861  2015-05-19 7.9910
## 862  2015-05-20 8.0430
## 863  2015-05-21 8.0940
## 864  2015-05-22 8.0860
## 865  2015-05-25 8.0860
## 866  2015-05-26 8.1720
## 867  2015-05-27 8.1570
## 868  2015-05-28 8.1300
## 869  2015-05-29 8.1660
## 870  2015-06-01 8.1770
## 871  2015-06-03 8.1980
## 872  2015-06-04 8.4110
## 873  2015-06-05 8.4450
## 874  2015-06-08 8.5170
## 875  2015-06-09 8.5360
## 876  2015-06-10 8.6400
## 877  2015-06-11 8.7150
## 878  2015-06-12 8.6730
## 879  2015-06-15 8.6750
## 880  2015-06-16 8.6550
## 881  2015-06-17 8.6220
## 882  2015-06-18 8.5090
## 883  2015-06-19 8.4700
## 884  2015-06-22 8.4260
## 885  2015-06-23 8.3520
## 886  2015-06-24 8.1930
## 887  2015-06-25 8.2430
## 888  2015-06-26 8.3120
## 889  2015-06-29 8.3590
## 890  2015-06-30 8.3800
## 891  2015-07-01 8.2760
## 892  2015-07-02 8.2900
## 893  2015-07-03 8.2680
## 894  2015-07-06 8.2590
## 895  2015-07-07 8.2690
## 896  2015-07-08 8.3940
## 897  2015-07-09 8.4340
## 898  2015-07-10 8.3930
## 899  2015-07-13 8.2900
## 900  2015-07-14 8.2900
## 901  2015-07-15 8.3000
## 902  2015-07-21 8.3340
## 903  2015-07-22 8.2980
## 904  2015-07-23 8.2690
## 905  2015-07-24 8.2800
## 906  2015-07-27 8.2990
## 907  2015-07-28 8.3560
## 908  2015-07-29 8.6500
## 909  2015-07-30 8.6370
## 910  2015-07-31 8.6030
## 911  2015-08-03 8.6210
## 912  2015-08-04 8.6330
## 913  2015-08-05 8.5050
## 914  2015-08-06 8.4930
## 915  2015-08-07 8.4560
## 916  2015-08-10 8.4560
## 917  2015-08-11 8.4890
## 918  2015-08-12 8.6240
## 919  2015-08-13 8.7050
## 920  2015-08-14 8.6880
## 921  2015-08-17 8.6880
## 922  2015-08-18 8.7120
## 923  2015-08-19 8.5960
## 924  2015-08-20 8.6630
## 925  2015-08-21 8.8810
## 926  2015-08-24 9.0090
## 927  2015-08-25 8.9830
## 928  2015-08-26 8.9250
## 929  2015-08-27 8.8160
## 930  2015-08-28 8.7460
## 931  2015-08-31 8.7860
## 932  2015-09-01 8.7750
## 933  2015-09-02 8.8060
## 934  2015-09-03 8.8840
## 935  2015-09-04 8.9310
## 936  2015-09-07 9.0470
## 937  2015-09-08 9.1940
## 938  2015-09-09 9.1250
## 939  2015-09-10 9.1410
## 940  2015-09-11 9.2540
## 941  2015-09-14 9.3020
## 942  2015-09-15 9.4080
## 943  2015-09-16 9.4980
## 944  2015-09-17 9.3480
## 945  2015-09-18 9.1080
## 946  2015-09-21 9.0630
## 947  2015-09-22 9.1120
## 948  2015-09-23 9.2160
## 949  2015-09-25 9.5090
## 950  2015-09-28 9.5890
## 951  2015-09-29 9.7700
## 952  2015-09-30 9.6240
## 953  2015-10-01 9.4190
## 954  2015-10-02 9.3700
## 955  2015-10-05 9.2390
## 956  2015-10-06 8.8630
## 957  2015-10-07 8.7100
## 958  2015-10-08 8.6930
## 959  2015-10-09 8.6990
## 960  2015-10-12 8.5460
## 961  2015-10-13 8.6080
## 962  2015-10-14 8.6080
## 963  2015-10-15 8.7070
## 964  2015-10-16 8.6820
## 965  2015-10-19 8.6790
## 966  2015-10-20 8.7020
## 967  2015-10-21 8.7540
## 968  2015-10-22 8.7780
## 969  2015-10-23 8.7050
## 970  2015-10-26 8.6640
## 971  2015-10-27 8.6670
## 972  2015-10-28 8.6540
## 973  2015-10-29 8.7110
## 974  2015-10-30 8.8030
## 975  2015-11-02 8.8720
## 976  2015-11-03 8.8550
## 977  2015-11-04 8.7520
## 978  2015-11-05 8.6850
## 979  2015-11-06 8.6350
## 980  2015-11-09 8.6890
## 981  2015-11-10 8.6950
## 982  2015-11-11 8.6280
## 983  2015-11-12 8.6410
## 984  2015-11-13 8.6700
## 985  2015-11-16 8.6650
## 986  2015-11-17 8.6770
## 987  2015-11-18 8.6210
## 988  2015-11-19 8.6280
## 989  2015-11-20 8.6570
## 990  2015-11-23 8.6580
## 991  2015-11-24 8.6660
## 992  2015-11-25 8.6280
## 993  2015-11-26 8.5800
## 994  2015-11-27 8.5880
## 995  2015-11-30 8.6050
## 996  2015-12-01 8.5520
## 997  2015-12-02 8.4570
## 998  2015-12-03 8.4890
## 999  2015-12-04 8.5040
## 1000 2015-12-07 8.6350
## 1001 2015-12-08 8.5810
## 1002 2015-12-09 8.5810
## 1003 2015-12-10 8.5840
## 1004 2015-12-11 8.6340
## 1005 2015-12-14 8.9350
## 1006 2015-12-15 9.1510
## 1007 2015-12-16 8.9640
## 1008 2015-12-17 8.8480
## 1009 2015-12-18 8.7990
## 1010 2015-12-21 8.7780
## 1011 2015-12-22 8.7610
## 1012 2015-12-23 8.7670
## 1013 2015-12-24 8.7910
## 1014 2015-12-28 8.8310
## 1015 2015-12-29 8.8670
## 1016 2015-12-30 8.8890
## 1017 2015-12-31 8.8720
## 1018 2016-01-04 8.8570
## 1019 2016-01-05 8.8280
## 1020 2016-01-06 8.8070
## 1021 2016-01-07 8.7930
## 1022 2016-01-08 8.7790
## 1023 2016-01-11 8.7950
## 1024 2016-01-12 8.6940
## 1025 2016-01-13 8.5850
## 1026 2016-01-14 8.5720
## 1027 2016-01-15 8.5410
## 1028 2016-01-18 8.6080
## 1029 2016-01-19 8.6860
## 1030 2016-01-20 8.5750
## 1031 2016-01-21 8.5470
## 1032 2016-01-22 8.4900
## 1033 2016-01-25 8.3840
## 1034 2016-01-26 8.4220
## 1035 2016-01-27 8.4450
## 1036 2016-01-28 8.4090
## 1037 2016-01-29 8.2770
## 1038 2016-02-01 8.1700
## 1039 2016-02-02 8.1150
## 1040 2016-02-03 8.1740
## 1041 2016-02-04 8.1260
## 1042 2016-02-05 8.0380
## 1043 2016-02-09 7.9960
## 1044 2016-02-10 8.0120
## 1045 2016-02-11 7.9490
## 1046 2016-02-12 7.9530
## 1047 2016-02-15 7.9550
## 1048 2016-02-16 7.9500
## 1049 2016-02-17 8.0420
## 1050 2016-02-18 8.0310
## 1051 2016-02-19 8.0820
## 1052 2016-02-22 8.1240
## 1053 2016-02-23 8.1480
## 1054 2016-02-24 8.2610
## 1055 2016-02-25 8.2600
## 1056 2016-02-26 8.2340
## 1057 2016-02-29 8.2440
## 1058 2016-03-01 8.2520
## 1059 2016-03-02 8.1780
## 1060 2016-03-03 8.0850
## 1061 2016-03-04 7.9910
## 1062 2016-03-07 7.8380
## 1063 2016-03-08 7.8690
## 1064 2016-03-09 7.8690
## 1065 2016-03-10 7.8750
## 1066 2016-03-11 7.8130
## 1067 2016-03-14 7.7300
## 1068 2016-03-15 7.7520
## 1069 2016-03-16 7.7720
## 1070 2016-03-17 7.7500
## 1071 2016-03-18 7.6370
## 1072 2016-03-21 7.6960
## 1073 2016-03-22 7.7680
## 1074 2016-03-23 7.7810
## 1075 2016-03-24 7.7830
## 1076 2016-03-28 7.8120
## 1077 2016-03-29 7.8330
## 1078 2016-03-30 7.7810
## 1079 2016-03-31 7.7130
## 1080 2016-04-01 7.5820
## 1081 2016-04-04 7.5960
## 1082 2016-04-05 7.6340
## 1083 2016-04-06 7.6010
## 1084 2016-04-07 7.5950
## 1085 2016-04-08 7.5770
## 1086 2016-04-11 7.5350
## 1087 2016-04-12 7.5290
## 1088 2016-04-13 7.4330
## 1089 2016-04-14 7.4350
## 1090 2016-04-15 7.4240
## 1091 2016-04-18 7.4260
## 1092 2016-04-19 7.4310
## 1093 2016-04-20 7.4120
## 1094 2016-04-21 7.4240
## 1095 2016-04-22 7.5530
## 1096 2016-04-25 7.6520
## 1097 2016-04-27 7.6279
## 1098 2016-04-28 7.6257
## 1099 2016-04-29 7.7157
## 1100 2016-05-03 7.6951
## 1101 2016-05-04 7.7049
## 1102 2016-05-05 7.7048
## 1103 2016-05-06 7.7148
## 1104 2016-05-09 7.7748
## 1105 2016-05-10 7.8147
## 1106 2016-05-11 7.8243
## 1107 2016-05-12 7.8342
## 1108 2016-05-13 7.7941
## 1109 2016-05-16 7.7540
## 1110 2016-05-17 7.7562
## 1111 2016-05-18 7.7259
## 1112 2016-05-19 7.8257
## 1113 2016-05-20 7.8756
## 1114 2016-05-23 7.8855
## 1115 2016-05-24 7.8954
## 1116 2016-05-25 7.8752
## 1117 2016-05-26 7.8486
## 1118 2016-05-27 7.8385
## 1119 2016-05-30 7.8484
## 1120 2016-05-31 7.8583
## 1121 2016-06-01 7.8480
## 1122 2016-06-02 7.8579
## 1123 2016-06-03 7.8378
## 1124 2016-06-06 7.7977
## 1125 2016-06-07 7.7502
## 1126 2016-06-08 7.7600
## 1127 2016-06-09 7.5906
## 1128 2016-06-10 7.6192
## 1129 2016-06-13 7.6431
## 1130 2016-06-14 7.6730
## 1131 2016-06-15 7.6961
## 1132 2016-06-16 7.6760
## 1133 2016-06-17 7.6859
## 1134 2016-06-20 7.6835
## 1135 2016-06-21 7.6969
## 1136 2016-06-22 7.6690
## 1137 2016-06-23 7.6454
## 1138 2016-06-24 7.7058
## 1139 2016-06-27 7.7380
## 1140 2016-06-28 7.8054
## 1141 2016-06-29 7.5528
## 1142 2016-06-30 7.4637
## 1143 2016-07-01 7.4636
## 1144 2016-07-04 7.3729
## 1145 2016-07-05 7.2556
## 1146 2016-07-06 7.2556
## 1147 2016-07-07 7.2556
## 1148 2016-07-08 7.2556
## 1149 2016-07-11 7.1207
## 1150 2016-07-12 7.1381
## 1151 2016-07-13 7.1325
## 1152 2016-07-14 7.2018
## 1153 2016-07-15 7.1769
## 1154 2016-07-18 7.2306
## 1155 2016-07-19 7.0946
## 1156 2016-07-20 7.0659
## 1157 2016-07-21 7.0460
## 1158 2016-07-22 7.0568
## 1159 2016-07-25 7.1515
## 1160 2016-07-26 7.0536
## 1161 2016-07-27 6.9922
## 1162 2016-07-28 6.9107
## 1163 2016-07-29 6.9133
## 1164 2016-08-01 6.9623
## 1165 2016-08-02 6.8685
## 1166 2016-08-03 6.9703
## 1167 2016-08-04 6.8628
## 1168 2016-08-05 6.8781
## 1169 2016-08-08 6.9337
## 1170 2016-08-09 6.9419
## 1171 2016-08-10 6.9105
## 1172 2016-08-11 6.9735
## 1173 2016-08-12 6.9729
## 1174 2016-08-15 6.8454
## 1175 2016-08-16 6.7913
## 1176 2016-08-17 6.8751
## 1177 2016-08-18 6.7677
## 1178 2016-08-19 6.7115
## 1179 2016-08-22 6.7964
## 1180 2016-08-23 6.7468
## 1181 2016-08-24 6.6572
## 1182 2016-08-25 7.0655
## 1183 2016-08-26 7.0072
## 1184 2016-08-29 7.1534
## 1185 2016-08-30 7.0907
## 1186 2016-08-31 7.1770
## 1187 2016-09-01 6.9829
## 1188 2016-09-02 7.2213
## 1189 2016-09-05 6.9565
## 1190 2016-09-06 6.8759
## 1191 2016-09-07 6.9276
## 1192 2016-09-08 6.8221
## 1193 2016-09-09 6.9542
## 1194 2016-09-12 6.9748
## 1195 2016-09-13 7.1060
## 1196 2016-09-14 7.1015
## 1197 2016-09-15 7.0678
## 1198 2016-09-16 7.0002
## 1199 2016-09-19 6.9739
## 1200 2016-09-20 6.9675
## 1201 2016-09-21 6.9379
## 1202 2016-09-22 6.8607
## 1203 2016-09-23 6.8925
## 1204 2016-09-26 6.9251
## 1205 2016-09-27 6.8778
## 1206 2016-09-28 6.8818
## 1207 2016-09-29 6.9790
## 1208 2016-09-30 7.0284
## 1209 2016-10-03 6.9658
## 1210 2016-10-04 6.9746
## 1211 2016-10-05 7.0112
## 1212 2016-10-06 6.9306
## 1213 2016-10-07 7.0474
## 1214 2016-10-10 7.1352
## 1215 2016-10-11 7.1793
## 1216 2016-10-12 7.0692
## 1217 2016-10-13 7.0675
## 1218 2016-10-14 6.9928
## 1219 2016-10-17 6.9822
## 1220 2016-10-18 7.0617
## 1221 2016-10-19 7.2004
## 1222 2016-10-20 7.0856
## 1223 2016-10-21 7.0260
## 1224 2016-10-24 7.0597
## 1225 2016-10-25 7.0596
## 1226 2016-10-26 7.1190
## 1227 2016-10-27 7.0931
## 1228 2016-10-28 7.3390
## 1229 2016-10-31 7.4461
## 1230 2016-11-01 7.3620
## 1231 2016-11-02 7.2650
## 1232 2016-11-03 7.3266
## 1233 2016-11-04 7.2989
## 1234 2016-11-07 7.3086
## 1235 2016-11-08 7.3042
## 1236 2016-11-09 7.4188
## 1237 2016-11-10 7.6263
## 1238 2016-11-11 7.9271
## 1239 2016-11-14 7.9635
## 1240 2016-11-15 7.7612
## 1241 2016-11-16 7.9605
## 1242 2016-11-17 7.7831
## 1243 2016-11-18 7.9938
## 1244 2016-11-21 7.8786
## 1245 2016-11-22 7.9322
## 1246 2016-11-23 8.1565
## 1247 2016-11-24 8.3416
## 1248 2016-11-25 8.4164
## 1249 2016-11-28 8.2899
## 1250 2016-11-29 8.1564
## 1251 2016-11-30 8.0269
## 1252 2016-12-01 7.9661
## 1253 2016-12-02 8.0426
## 1254 2016-12-05 8.0298
## 1255 2016-12-06 7.8858
## 1256 2016-12-07 7.5601
## 1257 2016-12-08 7.5302
## 1258 2016-12-09 7.6298
## 1259 2016-12-12 7.6236
## 1260 2016-12-13 7.8156
## 1261 2016-12-14 7.7641
## 1262 2016-12-15 7.9975
## 1263 2016-12-16 8.0619
## 1264 2016-12-19 7.9956
## 1265 2016-12-20 7.9118
## 1266 2016-12-21 7.9002
## 1267 2016-12-22 7.9107
## 1268 2016-12-23 7.9125
## 1269 2016-12-26 7.9621
## 1270 2016-12-27 7.9233
## 1271 2016-12-28 7.8862
## 1272 2016-12-29 7.9782
## 1273 2016-12-30 7.9227
## 1274 2017-01-02 7.9228
## 1275 2017-01-03 7.9481
## 1276 2017-01-04 7.8130
## 1277 2017-01-05 7.7228
## 1278 2017-01-06 7.5630
## 1279 2017-01-09 7.5921
## 1280 2017-01-10 7.5689
## 1281 2017-01-11 7.5837
## 1282 2017-01-12 7.4481
## 1283 2017-01-13 7.4339
## 1284 2017-01-16 7.4914
## 1285 2017-01-17 7.4699
## 1286 2017-01-18 7.4773
## 1287 2017-01-19 7.5496
## 1288 2017-01-20 7.5497
## 1289 2017-01-23 7.5179
## 1290 2017-01-24 7.4949
## 1291 2017-01-25 7.4951
## 1292 2017-01-26 7.5953
## 1293 2017-01-27 7.5984
## 1294 2017-01-30 7.5868
## 1295 2017-01-31 7.6263
## 1296 2017-02-01 7.6310
## 1297 2017-02-02 7.6297
## 1298 2017-02-03 7.5772
## 1299 2017-02-06 7.5598
## 1300 2017-02-07 7.5527
## 1301 2017-02-08 7.5326
## 1302 2017-02-09 7.4805
## 1303 2017-02-10 7.5010
## 1304 2017-02-13 7.5156
## 1305 2017-02-14 7.5377
## 1306 2017-02-15 7.5378
## 1307 2017-02-16 7.5218
## 1308 2017-02-17 7.5088
## 1309 2017-02-20 7.5307
## 1310 2017-02-21 7.5673
## 1311 2017-02-22 7.5545
## 1312 2017-02-23 7.5546
## 1313 2017-02-24 7.5255
## 1314 2017-02-27 7.5256
## 1315 2017-02-28 7.5287
## 1316 2017-03-01 7.5304
## 1317 2017-03-02 7.4942
## 1318 2017-03-03 7.4914
## 1319 2017-03-06 7.4740
## 1320 2017-03-07 7.4220
## 1321 2017-03-08 7.4194
## 1322 2017-03-09 7.4964
## 1323 2017-03-10 7.4602
## 1324 2017-03-13 7.4603
## 1325 2017-03-14 7.4241
## 1326 2017-03-15 7.3883
## 1327 2017-03-16 7.2517
## 1328 2017-03-17 7.2233
## 1329 2017-03-20 7.1384
## 1330 2017-03-21 7.1667
## 1331 2017-03-22 7.1527
## 1332 2017-03-23 7.1387
## 1333 2017-03-24 7.1246
## 1334 2017-03-27 7.1558
## 1335 2017-03-28 7.1559
## 1336 2017-03-29 7.1559
## 1337 2017-03-30 7.1560
## 1338 2017-03-31 7.1560
## 1339 2017-04-03 7.1561
## 1340 2017-04-04 7.0196
## 1341 2017-04-05 7.0547
## 1342 2017-04-06 7.1040
## 1343 2017-04-07 7.1394
## 1344 2017-04-10 7.1041
## 1345 2017-04-11 7.0691
## 1346 2017-04-12 7.0903
## 1347 2017-04-13 7.0410
## 1348 2017-04-14 7.0411
## 1349 2017-04-17 7.0551
## 1350 2017-04-18 7.0695
## 1351 2017-04-19 7.1048
## 1352 2017-04-20 7.1048
## 1353 2017-04-21 7.1191
## 1354 2017-04-25 7.0837
## 1355 2017-04-26 7.0487
## 1356 2017-04-27 7.0558
## 1357 2017-04-28 7.0417
## 1358 2017-05-02 7.0277
## 1359 2017-05-03 7.0278
## 1360 2017-05-04 7.0279
## 1361 2017-05-05 7.0915
## 1362 2017-05-08 7.0846
## 1363 2017-05-09 7.1274
## 1364 2017-05-10 7.2490
## 1365 2017-05-11 7.2490
## 1366 2017-05-12 7.1416
## 1367 2017-05-15 7.0493
## 1368 2017-05-16 7.0210
## 1369 2017-05-17 7.0350
## 1370 2017-05-18 7.1415
## 1371 2017-05-19 6.9996
## 1372 2017-05-22 6.9784
## 1373 2017-05-23 6.9431
## 1374 2017-05-24 6.9501
## 1375 2017-05-25 6.9500
## 1376 2017-05-26 6.9430
## 1377 2017-05-29 6.9500
## 1378 2017-05-30 6.9850
## 1379 2017-05-31 6.9568
## 1380 2017-06-01 6.9568
## 1381 2017-06-02 6.9568
## 1382 2017-06-05 6.9638
## 1383 2017-06-06 6.9356
## 1384 2017-06-07 6.9566
## 1385 2017-06-08 6.9284
## 1386 2017-06-09 6.8722
## 1387 2017-06-12 6.8792
## 1388 2017-06-13 6.8721
## 1389 2017-06-14 6.8580
## 1390 2017-06-15 6.8091
## 1391 2017-06-16 6.8020
## 1392 2017-06-19 6.7326
## 1393 2017-06-20 6.8017
## 1394 2017-06-21 6.8221
## 1395 2017-06-22 6.8221
## 1396 2017-06-23 6.8220
## 1397 2017-06-27 6.8220
## 1398 2017-06-28 6.8220
## 1399 2017-06-29 6.8220
## 1400 2017-06-30 6.8221
## 1401 2017-07-03 6.8641
## 1402 2017-07-04 6.7871
## 1403 2017-07-05 6.7869
## 1404 2017-07-06 6.9982
## 1405 2017-07-07 7.1774
## 1406 2017-07-10 7.1846
## 1407 2017-07-11 7.0838
## 1408 2017-07-12 7.0337
## 1409 2017-07-13 6.9981
## 1410 2017-07-14 6.9483
## 1411 2017-07-17 6.9412
## 1412 2017-07-18 6.9554
## 1413 2017-07-19 6.9057
## 1414 2017-07-20 6.9482
## 1415 2017-07-21 6.9269
## 1416 2017-07-24 6.9269
## 1417 2017-07-25 6.9552
## 1418 2017-07-26 6.9979
## 1419 2017-07-27 6.9836
## 1420 2017-07-28 7.0050
## 1421 2017-07-31 6.9480
## 1422 2017-08-01 6.9480
## 1423 2017-08-02 6.9195
## 1424 2017-08-03 6.9053
## 1425 2017-08-04 6.8982
## 1426 2017-08-07 6.8840
## 1427 2017-08-08 6.8345
## 1428 2017-08-09 6.8698
## 1429 2017-08-10 6.8839
## 1430 2017-08-11 6.9123
## 1431 2017-08-14 6.9051
## 1432 2017-08-15 6.9122
## 1433 2017-08-16 6.9264
## 1434 2017-08-17 6.9264
## 1435 2017-08-18 6.8979
## 1436 2017-08-21 6.9121
## 1437 2017-08-22 6.8766
## 1438 2017-08-23 6.8907
## 1439 2017-08-24 6.8552
## 1440 2017-08-25 6.7705
## 1441 2017-08-28 6.7634
## 1442 2017-08-29 6.7351
## 1443 2017-08-30 6.6720
## 1444 2017-08-31 6.6301
## 1445 2017-09-01 6.6301
## 1446 2017-09-04 6.6580
## 1447 2017-09-05 6.5745
## 1448 2017-09-06 6.5881
## 1449 2017-09-07 6.5534
## 1450 2017-09-08 6.4020
## 1451 2017-09-11 6.4293
## 1452 2017-09-12 6.4635
## 1453 2017-09-13 6.4701
## 1454 2017-09-14 6.5529
## 1455 2017-09-15 6.4975
## 1456 2017-09-18 6.4836
## 1457 2017-09-19 6.4557
## 1458 2017-09-20 6.4350
## 1459 2017-09-21 6.4312
## 1460 2017-09-22 6.4312
## 1461 2017-09-25 6.2575
## 1462 2017-09-26 6.3525
## 1463 2017-09-27 6.5034
## 1464 2017-09-28 6.7101
## 1465 2017-09-29 6.4549
## 1466 2017-10-02 6.5309
## 1467 2017-10-03 6.5308
## 1468 2017-10-04 6.4063
## 1469 2017-10-05 6.4820
## 1470 2017-10-06 6.5723
## 1471 2017-10-09 6.5862
## 1472 2017-10-10 6.5931
## 1473 2017-10-11 6.6069
## 1474 2017-10-12 6.6194
## 1475 2017-10-13 6.5579
## 1476 2017-10-16 6.5928
## 1477 2017-10-17 6.6419
## 1478 2017-10-18 6.6417
## 1479 2017-10-19 6.6206
## 1480 2017-10-20 6.6769
## 1481 2017-10-23 6.7477
## 1482 2017-10-24 6.7548
## 1483 2017-10-25 6.9052
## 1484 2017-10-26 6.8405
## 1485 2017-10-27 6.7700
## 1486 2017-10-30 6.8405
## 1487 2017-10-31 6.7618
## 1488 2017-11-01 6.7547
## 1489 2017-11-02 6.7120
## 1490 2017-11-03 6.6271
## 1491 2017-11-06 6.6765
## 1492 2017-11-07 6.6411
## 1493 2017-11-08 6.6596
## 1494 2017-11-09 6.6693
## 1495 2017-11-10 6.6977
## 1496 2017-11-13 6.6950
## 1497 2017-11-14 6.6832
## 1498 2017-11-15 6.6687
## 1499 2017-11-16 6.6970
## 1500 2017-11-17 6.6018
## 1501 2017-11-20 6.6117
## 1502 2017-11-21 6.6257
## 1503 2017-11-22 6.5971
## 1504 2017-11-23 6.5547
## 1505 2017-11-24 6.5687
## 1506 2017-11-27 6.6109
## 1507 2017-11-28 6.5825
## 1508 2017-11-29 6.5468
## 1509 2017-11-30 6.5255
## 1510 2017-12-01 6.5254
## 1511 2017-12-04 6.5677
## 1512 2017-12-05 6.5182
## 1513 2017-12-06 6.5389
## 1514 2017-12-07 6.5812
## 1515 2017-12-08 6.5457
## 1516 2017-12-11 6.5174
## 1517 2017-12-12 6.5314
## 1518 2017-12-13 6.5240
## 1519 2017-12-14 6.5027
## 1520 2017-12-15 6.4815
## 1521 2017-12-18 6.5306
## 1522 2017-12-19 6.4812
## 1523 2017-12-20 6.4805
## 1524 2017-12-21 6.3614
## 1525 2017-12-22 6.3543
## 1526 2017-12-25 6.3537
## 1527 2017-12-26 6.3537
## 1528 2017-12-27 6.3467
## 1529 2017-12-28 6.3396
## 1530 2017-12-29 6.3116
## 1531 2018-01-01 6.3114
## 1532 2018-01-02 6.2837
## 1533 2018-01-03 6.1934
## 1534 2018-01-04 6.1794
## 1535 2018-01-05 6.1586
## 1536 2018-01-08 6.1173
## 1537 2018-01-09 6.2133
## 1538 2018-01-10 6.2820
## 1539 2018-01-11 6.0925
## 1540 2018-01-12 6.0714
## 1541 2018-01-15 6.1234
## 1542 2018-01-16 5.9467
## 1543 2018-01-17 6.1572
## 1544 2018-01-18 6.1169
## 1545 2018-01-19 6.1222
## 1546 2018-01-22 6.2352
## 1547 2018-01-23 6.1629
## 1548 2018-01-24 6.1826
## 1549 2018-01-25 6.1630
## 1550 2018-01-26 6.3031
## 1551 2018-01-29 6.1002
## 1552 2018-01-30 6.5590
## 1553 2018-01-31 6.1954
## 1554 2018-02-01 6.2089
## 1555 2018-02-02 6.3523
## 1556 2018-02-05 6.3383
## 1557 2018-02-06 6.3560
## 1558 2018-02-07 6.3380
## 1559 2018-02-08 6.3139
## 1560 2018-02-09 6.4355
## 1561 2018-02-12 6.4089
## 1562 2018-02-13 6.4788
## 1563 2018-02-14 6.3932
## 1564 2018-02-15 6.5314
## 1565 2018-02-16 6.4273
## 1566 2018-02-19 6.4109
## 1567 2018-02-20 6.5310
## 1568 2018-02-21 6.3822
## 1569 2018-02-22 6.7059
## 1570 2018-02-23 6.4761
## 1571 2018-02-26 6.4502
## 1572 2018-02-27 6.5729
## 1573 2018-02-28 6.6709
## 1574 2018-03-01 6.5663
## 1575 2018-03-02 6.6018
## 1576 2018-03-05 6.7109
## 1577 2018-03-06 6.7422
## 1578 2018-03-07 6.6863
## 1579 2018-03-08 6.7935
## 1580 2018-03-09 6.8536
## 1581 2018-03-12 6.7312
## 1582 2018-03-13 6.5764
## 1583 2018-03-14 6.6375
## 1584 2018-03-15 6.7079
## 1585 2018-03-16 6.7151
## 1586 2018-03-19 6.7435
## 1587 2018-03-20 6.7437
## 1588 2018-03-21 6.7867
## 1589 2018-03-22 6.8154
## 1590 2018-03-23 6.9231
## 1591 2018-03-26 6.8157
## 1592 2018-03-27 6.8020
## 1593 2018-03-28 6.7381
## 1594 2018-03-29 6.6394
## 1595 2018-03-30 6.6395
## 1596 2018-04-02 6.6395
## 1597 2018-04-03 6.5695
## 1598 2018-04-04 6.6048
## 1599 2018-04-05 6.5909
## 1600 2018-04-06 6.6332
## 1601 2018-04-09 6.6333
## 1602 2018-04-10 6.6475
## 1603 2018-04-11 6.6198
## 1604 2018-04-12 6.6058
## 1605 2018-04-13 6.5919
## 1606 2018-04-16 6.6061
## 1607 2018-04-17 6.6485
## 1608 2018-04-18 6.6489
## 1609 2018-04-19 6.7341
## 1610 2018-04-20 6.8201
## 1611 2018-04-23 6.8923
## 1612 2018-04-24 6.9359
## 1613 2018-04-25 6.8209
## 1614 2018-04-26 7.0759
## 1615 2018-04-27 6.8215
## 1616 2018-04-30 6.9664
## 1617 2018-05-01 6.8222
## 1618 2018-05-02 6.9307
## 1619 2018-05-03 6.9673
## 1620 2018-05-04 7.0260
## 1621 2018-05-07 7.1891
## 1622 2018-05-08 7.3400
## 1623 2018-05-09 7.4161
## 1624 2018-05-10 7.3329
## 1625 2018-05-11 7.0422
## 1626 2018-05-14 7.0718
## 1627 2018-05-15 7.0645
## 1628 2018-05-16 7.2285
## 1629 2018-05-17 7.2062
## 1630 2018-05-18 7.4407
## 1631 2018-05-21 7.4945
## 1632 2018-05-22 7.5332
## 1633 2018-05-23 7.6891
## 1634 2018-05-24 7.5420
## 1635 2018-05-25 7.3283
## 1636 2018-05-28 7.1562
## 1637 2018-05-29 7.4206
## 1638 2018-05-30 7.0598
## 1639 2018-05-31 6.9277
## 1640 2018-06-01 6.9717
## 1641 2018-06-04 7.0085
## 1642 2018-06-05 7.1644
## 1643 2018-06-06 7.2265
## 1644 2018-06-07 7.2720
## 1645 2018-06-08 7.3785
## 1646 2018-06-11 7.3335
## 1647 2018-06-12 7.3335
## 1648 2018-06-13 7.3335
## 1649 2018-06-14 7.3335
## 1650 2018-06-15 7.3335
## 1651 2018-06-18 7.3335
## 1652 2018-06-19 7.3335
## 1653 2018-06-20 7.3335
## 1654 2018-06-21 7.4869
## 1655 2018-06-22 7.5801
## 1656 2018-06-25 7.6977
## 1657 2018-06-26 7.6587
## 1658 2018-06-27 7.7778
## 1659 2018-06-28 7.8577
## 1660 2018-06-29 7.7784
## 1661 2018-07-02 7.7787
## 1662 2018-07-03 7.9469
## 1663 2018-07-04 7.7245
## 1664 2018-07-05 7.7012
## 1665 2018-07-06 7.6229
## 1666 2018-07-09 7.4292
## 1667 2018-07-10 7.3527
## 1668 2018-07-11 7.5229
## 1669 2018-07-12 7.5077
## 1670 2018-07-13 7.5468
## 1671 2018-07-16 7.5471
## 1672 2018-07-17 7.5863
## 1673 2018-07-18 7.7288
## 1674 2018-07-19 7.8246
## 1675 2018-07-20 7.8810
## 1676 2018-07-23 7.7933
## 1677 2018-07-24 7.8096
## 1678 2018-07-25 7.7310
## 1679 2018-07-26 7.7870
## 1680 2018-07-27 7.6999
## 1681 2018-07-30 7.7002
## 1682 2018-07-31 7.7879
## 1683 2018-08-01 7.7094
## 1684 2018-08-02 7.8292
## 1685 2018-08-03 7.8296
## 1686 2018-08-06 7.7819
## 1687 2018-08-07 7.7504
## 1688 2018-08-08 7.6720
## 1689 2018-08-09 7.6250
## 1690 2018-08-10 7.7123
## 1691 2018-08-13 7.8323
## 1692 2018-08-14 8.0363
## 1693 2018-08-15 8.0122
## 1694 2018-08-16 7.9803
## 1695 2018-08-17 7.9807
## 1696 2018-08-20 7.8351
## 1697 2018-08-21 7.8201
## 1698 2018-08-22 7.8204
## 1699 2018-08-23 7.8365
## 1700 2018-08-24 7.8772
## 1701 2018-08-27 7.9993
## 1702 2018-08-28 7.9590
## 1703 2018-08-29 7.9520
## 1704 2018-08-30 8.0013
## 1705 2018-08-31 8.1829
## 1706 2018-09-03 8.3002
## 1707 2018-09-04 8.4188
## 1708 2018-09-05 8.5569
## 1709 2018-09-06 8.6788
## 1710 2018-09-07 8.4217
## 1711 2018-09-10 8.5589
## 1712 2018-09-11 8.5605
## 1713 2018-09-12 8.6642
## 1714 2018-09-13 8.5438
## 1715 2018-09-14 8.4417
## 1716 2018-09-17 8.4763
## 1717 2018-09-18 8.4427
## 1718 2018-09-19 8.2582
## 1719 2018-09-20 8.1917
## 1720 2018-09-21 8.1755
## 1721 2018-09-24 8.2002
## 1722 2018-09-25 8.2592
## 1723 2018-09-26 8.2438
## 1724 2018-09-27 8.1607
## 1725 2018-09-28 8.1612
## 1726 2018-10-01 8.1616
## 1727 2018-10-02 8.0543
## 1728 2018-10-03 8.3060
## 1729 2018-10-04 8.3149
## 1730 2018-10-05 8.4344
## 1731 2018-10-08 8.4349
## 1732 2018-10-09 8.5642
## 1733 2018-10-10 8.6613
## 1734 2018-10-11 8.6097
## 1735 2018-10-12 8.7852
## 1736 2018-10-15 8.9634
## 1737 2018-10-16 8.9640
## 1738 2018-10-17 8.6653
## 1739 2018-10-18 8.5270
## 1740 2018-10-19 8.7014
## 1741 2018-10-22 8.6670
## 1742 2018-10-23 8.6851
## 1743 2018-10-24 8.5649
## 1744 2018-10-25 8.5654
## 1745 2018-10-26 8.7055
## 1746 2018-10-29 8.7061
## 1747 2018-10-30 8.5845
## 1748 2018-10-31 8.6210
## 1749 2018-11-01 8.5001
## 1750 2018-11-02 8.3805
## 1751 2018-11-05 8.2807
## 1752 2018-11-06 8.2541
## 1753 2018-11-07 8.1546
## 1754 2018-11-08 8.1551
## 1755 2018-11-09 8.0554
## 1756 2018-11-12 8.0975
## 1757 2018-11-13 8.2322
## 1758 2018-11-14 8.2334
## 1759 2018-11-15 8.0830
## 1760 2018-11-16 8.0834
## 1761 2018-11-19 8.0504
## 1762 2018-11-20 8.0515
## 1763 2018-11-21 7.9768
## 1764 2018-11-22 7.9689
## 1765 2018-11-23 7.9197
## 1766 2018-11-26 7.8790
## 1767 2018-11-27 7.8793
## 1768 2018-11-28 7.8803
## 1769 2018-11-29 7.9135
## 1770 2018-11-30 7.8728
## 1771 2018-12-03 7.8076
## 1772 2018-12-04 7.8734
## 1773 2018-12-05 7.9569
## 1774 2018-12-06 7.9987
## 1775 2018-12-07 8.0407
## 1776 2018-12-10 8.0829
## 1777 2018-12-11 8.3801
## 1778 2018-12-12 8.2108
## 1779 2018-12-13 8.0848
## 1780 2018-12-14 8.0768
## 1781 2018-12-17 8.1613
## 1782 2018-12-18 8.1617
## 1783 2018-12-19 7.9960
## 1784 2018-12-20 8.0632
## 1785 2018-12-21 7.9634
## 1786 2018-12-24 7.9653
## 1787 2018-12-25 7.9653
## 1788 2018-12-26 7.9653
## 1789 2018-12-27 7.9657
## 1790 2018-12-28 7.9660
## 1791 2018-12-31 7.9672
## 1792 2019-01-01 7.9672
## 1793 2019-01-02 8.0110
## 1794 2019-01-03 8.0770
## 1795 2019-01-04 8.0830
## 1796 2019-01-07 7.8900
## 1797 2019-01-08 7.8940
## 1798 2019-01-09 7.9510
## 1799 2019-01-10 7.9220
## 1800 2019-01-11 7.9600
## 1801 2019-01-14 7.9790
## 1802 2019-01-15 8.0070
## 1803 2019-01-16 8.0720
## 1804 2019-01-17 8.0830
## 1805 2019-01-18 8.0880
## 1806 2019-01-21 8.0860
## 1807 2019-01-22 8.0970
## 1808 2019-01-23 8.0790
## 1809 2019-01-24 8.0980
## 1810 2019-01-25 8.1020
## 1811 2019-01-28 8.1030
## 1812 2019-01-29 8.1420
## 1813 2019-01-30 8.1620
## 1814 2019-01-31 8.0510
## 1815 2019-02-01 7.9090
## 1816 2019-02-04 7.8460
## 1817 2019-02-06 7.7760
## 1818 2019-02-07 7.7900
## 1819 2019-02-08 7.8560
## 1820 2019-02-11 7.9160
## 1821 2019-02-12 7.9380
## 1822 2019-02-13 7.8900
## 1823 2019-02-14 7.9660
## 1824 2019-02-15 8.0170
## 1825 2019-02-18 8.0060
## 1826 2019-02-19 7.9930
## 1827 2019-02-20 7.9120
## 1828 2019-02-21 7.9350
## 1829 2019-02-22 7.9570
## 1830 2019-02-25 7.8980
## 1831 2019-02-26 7.8290
## 1832 2019-02-27 7.7950
## 1833 2019-02-28 7.8010
## 1834 2019-03-01 7.8400
## 1835 2019-03-04 7.8600
## 1836 2019-03-05 7.8600
## 1837 2019-03-06 7.8850
## 1838 2019-03-08 7.9580
## 1839 2019-03-11 7.9590
## 1840 2019-03-12 7.8880
## 1841 2019-03-13 7.8610
## 1842 2019-03-14 7.8380
## 1843 2019-03-15 7.8020
## 1844 2019-03-18 7.7390
## 1845 2019-03-19 7.7330
## 1846 2019-03-20 7.7150
## 1847 2019-03-21 7.6160
## 1848 2019-03-22 7.5970
## 1849 2019-03-25 7.6480
## 1850 2019-03-26 7.6250
## 1851 2019-03-27 7.6220
## 1852 2019-03-28 7.6590
## 1853 2019-03-29 7.6600
## 1854 2019-04-01 7.5930
## 1855 2019-04-02 7.6040
## 1856 2019-04-04 7.5880
## 1857 2019-04-05 7.5630
## 1858 2019-04-08 7.6290
## 1859 2019-04-09 7.6570
## 1860 2019-04-10 7.6680
## 1861 2019-04-11 7.6700
## 1862 2019-04-12 7.6840
## 1863 2019-04-15 7.6650
## 1864 2019-04-16 7.6290
## 1865 2019-04-18 7.5820
## 1866 2019-04-22 7.6170
## 1867 2019-04-23 7.6520
## 1868 2019-04-24 7.6800
## 1869 2019-04-25 7.7370
## 1870 2019-04-26 7.7780
## 1871 2019-04-29 7.7800
## 1872 2019-04-30 7.8010
## 1873 2019-05-02 7.8530
## 1874 2019-05-03 7.8720
## 1875 2019-05-06 7.9310
## 1876 2019-05-07 7.9760
## 1877 2019-05-08 8.0260
## 1878 2019-05-09 8.0580
## 1879 2019-05-10 8.0260
## 1880 2019-05-13 8.0340
## 1881 2019-05-14 8.0660
## 1882 2019-05-15 8.0200
## 1883 2019-05-16 8.0120
## 1884 2019-05-17 8.0340
## 1885 2019-05-20 8.0910
## 1886 2019-05-21 8.0890
## 1887 2019-05-22 8.0870
## 1888 2019-05-23 8.0500
## 1889 2019-05-24 7.9310
## 1890 2019-05-27 7.9080
## 1891 2019-05-28 7.9590
## 1892 2019-05-29 8.0340
## 1893 2019-05-31 8.0230
## 1894 2019-06-10 7.7420
## 1895 2019-06-11 7.7180
## 1896 2019-06-12 7.7010
## 1897 2019-06-13 7.6960
## 1898 2019-06-14 7.6950
## 1899 2019-06-17 7.6650
## 1900 2019-06-18 7.6640
## 1901 2019-06-19 7.5770
## 1902 2019-06-20 7.4610
## 1903 2019-06-21 7.4130
## 1904 2019-06-24 7.4850
## 1905 2019-06-25 7.4480
## 1906 2019-06-26 7.4420
## 1907 2019-06-27 7.4190
## 1908 2019-06-28 7.3690
## 1909 2019-07-01 7.3670
## 1910 2019-07-02 7.3440
## 1911 2019-07-03 7.3020
## 1912 2019-07-04 7.2470
## 1913 2019-07-05 7.2170
## 1914 2019-07-08 7.2480
## 1915 2019-07-09 7.2680
## 1916 2019-07-10 7.3330
## 1917 2019-07-11 7.2290
## 1918 2019-07-12 7.2030
## 1919 2019-07-15 7.1220
## 1920 2019-07-16 7.1030
## 1921 2019-07-17 7.1160
## 1922 2019-07-18 7.1430
## 1923 2019-07-19 7.1400
## 1924 2019-07-22 7.1790
## 1925 2019-07-23 7.2620
## 1926 2019-07-24 7.2660
## 1927 2019-07-25 7.1940
## 1928 2019-07-26 7.2150
## 1929 2019-07-29 7.2570
## 1930 2019-07-30 7.3130
## 1931 2019-07-31 7.3780
## 1932 2019-08-01 7.4800
## 1933 2019-08-02 7.5430
## 1934 2019-08-05 7.6250
## 1935 2019-08-06 7.6660
## 1936 2019-08-07 7.5100
## 1937 2019-08-08 7.4090
## 1938 2019-08-09 7.3080
## 1939 2019-08-12 7.3430
## 1940 2019-08-13 7.4610
## 1941 2019-08-14 7.4370
## 1942 2019-08-15 7.4600
## 1943 2019-08-16 7.4130
## 1944 2019-08-19 7.3260
## 1945 2019-08-20 7.3490
## 1946 2019-08-21 7.3140
## 1947 2019-08-22 7.2440
## 1948 2019-08-23 7.2420
## 1949 2019-08-26 7.2860
## 1950 2019-08-27 7.2780
## 1951 2019-08-28 7.3270
## 1952 2019-08-29 7.3490
## 1953 2019-08-30 7.3540
## 1954 2019-09-02 7.3330
## 1955 2019-09-03 7.3590
## 1956 2019-09-04 7.3510
## 1957 2019-09-05 7.3190
## 1958 2019-09-06 7.3150
## 1959 2019-09-09 7.2940
## 1960 2019-09-10 7.2550
## 1961 2019-09-11 7.2570
## 1962 2019-09-12 7.2560
## 1963 2019-09-13 7.2030
## 1964 2019-09-16 7.2380
## 1965 2019-09-17 7.2690
## 1966 2019-09-18 7.2260
## 1967 2019-09-19 7.2110
## 1968 2019-09-20 7.2430
## 1969 2019-09-23 7.2460
## 1970 2019-09-24 7.3120
## 1971 2019-09-25 7.3290
## 1972 2019-09-26 7.3180
## 1973 2019-09-27 7.3330
## 1974 2019-09-30 7.2960
## 1975 2019-10-01 7.3010
## 1976 2019-10-02 7.2750
## 1977 2019-10-03 7.2600
## 1978 2019-10-04 7.2300
## 1979 2019-10-07 7.2400
## 1980 2019-10-08 7.2570
## 1981 2019-10-09 7.2710
## 1982 2019-10-10 7.2820
## 1983 2019-10-11 7.2540
## 1984 2019-10-14 7.2120
## 1985 2019-10-15 7.2200
## 1986 2019-10-16 7.2995
## 1987 2019-10-17 7.2465
## 1988 2019-10-18 7.2385
## 1989 2019-10-21 7.2380
## 1990 2019-10-22 7.2050
## 1991 2019-10-23 7.1885
## 1992 2019-10-24 7.1695
## 1993 2019-10-25 7.1990
## 1994 2019-10-28 7.1495
## 1995 2019-10-29 7.1400
## 1996 2019-10-30 7.1390
## 1997 2019-10-31 7.1105
## 1998 2019-11-01 7.1295
## 1999 2019-11-04 7.0980
## 2000 2019-11-05 7.0790
## 2001 2019-11-06 7.0690
## 2002 2019-11-07 7.1080
## 2003 2019-11-08 7.0735
## 2004 2019-11-11 7.1170
## 2005 2019-11-12 7.1485
## 2006 2019-11-13 7.1695
## 2007 2019-11-14 7.1850
## 2008 2019-11-15 7.1475
## 2009 2019-11-18 7.1130
## 2010 2019-11-19 7.1330
## 2011 2019-11-20 7.1505
## 2012 2019-11-21 7.1865
## 2013 2019-11-22 7.1695
## 2014 2019-11-25 7.1720
## 2015 2019-11-26 7.1745
## 2016 2019-11-27 7.1905
## 2017 2019-11-28 7.1655
## 2018 2019-11-29 7.1795
## 2019 2019-12-02 7.2375
## 2020 2019-12-03 7.2735
## 2021 2019-12-04 7.2755
## 2022 2019-12-05 7.2290
## 2023 2019-12-06 7.2090
## 2024 2019-12-09 7.2215
## 2025 2019-12-10 7.2250
## 2026 2019-12-11 7.2345
## 2027 2019-12-12 7.3035
## 2028 2019-12-13 7.3320
## 2029 2019-12-16 7.3595
## 2030 2019-12-17 7.4200
## 2031 2019-12-18 7.4510
## 2032 2019-12-19 7.3465
## 2033 2019-12-20 7.2845
## 2034 2019-12-23 7.2535
## 2035 2019-12-24 7.2050
## 2036 2019-12-26 7.2320
## 2037 2019-12-27 7.1910
## 2038 2019-12-30 7.1945
## 2039 2019-12-31 7.1485
## 2040 2020-01-01 7.1015
## 2041 2020-01-02 7.1770
## 2042 2020-01-03 7.1685
## 2043 2020-01-06 7.2315
## 2044 2020-01-07 7.2190
## 2045 2020-01-08 7.1730
## 2046 2020-01-09 7.1235
## 2047 2020-01-10 7.0330
## 2048 2020-01-13 6.9595
## 2049 2020-01-14 6.9570
## 2050 2020-01-15 6.9820
## 2051 2020-01-16 6.9475
## 2052 2020-01-17 6.9275
## 2053 2020-01-20 6.9215
## 2054 2020-01-21 6.8785
## 2055 2020-01-22 6.8060
## 2056 2020-01-23 6.7630
## 2057 2020-01-24 6.7025
## 2058 2020-01-27 6.7580
## 2059 2020-01-28 6.8690
## 2060 2020-01-29 6.7400
## 2061 2020-01-30 6.7370
## 2062 2020-01-31 6.7330
## 2063 2020-02-03 6.7855
## 2064 2020-02-04 6.7545
## 2065 2020-02-05 6.6945
## 2066 2020-02-06 6.6645
## 2067 2020-02-07 6.6650
## 2068 2020-02-10 6.5920
## 2069 2020-02-11 6.5800
## 2070 2020-02-12 6.5570
## 2071 2020-02-13 6.5610
## 2072 2020-02-14 6.5750
## 2073 2020-02-17 6.5740
## 2074 2020-02-18 6.5480
## 2075 2020-02-19 6.5270
## 2076 2020-02-20 6.5160
## 2077 2020-02-21 6.5420
## 2078 2020-02-24 6.5250
## 2079 2020-02-25 6.5460
## 2080 2020-02-26 6.5820
## 2081 2020-02-27 6.7160
## 2082 2020-02-28 6.8870
## 2083 2020-03-02 6.9630
## 2084 2020-03-03 6.8510
## 2085 2020-03-04 6.6310
## 2086 2020-03-05 6.5520
## 2087 2020-03-06 6.6540
## 2088 2020-03-09 6.9030
## 2089 2020-03-10 6.9740
## 2090 2020-03-11 6.9790
## 2091 2020-03-12 7.2480
## 2092 2020-03-13 7.2960
## 2093 2020-03-16 7.3200
## 2094 2020-03-17 7.5470
## 2095 2020-03-18 7.5810
## 2096 2020-03-19 7.9140
## 2097 2020-03-20 8.0990
## 2098 2020-03-23 8.2450
## 2099 2020-03-24 8.3220
## 2100 2020-03-26 8.2750
## 2101 2020-03-27 7.9070
## 2102 2020-03-30 7.8630
## 2103 2020-03-31 7.9070
## 2104 2020-04-01 7.9380
## 2105 2020-04-02 8.0380
## 2106 2020-04-03 8.0960
## 2107 2020-04-06 8.1770
## 2108 2020-04-07 8.1390
## 2109 2020-04-08 8.1010
## 2110 2020-04-09 8.1150
## 2111 2020-04-13 8.0300
## 2112 2020-04-14 7.9270
## 2113 2020-04-15 7.9290
## 2114 2020-04-16 7.9690
## 2115 2020-04-17 7.9270
## 2116 2020-04-20 7.8520
## 2117 2020-04-21 7.7770
## 2118 2020-04-22 7.8390
## 2119 2020-04-23 7.8420
## 2120 2020-04-24 7.9240
## 2121 2020-04-27 7.9920
## 2122 2020-04-28 8.0950
## 2123 2020-04-29 8.0770
## 2124 2020-04-30 7.8920
## 2125 2020-05-04 7.9650
## 2126 2020-05-05 8.0730
## 2127 2020-05-06 8.0850
## 2128 2020-05-08 8.0920
## 2129 2020-05-11 8.0770
## 2130 2020-05-12 8.0000
## 2131 2020-05-13 7.8980
## 2132 2020-05-14 7.8610
## 2133 2020-05-15 7.8090
## 2134 2020-05-18 7.7450
## 2135 2020-05-19 7.7230
## 2136 2020-05-20 7.6760
## 2137 2020-05-26 7.3300
## 2138 2020-05-27 7.3460
## 2139 2020-05-28 7.3600
## 2140 2020-05-29 7.3400
## 2141 2020-06-02 7.2260
## 2142 2020-06-03 7.0120
## 2143 2020-06-04 7.0740
## 2144 2020-06-05 7.1090
## 2145 2020-06-08 7.2070
## 2146 2020-06-09 7.2780
## 2147 2020-06-10 7.2650
## 2148 2020-06-11 7.2000
## 2149 2020-06-12 7.2440
## 2150 2020-06-15 7.2390
## 2151 2020-06-16 7.1850
## 2152 2020-06-17 7.1630
## 2153 2020-06-18 7.1880
## 2154 2020-06-19 7.1850
## 2155 2020-06-22 7.2180
## 2156 2020-06-23 7.1680
## 2157 2020-06-24 7.1550
## 2158 2020-06-25 7.1840
## 2159 2020-06-26 7.1940
## 2160 2020-06-29 7.2330
## 2161 2020-06-30 7.2150
## 2162 2020-07-01 7.2130
## 2163 2020-07-02 7.2330
## 2164 2020-07-03 7.2390
## 2165 2020-07-06 7.2470
## 2166 2020-07-07 7.1950
## 2167 2020-07-08 7.1280
## 2168 2020-07-09 7.0890
## 2169 2020-07-10 7.1120
## 2170 2020-07-13 7.0800
## 2171 2020-07-14 7.0820
## 2172 2020-07-15 7.0660
## 2173 2020-07-16 7.0440
## 2174 2020-07-17 7.0610
## 2175 2020-07-20 7.0740
## 2176 2020-07-21 7.0510
## 2177 2020-07-22 6.9920
## 2178 2020-07-23 6.9090
## 2179 2020-07-24 6.8660
## 2180 2020-07-27 6.8700
## 2181 2020-07-28 6.8470
## 2182 2020-07-29 6.8260
## 2183 2020-07-30 6.8250
## 2184 2020-08-03 6.8380
## 2185 2020-08-04 6.8390
## 2186 2020-08-05 6.8320
## 2187 2020-08-06 6.7990
## 2188 2020-08-07 6.7870
## 2189 2020-08-10 6.7970
## 2190 2020-08-11 6.7910
## 2191 2020-08-12 6.7610
## 2192 2020-08-13 6.7650
## 2193 2020-08-14 6.7660
## 2194 2020-08-18 6.7580
## 2195 2020-08-19 6.7260
## 2196 2020-08-24 6.7360
## 2197 2020-08-25 6.7170
## 2198 2020-08-26 6.7550
## 2199 2020-08-27 6.8100
## 2200 2020-08-28 6.8570
## 2201 2020-08-31 6.8640
## 2202 2020-09-01 6.8640
## 2203 2020-09-02 6.9080
## 2204 2020-09-03 6.9490
## 2205 2020-09-04 6.9480
## 2206 2020-09-07 6.9100
## 2207 2020-09-08 6.8830
## 2208 2020-09-09 6.8970
## 2209 2020-09-10 6.9010
## 2210 2020-09-11 6.9740
## 2211 2020-09-14 6.9430
## 2212 2020-09-15 6.9130
## 2213 2020-09-16 6.9150
## 2214 2020-09-17 6.9220
## 2215 2020-09-18 6.9150
## 2216 2020-09-21 6.8770
## 2217 2020-09-22 6.8900
## 2218 2020-09-23 6.9050
## 2219 2020-09-24 6.9120
## 2220 2020-09-25 6.9150
## 2221 2020-09-28 6.9150
## 2222 2020-09-29 6.9750
## 2223 2020-09-30 6.9300
## 2224 2020-10-01 6.9360
## 2225 2020-10-02 6.9220
## 2226 2020-10-05 6.9190
## 2227 2020-10-06 6.8950
## 2228 2020-10-07 6.8960
## 2229 2020-10-08 6.8990
## 2230 2020-10-09 6.9000
## 2231 2020-10-12 6.8990
## 2232 2020-10-13 6.8830
## 2233 2020-10-14 6.8600
## 2234 2020-10-15 6.8170
## 2235 2020-10-16 6.7590
## 2236 2020-10-19 6.6900
## 2237 2020-10-20 6.6590
## 2238 2020-10-21 6.6200
## 2239 2020-10-22 6.6080
## 2240 2020-10-23 6.6290
## 2241 2020-10-26 6.6110
## 2242 2020-10-27 6.6090
## 2243 2020-10-28 6.7030
## 2244 2020-11-02 6.6120
## 2245 2020-11-03 6.6010
## 2246 2020-11-04 6.6290
## 2247 2020-11-05 6.6090
## 2248 2020-11-06 6.3850
## 2249 2020-11-09 6.2630
## 2250 2020-11-10 6.2610
## 2251 2020-11-11 6.3150
## 2252 2020-11-12 6.3260
## 2253 2020-11-13 6.3240
## 2254 2020-11-16 6.2820
## 2255 2020-11-17 6.2070
## 2256 2020-11-18 6.1810
## 2257 2020-11-19 6.1780
## 2258 2020-11-20 6.2000
## 2259 2020-11-23 6.2390
## 2260 2020-11-24 6.2340
## 2261 2020-11-25 6.2260
## 2262 2020-11-26 6.2160
## 2263 2020-11-27 6.2180
## 2264 2020-11-30 6.1880
## 2265 2020-12-01 6.1850
## 2266 2020-12-02 6.1780
## 2267 2020-12-03 6.2090
## 2268 2020-12-04 6.1980
## 2269 2020-12-07 6.2380
## 2270 2020-12-08 6.2150
## 2271 2020-12-10 6.1950
## 2272 2020-12-11 6.1820
## 2273 2020-12-14 6.1600
## 2274 2020-12-15 6.1250
## 2275 2020-12-16 6.1010
## 2276 2020-12-17 6.0070
## 2277 2020-12-18 5.9760
## 2278 2020-12-21 6.0380
## 2279 2020-12-22 6.1100
## 2280 2020-12-23 6.0970
## 2281 2020-12-28 6.0370
## 2282 2020-12-29 5.9090
## 2283 2020-12-30 5.9420
## 2284 2021-01-04 5.9490
## 2285 2021-01-05 5.9980
## 2286 2021-01-06 6.0630
## 2287 2021-01-07 6.0310
## 2288 2021-01-08 6.1280
## 2289 2021-01-11 6.2180
## 2290 2021-01-12 6.2620
## 2291 2021-01-13 6.2180
## 2292 2021-01-14 6.2100
## 2293 2021-01-15 6.2090
## 2294 2021-01-18 6.2130
## 2295 2021-01-19 6.2920
## 2296 2021-01-20 6.2750
## 2297 2021-01-21 6.2910
## 2298 2021-01-22 6.2880
## 2299 2021-01-25 6.2910
## 2300 2021-01-26 6.2880
## 2301 2021-01-27 6.3050
## 2302 2021-01-28 6.2560
## 2303 2021-01-29 6.2570
## 2304 2021-02-01 6.2190
## 2305 2021-02-02 6.1790
## 2306 2021-02-03 6.1780
## 2307 2021-02-04 6.2000
## 2308 2021-02-05 6.1650
## 2309 2021-02-08 6.1960
## 2310 2021-02-09 6.2210
## 2311 2021-02-11 6.2410
## 2312 2021-02-15 6.2460
## 2313 2021-02-16 6.2840
## 2314 2021-02-17 6.3720
## 2315 2021-02-18 6.5320
## 2316 2021-02-19 6.5990
## 2317 2021-02-22 6.6610
## 2318 2021-02-23 6.6480
## 2319 2021-02-24 6.5550
## 2320 2021-02-26 6.5980
## 2321 2021-03-01 6.5900
## 2322 2021-03-02 6.5860
## 2323 2021-03-03 6.5690
## 2324 2021-03-04 6.6060
## 2325 2021-03-05 6.6250
## 2326 2021-03-08 6.7570
## 2327 2021-03-09 6.8170
## 2328 2021-03-10 6.7230
## 2329 2021-03-12 6.8060
## 2330 2021-03-15 6.7580
## 2331 2021-03-16 6.7470
## 2332 2021-03-17 6.7570
## 2333 2021-03-18 6.7520
## 2334 2021-03-19 6.8210
## 2335 2021-03-22 6.8100
## 2336 2021-03-23 6.7730
## 2337 2021-03-24 6.7360
## 2338 2021-03-25 6.7290
## 2339 2021-03-26 6.7490
## 2340 2021-03-29 6.7560
## 2341 2021-03-30 6.7940
## 2342 2021-03-31 6.8140
## 2343 2021-04-01 6.7610
## 2344 2021-04-05 6.6170
## 2345 2021-04-06 6.6690
## 2346 2021-04-07 6.5400
## 2347 2021-04-08 6.4570
## 2348 2021-04-09 6.4530
## 2349 2021-04-12 6.5120
## 2350 2021-04-13 6.5230
## 2351 2021-04-14 6.5730
## 2352 2021-04-15 6.5690
## 2353 2021-04-16 6.5060
## 2354 2021-04-19 6.4761
## 2355 2021-04-20 6.4372
## 2356 2021-04-21 6.4496
## 2357 2021-04-22 6.4399
## 2358 2021-04-23 6.4440
## 2359 2021-04-26 6.4426
## 2360 2021-04-27 6.4509
## 2361 2021-04-28 6.4829
## 2362 2021-04-29 6.4745
## 2363 2021-04-30 6.4871
## 2364 2021-05-03 6.4982
## 2365 2021-05-04 6.4383
## 2366 2021-05-05 6.4564
## 2367 2021-05-06 6.4354
## 2368 2021-05-07 6.4132
## 2369 2021-05-10 6.4061
## 2370 2021-05-11 6.4047
## 2371 2021-05-12 6.4047
## 2372 2021-05-13 6.4047
## 2373 2021-05-14 6.4047
## 2374 2021-05-17 6.4367
## 2375 2021-05-18 6.4814
## 2376 2021-05-19 6.4688
## 2377 2021-05-20 6.5010
## 2378 2021-05-21 6.4898
## 2379 2021-05-24 6.4520
## 2380 2021-05-25 6.4410
## 2381 2021-05-28 6.4260
## 2382 2021-05-31 6.4450
## 2383 2021-06-02 6.4490
## 2384 2021-06-03 6.4540
## 2385 2021-06-04 6.4400
## 2386 2021-06-07 6.4390
## 2387 2021-06-08 6.4460
## 2388 2021-06-09 6.4370
## 2389 2021-06-10 6.3450
## 2390 2021-06-11 6.4340
## 2391 2021-06-14 6.3580
## 2392 2021-06-15 6.4180
## 2393 2021-06-16 6.4600
## 2394 2021-06-17 6.4760
## 2395 2021-06-18 6.5640
## 2396 2021-06-21 6.5630
## 2397 2021-06-22 6.6390
## 2398 2021-06-23 6.6290
## 2399 2021-06-24 6.6100
## 2400 2021-06-25 6.5270
## 2401 2021-06-28 6.5910
## 2402 2021-06-29 6.6100
## 2403 2021-06-30 6.6300
## 2404 2021-07-01 6.6140
## 2405 2021-07-02 6.6360
## 2406 2021-07-05 6.6440
## 2407 2021-07-06 6.5840
## 2408 2021-07-07 6.5530
## 2409 2021-07-08 6.5310
## 2410 2021-07-09 6.5540
## 2411 2021-07-12 6.5390
## 2412 2021-07-13 6.5160
## 2413 2021-07-14 6.5060
## 2414 2021-07-15 6.4500
## 2415 2021-07-16 6.4370
## 2416 2021-07-19 6.3430
## 2417 2021-07-21 6.3270
## 2418 2021-07-22 6.3070
## 2419 2021-07-23 6.2980
## 2420 2021-07-26 6.3140
## 2421 2021-07-27 6.3060
## 2422 2021-07-28 6.3090
## 2423 2021-07-29 6.3060
## 2424 2021-07-30 6.3070
## 2425 2021-08-02 6.3040
## 2426 2021-08-03 6.2760
## 2427 2021-08-04 6.2560
## 2428 2021-08-05 6.2690
## 2429 2021-08-06 6.2880
## 2430 2021-08-09 6.3440
## 2431 2021-08-10 6.3360
## 2432 2021-08-11 6.3510
## 2433 2021-08-12 6.3410
## 2434 2021-08-13 6.3790
## 2435 2021-08-16 6.3500
## 2436 2021-08-18 6.3220
## 2437 2021-08-19 6.3250
## 2438 2021-08-20 6.3470
## 2439 2021-08-23 6.3800
## 2440 2021-08-24 6.3600
## 2441 2021-08-25 6.2440
## 2442 2021-08-26 6.1750
## 2443 2021-08-27 6.1660
## 2444 2021-08-30 6.1410
## 2445 2021-08-31 6.0770
## 2446 2021-09-01 6.0560
## 2447 2021-09-02 6.1130
## 2448 2021-09-03 6.1320
## 2449 2021-09-06 6.0930
## 2450 2021-09-07 6.1160
## 2451 2021-09-08 6.1510
## 2452 2021-09-09 6.1910
## 2453 2021-09-10 6.1550
## 2454 2021-09-13 6.1620
## 2455 2021-09-14 6.1710
## 2456 2021-09-15 6.1730
## 2457 2021-09-16 6.1600
## 2458 2021-09-17 6.1630
## 2459 2021-09-20 6.1770
## 2460 2021-09-21 6.1990
## 2461 2021-09-22 6.2060
## 2462 2021-09-23 6.2330
## 2463 2021-09-24 6.2380
## 2464 2021-09-27 6.2440
## 2465 2021-09-28 6.3130
## 2466 2021-09-29 6.3330
## 2467 2021-09-30 6.3530
## 2468 2021-10-01 6.3590
## 2469 2021-10-04 6.3330
## 2470 2021-10-05 6.3220
## 2471 2021-10-06 6.3100
## 2472 2021-10-07 6.3280
## 2473 2021-10-08 6.3500
## 2474 2021-10-11 6.3630
## 2475 2021-10-12 6.3720
## 2476 2021-10-13 6.3420
## 2477 2021-10-14 6.2940
## 2478 2021-10-15 6.2690
## 2479 2021-10-18 6.2100
## 2480 2021-10-19 6.2090
## 2481 2021-10-21 6.2050
## 2482 2021-10-22 6.1830
## 2483 2021-10-25 6.1690
## 2484 2021-10-26 6.1540
## 2485 2021-10-27 6.1530
## 2486 2021-10-28 6.1580
## 2487 2021-10-29 6.1690
## 2488 2021-11-01 6.2290
## 2489 2021-11-02 6.2410
## 2490 2021-11-03 6.2280
## 2491 2021-11-04 6.2250
## 2492 2021-11-05 6.2080
## 2493 2021-11-08 6.1780
## 2494 2021-11-09 6.1650
## 2495 2021-11-10 6.1570
## 2496 2021-11-11 6.1700
## 2497 2021-11-12 6.2010
## 2498 2021-11-15 6.1880
## 2499 2021-11-16 6.1970
## 2500 2021-11-17 6.1810
## 2501 2021-11-18 6.1900
## 2502 2021-11-19 6.1760
## 2503 2021-11-22 6.1890
## 2504 2021-11-23 6.1770
## 2505 2021-11-24 6.1880
## 2506 2021-11-25 6.1960
## 2507 2021-11-26 6.2270
## 2508 2021-11-29 6.2220
## 2509 2021-11-30 6.2670
## 2510 2021-12-01 6.2930
## 2511 2021-12-02 6.3820
## 2512 2021-12-03 6.3930
## 2513 2021-12-06 6.4160
## 2514 2021-12-07 6.4180
## 2515 2021-12-08 6.3820
## 2516 2021-12-09 6.3290
## 2517 2021-12-10 6.3080
## 2518 2021-12-13 6.3140
## 2519 2021-12-14 6.3300
## 2520 2021-12-15 6.4000
## 2521 2021-12-16 6.4220
## 2522 2021-12-17 6.4120
## 2523 2021-12-20 6.4400
## 2524 2021-12-21 6.4230
## 2525 2021-12-22 6.4000
## 2526 2021-12-23 6.3890
## 2527 2021-12-24 6.3720
## 2528 2021-12-27 6.3470
## 2529 2021-12-28 6.3540
## 2530 2021-12-29 6.3620
## 2531 2021-12-30 6.3760
## 2532 2021-12-31 6.3680
## 2533 2022-01-03 6.3680
## 2534 2022-01-04 6.4090
## 2535 2022-01-05 6.3040
## 2536 2022-01-06 6.3560
## 2537 2022-01-07 6.4230
## 2538 2022-01-10 6.4630
## 2539 2022-01-11 6.4470
## 2540 2022-01-12 6.4260
## 2541 2022-01-13 6.4120
## 2542 2022-01-14 6.4030
## 2543 2022-01-17 6.3890
## 2544 2022-01-18 6.3960
## 2545 2022-01-19 6.4140
## 2546 2022-01-20 6.4220
## 2547 2022-01-21 6.4250
## 2548 2022-01-24 6.4180
## 2549 2022-01-25 6.4080
## 2550 2022-01-26 6.4110
## 2551 2022-01-27 6.4350
## 2552 2022-01-28 6.4630
## 2553 2022-01-31 6.4490
## 2554 2022-02-02 6.4410
## 2555 2022-02-03 6.4430
## 2556 2022-02-04 6.4530
## 2557 2022-02-07 6.4920
## 2558 2022-02-08 6.4960
## 2559 2022-02-09 6.4980
## 2560 2022-02-10 6.4980
## 2561 2022-02-11 6.5030
## 2562 2022-02-14 6.5080
## 2563 2022-02-15 6.5100
## 2564 2022-02-16 6.5120
## 2565 2022-02-17 6.5080
## 2566 2022-02-18 6.5020
## 2567 2022-02-21 6.4940
## 2568 2022-02-22 6.5030
## 2569 2022-02-23 6.5010
## 2570 2022-02-24 6.5150
## 2571 2022-02-25 6.5100
## 2572 2022-03-01 6.5100
## 2573 2022-03-02 6.5500
## 2574 2022-03-04 6.6370
## 2575 2022-03-07 6.7130
## 2576 2022-03-08 6.7980
## 2577 2022-03-09 6.7970
## 2578 2022-03-10 6.7640
## 2579 2022-03-11 6.7310
## 2580 2022-03-14 6.7230
## 2581 2022-03-15 6.7340
## 2582 2022-03-16 6.7490
## 2583 2022-03-17 6.7420
## 2584 2022-03-18 6.7230
## 2585 2022-03-21 6.7200
## 2586 2022-03-22 6.7300
## 2587 2022-03-23 6.7410
## 2588 2022-03-24 6.7170
## 2589 2022-03-25 6.7050
## 2590 2022-03-28 6.7150
## 2591 2022-03-29 6.7600
## 2592 2022-03-30 6.7510
## 2593 2022-03-31 6.7490
## 2594 2022-04-01 6.7550
## 2595 2022-04-04 6.7510
## 2596 2022-04-05 6.7490
## 2597 2022-04-06 6.7800
## 2598 2022-04-07 6.7920
## 2599 2022-04-08 6.7890
## 2600 2022-04-11 6.8340
## 2601 2022-04-12 6.8760
## 2602 2022-04-13 6.9170
## 2603 2022-04-14 6.9220
## 2604 2022-04-18 6.9570
## 2605 2022-04-19 6.9770
## 2606 2022-04-20 6.9780
## 2607 2022-04-21 6.9780
## 2608 2022-04-22 6.9760
## 2609 2022-04-25 7.0430
## 2610 2022-04-26 7.0240
## 2611 2022-04-27 6.9950
## 2612 2022-04-28 6.9980
## 2613 2022-05-09 7.1700
## 2614 2022-05-10 7.3300
## 2615 2022-05-11 7.4190
## 2616 2022-05-12 7.3990
## 2617 2022-05-13 7.3770
## 2618 2022-05-17 7.3910
## 2619 2022-05-18 7.3400
## 2620 2022-05-19 7.3360
## 2621 2022-05-20 7.2800
## 2622 2022-05-23 7.2000
## 2623 2022-05-24 7.2220
## 2624 2022-05-25 7.2030
## 2625 2022-05-27 7.1410
## 2626 2022-05-30 7.0650
## 2627 2022-05-31 7.0470
## 2628 2022-06-02 7.0460
## 2629 2022-06-03 6.9960
## 2630 2022-06-06 6.9660
## 2631 2022-06-07 7.0260
## 2632 2022-06-08 7.1090
## 2633 2022-06-09 7.1870
## 2634 2022-06-10 7.2200
## 2635 2022-06-13 7.2900
## 2636 2022-06-14 7.4130
## 2637 2022-06-15 7.4350
## 2638 2022-06-16 7.4110
## 2639 2022-06-17 7.4660
## 2640 2022-06-20 7.4990
## 2641 2022-06-21 7.5140
## 2642 2022-06-22 7.4940
## 2643 2022-06-23 7.4310
## 2644 2022-06-24 7.3790
## 2645 2022-06-27 7.3160
## 2646 2022-06-28 7.2920
## 2647 2022-06-29 7.2880
## 2648 2022-06-30 7.2490
## 2649 2022-07-01 7.2420
## 2650 2022-07-04 7.2720
## 2651 2022-07-05 7.2980
## 2652 2022-07-06 7.2770
## 2653 2022-07-07 7.2770
## 2654 2022-07-08 7.2570
## 2655 2022-07-11 7.2930
## 2656 2022-07-12 7.2770
## 2657 2022-07-13 7.2440
## 2658 2022-07-14 7.2810
## 2659 2022-07-15 7.3650
## 2660 2022-07-18 7.3820
## 2661 2022-07-19 7.4160
## 2662 2022-07-20 7.4680
## 2663 2022-07-21 7.4840
## 2664 2022-07-22 7.4910
## 2665 2022-07-25 7.4420
## 2666 2022-07-26 7.4150
## 2667 2022-07-27 7.4140
## 2668 2022-07-28 7.3100
## 2669 2022-07-29 7.1970
## 2670 2022-08-01 7.1260
## 2671 2022-08-02 7.1590
## 2672 2022-08-03 7.2250
## 2673 2022-08-04 7.2150
## 2674 2022-08-05 7.1430
## 2675 2022-08-08 7.0960
## 2676 2022-08-09 7.1140
## 2677 2022-08-10 7.1030
## 2678 2022-08-11 7.0100
## 2679 2022-08-12 6.9710
## 2680 2022-08-15 7.0490
## 2681 2022-08-16 7.0680
## 2682 2022-08-18 7.0470
## 2683 2022-08-19 7.0940
## 2684 2022-08-22 7.1550
## 2685 2022-08-23 7.1560
## 2686 2022-08-24 7.0660
## 2687 2022-08-25 7.0610
## 2688 2022-08-26 7.0730
## 2689 2022-08-29 7.1410
## 2690 2022-08-30 7.1530
## 2691 2022-08-31 7.1170
## 2692 2022-09-01 7.1370
## 2693 2022-09-02 7.1440
## 2694 2022-09-05 7.1630
## 2695 2022-09-06 7.1820
## 2696 2022-09-07 7.2010
## 2697 2022-09-08 7.2100
## 2698 2022-09-09 7.1770
## 2699 2022-09-12 7.1700
## 2700 2022-09-13 7.1170
## 2701 2022-09-14 7.1240
## 2702 2022-09-15 7.1700
## 2703 2022-09-16 7.2140
## 2704 2022-09-19 7.2090
## 2705 2022-09-20 7.1980
## 2706 2022-09-21 7.1950
## 2707 2022-09-22 7.2280
## 2708 2022-09-23 7.2740
## 2709 2022-09-26 7.3430
## 2710 2022-09-27 7.4000
## 2711 2022-09-28 7.4060
## 2712 2022-09-29 7.3930
## 2713 2022-09-30 7.3800
## 2714 2022-10-03 7.3580
## 2715 2022-10-04 7.2910
## 2716 2022-10-05 7.2010
## 2717 2022-10-06 7.2190
## 2718 2022-10-07 7.2420
## 2719 2022-10-10 7.2780
## 2720 2022-10-11 7.3270
## 2721 2022-10-12 7.3530
## 2722 2022-10-13 7.3580
## 2723 2022-10-14 7.3360
## 2724 2022-10-17 7.4120
## 2725 2022-10-18 7.4440
## 2726 2022-10-19 7.4430
## 2727 2022-10-20 7.5080
## 2728 2022-10-21 7.5550
## 2729 2022-10-24 7.6540
## 2730 2022-10-25 7.6490
## 2731 2022-10-26 7.6370
## 2732 2022-10-27 7.5740
## 2733 2022-10-28 7.5840
## 2734 2022-10-31 7.5410
## 2735 2022-11-01 7.5400
## 2736 2022-11-02 7.4550
## 2737 2022-11-03 7.4350
## 2738 2022-11-04 7.4820
## 2739 2022-11-07 7.4680
## 2740 2022-11-08 7.4630
## 2741 2022-11-09 7.3230
## 2742 2022-11-10 7.3220
## 2743 2022-11-11 7.2020
## 2744 2022-11-14 7.1010
## 2745 2022-11-15 7.0430
## 2746 2022-11-16 7.0030
## 2747 2022-11-17 7.0160
## 2748 2022-11-18 7.0450
## 2749 2022-11-21 7.0700
## 2750 2022-11-22 7.0580
## 2751 2022-11-23 7.0290
## 2752 2022-11-24 6.9940
## 2753 2022-11-25 6.9430
## 2754 2022-11-28 6.9670
## 2755 2022-11-29 6.9790
## 2756 2022-11-30 6.9490
## 2757 2022-12-01 6.8560
## 2758 2022-12-02 6.8430
## 2759 2022-12-05 6.8850
## 2760 2022-12-06 6.9150
## 2761 2022-12-07 7.0150
## 2762 2022-12-08 6.9530
## 2763 2022-12-09 6.9580
## 2764 2022-12-12 6.9480
## 2765 2022-12-13 6.9480
## 2766 2022-12-14 6.9240
## 2767 2022-12-15 6.8590
## 2768 2022-12-16 6.9000
## 2769 2022-12-19 6.8810
## 2770 2022-12-20 6.9060
## 2771 2022-12-21 6.9290
## 2772 2022-12-22 6.9180
## 2773 2022-12-23 6.9240
## 2774 2022-12-26 6.9110
## 2775 2022-12-27 6.9090
## 2776 2022-12-28 6.9220
## 2777 2022-12-29 6.8950
## 2778 2022-12-30 6.9250
## 2779 2023-01-02 6.9660
## 2780 2023-01-03 7.0500
## 2781 2023-01-04 7.0250
## 2782 2023-01-05 6.9960
## 2783 2023-01-06 6.9660
## 2784 2023-01-09 6.9350
## 2785 2023-01-10 6.8630
## 2786 2023-01-11 6.8080
## 2787 2023-01-12 6.7290
## 2788 2023-01-13 6.6970
## 2789 2023-01-16 6.7380
## 2790 2023-01-17 6.7840
## 2791 2023-01-18 6.7160
## 2792 2023-01-19 6.6750
## 2793 2023-01-20 6.6340
## 2794 2023-01-23 6.6140
## 2795 2023-01-24 6.6180
## 2796 2023-01-25 6.6630
## 2797 2023-01-26 6.6840
## 2798 2023-01-27 6.7270
## 2799 2023-01-30 6.7640
## 2800 2023-01-31 6.7060
## 2801 2023-02-01 6.6520
## 2802 2023-02-02 6.6290
## 2803 2023-02-03 6.5680
## 2804 2023-02-06 6.6630
## 2805 2023-02-07 6.7170
## 2806 2023-02-08 6.7060
## 2807 2023-02-09 6.6330
## 2808 2023-02-10 6.6700
## 2809 2023-02-13 6.7290
## 2810 2023-02-14 6.7180
## 2811 2023-02-15 6.7630
## 2812 2023-02-16 6.7280
## 2813 2023-02-17 6.7280
## 2814 2023-02-20 6.7170
## 2815 2023-02-21 6.7310
## 2816 2023-02-22 6.7690
## 2817 2023-02-23 6.7990
## 2818 2023-02-24 6.7900
## 2819 2023-02-27 6.8410
## 2820 2023-02-28 6.8850
## 2821 2023-03-01 6.8870
## 2822 2023-03-02 6.9370
## 2823 2023-03-03 6.9820
## 2824 2023-03-06 6.9710
## 2825 2023-03-07 6.9730
## 2826 2023-03-08 6.9940
## 2827 2023-03-09 7.0390
## 2828 2023-03-10 6.9620
## 2829 2023-03-13 6.8930
## 2830 2023-03-14 6.7910
## 2831 2023-03-15 6.7560
## 2832 2023-03-16 6.8210
## 2833 2023-03-17 6.9530
## 2834 2023-03-20 6.8910
## 2835 2023-03-21 6.9040
## 2836 2023-03-22 6.8830
## 2837 2023-03-24 6.8430
## 2838 2023-03-27 6.8020
## 2839 2023-03-28 6.8040
## 2840 2023-03-29 6.8300
## 2841 2023-03-30 6.8360
## 2842 2023-03-31 6.8150
## 2843 2023-04-03 6.7870
## 2844 2023-04-04 6.7460
## 2845 2023-04-05 6.7110
## 2846 2023-04-06 6.6780
## 2847 2023-04-07 6.6690
## 2848 2023-04-10 6.6990
## 2849 2023-04-11 6.6730
## 2850 2023-04-12 6.6390
## 2851 2023-04-13 6.6430
## 2852 2023-04-14 6.6390
## 2853 2023-04-17 6.6440
## 2854 2023-04-18 6.6680
## 2855 2023-04-19 6.6620
## 2856 2023-04-26 6.5800
## 2857 2023-04-27 6.5320
## 2858 2023-04-28 6.5360
## 2859 2023-05-02 6.5170
## 2860 2023-05-03 6.5090
## 2861 2023-05-04 6.4410
## 2862 2023-05-05 6.4360
## 2863 2023-05-08 6.4720
## 2864 2023-05-09 6.4770
## 2865 2023-05-10 6.4740
## 2866 2023-05-11 6.4280
## 2867 2023-05-12 6.4050
## 2868 2023-05-15 6.4180
## 2869 2023-05-16 6.4000
## 2870 2023-05-17 6.3660
## 2871 2023-05-18 6.3500
## 2872 2023-05-19 6.4260
## 2873 2023-05-22 6.4540
## 2874 2023-05-23 6.4320
## 2875 2023-05-24 6.4200
## 2876 2023-05-25 6.4080
## 2877 2023-05-26 6.4350
## 2878 2023-05-29 6.4100
## 2879 2023-05-30 6.3920
## 2880 2023-05-31 6.3920
## 2881 2023-06-01 6.3640
## 2882 2023-06-05 6.4000
## 2883 2023-06-06 6.3550
## 2884 2023-06-07 6.3450
## 2885 2023-06-08 6.3680
## 2886 2023-06-09 6.3410
## 2887 2023-06-12 6.3090
## 2888 2023-06-13 6.3030
## 2889 2023-06-14 6.2620
## 2890 2023-06-15 6.2790
## 2891 2023-06-16 6.3060
## 2892 2023-06-19 6.3100
## 2893 2023-06-20 6.3450
## 2894 2023-06-21 6.3240
## 2895 2023-06-22 6.2970
## 2896 2023-06-23 6.3050
## 2897 2023-06-26 6.2860
## 2898 2023-06-27 6.2570
## 2899 2023-06-28 6.2430
## 2900 2023-07-03 6.2310
## 2901 2023-07-04 6.2260
## 2902 2023-07-05 6.1870
## 2903 2023-07-06 6.2100
## 2904 2023-07-07 6.2460
## 2905 2023-07-10 6.2580
## 2906 2023-07-11 6.2500
## 2907 2023-07-12 6.2040
## 2908 2023-07-13 6.1960
## 2909 2023-07-14 6.1910
## 2910 2023-07-17 6.2010
## 2911 2023-07-18 6.2120
## 2912 2023-07-20 6.2260
## 2913 2023-07-21 6.2440
## 2914 2023-07-24 6.2460
## 2915 2023-07-25 6.2330
## 2916 2023-07-26 6.2550
## 2917 2023-07-27 6.2580
## 2918 2023-07-28 6.2740
## 2919 2023-07-31 6.2680
## 2920 2023-08-01 6.2670
## 2921 2023-08-02 6.2680
## 2922 2023-08-03 6.2850
## 2923 2023-08-04 6.3380
## 2924 2023-08-07 6.3470
## 2925 2023-08-08 6.3570
## 2926 2023-08-09 6.3350
## 2927 2023-08-10 6.3280
## 2928 2023-08-11 6.3300
## 2929 2023-08-14 6.3740
## 2930 2023-08-15 6.4100
## 2931 2023-08-16 6.4400
## 2932 2023-08-17 6.4300
## 2933 2023-08-18 6.4920
## 2934 2023-08-21 6.5810
## 2935 2023-08-22 6.6770
## 2936 2023-08-23 6.6140
## 2937 2023-08-24 6.5740
## 2938 2023-08-25 6.5280
## 2939 2023-08-28 6.4660
## 2940 2023-08-29 6.3940
## 2941 2023-08-30 6.3680
## 2942 2023-08-31 6.3810
## 2943 2023-09-01 6.3810
## 2944 2023-09-04 6.3830
## 2945 2023-09-05 6.4460
## 2946 2023-09-06 6.5200
## 2947 2023-09-07 6.5620
## 2948 2023-09-08 6.5620
## 2949 2023-09-11 6.5950
## 2950 2023-09-12 6.6500
## 2951 2023-09-13 6.6820
## 2952 2023-09-14 6.6410
## 2953 2023-09-15 6.6930
## 2954 2023-09-18 6.7160
## 2955 2023-09-19 6.7490
## 2956 2023-09-20 6.7650
## 2957 2023-09-21 6.7990
## 2958 2023-09-22 6.7390
## 2959 2023-09-25 6.7410
## 2960 2023-09-26 6.8350
## 2961 2023-09-27 6.8860
## 2962 2023-09-28 6.8840
## 2963 2023-09-29 6.9100
## 2964 2023-10-02 6.9710
## 2965 2023-10-03 7.0250
## 2966 2023-10-04 7.0830
## 2967 2023-10-05 7.0350
## 2968 2023-10-06 7.0080
## 2969 2023-10-09 7.0040
## 2970 2023-10-10 6.9410
## 2971 2023-10-11 6.8280
## 2972 2023-10-12 6.7710
## 2973 2023-10-13 6.7820
## 2974 2023-10-16 6.7590
## 2975 2023-10-17 6.8120
## 2976 2023-10-18 6.8320
## 2977 2023-10-19 7.0200
## 2978 2023-10-20 7.1640
## 2979 2023-10-23 7.2640
last(yield)
##            time close
## 2979 2023-10-23 7.264

Plot Chart

Basic

yield %>% 
  plot_time_series(.date_var = time, .value = close)

Seasonality

yield %>% 
 plot_seasonal_diagnostics(.date_var = time, .value = close)
yield %>% 
 plot_seasonal_diagnostics(.date_var = time, .value = close, .feature_set = "week")
yield %>% 
 plot_seasonal_diagnostics(.date_var = time, .value = close, .feature_set = "wday.lbl")
yield %>% 
 plot_seasonal_diagnostics(.date_var = time, .value = close, .feature_set = "month.lbl")
yield %>% 
 plot_seasonal_diagnostics(.date_var = time, .value = close, .feature_set = "quarter")
yield %>% 
 plot_seasonal_diagnostics(.date_var = time, .value = close, .feature_set = "year")

Anomali Detection

yield %>% 
  plot_anomaly_diagnostics(.date_var = time, .value = close)
## frequency = 5 observations per 1 week
## trend = 66 observations per 3 months

ACF Diagnostic

yield %>% 
  plot_acf_diagnostics(.date_var = time, .value = close)
yield %>% 
  plot_acf_diagnostics(.date_var = time, .value = diff_vec(close), .lags = 60)
## diff_vec(): Initial values: 6.88199997

Augmented ACF

yield_lags_tbl <- yield %>%
    tk_augment_lags(close, .lags = 60) %>%
    drop_na()

yield_lags_tbl %>% glimpse()
## Rows: 2,919
## Columns: 3
## $ time        <date> 2012-02-23, 2012-02-24, 2012-02-27, 2012-02-28, 2012-02-2…
## $ close       <dbl> 5.313, 5.451, 5.450, 5.686, 5.616, 5.534, 5.537, 5.509, 5.…
## $ close_lag60 <dbl> 6.882, 6.882, 6.415, 6.157, 6.157, 6.030, 6.029, 6.060, 6.…
# model_formula <- as.formula(
#     close ~ time
#     + .
#     + (as.factor(week2) * wday.lbl))
# 
# yield %>% plot_time_series_regression(.date_var = time, .formula = model_formula)

STL Diagnostic

yield %>% 
  plot_stl_diagnostics(.date_var = time, 
                       .value = close)
## frequency = 5 observations per 1 week
## trend = 66 observations per 3 months
yield %>% 
  plot_stl_diagnostics(.date_var = time, 
                       .value = close, .feature_set = c("season", "trend"))
## frequency = 5 observations per 1 week
## trend = 66 observations per 3 months
yield %>% 
  plot_stl_diagnostics(.date_var = time, 
                       .value = close, .feature_set = c("trend", "remainder"))
## frequency = 5 observations per 1 week
## trend = 66 observations per 3 months

Basic Preparation

Splits

splits <- time_series_split(yield, assess = "3 year", cumulative = T)
## Using date_var: time
splits %>%
    tk_time_series_cv_plan() %>%
    plot_time_series_cv_plan(time, close)

Recipe (Fourier and No Fourier)

recipe_spec_fourier <- recipe(close ~ ., data = training(splits)) %>%
  step_timeseries_signature(time) %>%
  step_rm(matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")) %>% 
  step_rm(c("time_month.lbl","time_wday.lbl")) %>%
  step_fourier(time, period = c(9, 24, 48), K = 2)
  
recipe_spec <- recipe(close ~ ., data = training(splits)) %>%
  step_timeseries_signature(time) %>%
  step_rm(matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")) %>% 
  step_rm(c("time_month.lbl","time_wday.lbl"))

recipe_spec_fourier %>% prep() %>% juice() %>% glimpse()
## Rows: 2,235
## Columns: 30
## $ time           <date> 2011-11-29, 2011-11-30, 2011-12-01, 2011-12-02, 2011-1…
## $ close          <dbl> 6.882, 6.882, 6.415, 6.157, 6.157, 6.030, 6.029, 6.060,…
## $ time_index.num <dbl> 1322524800, 1322611200, 1322697600, 1322784000, 1323043…
## $ time_year      <int> 2011, 2011, 2011, 2011, 2011, 2011, 2011, 2011, 2011, 2…
## $ time_half      <int> 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2…
## $ time_quarter   <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4…
## $ time_month     <int> 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,…
## $ time_day       <int> 29, 30, 1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15, 16, 19, 20…
## $ time_wday      <int> 3, 4, 5, 6, 2, 3, 4, 5, 6, 2, 3, 4, 5, 6, 2, 3, 4, 5, 6…
## $ time_mday      <int> 29, 30, 1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15, 16, 19, 20…
## $ time_qday      <int> 60, 61, 62, 63, 66, 67, 68, 69, 70, 73, 74, 75, 76, 77,…
## $ time_yday      <int> 333, 334, 335, 336, 339, 340, 341, 342, 343, 346, 347, …
## $ time_mweek     <int> 5, 5, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4…
## $ time_week      <int> 48, 48, 48, 48, 49, 49, 49, 49, 49, 50, 50, 50, 50, 50,…
## $ time_week2     <int> 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1…
## $ time_week3     <int> 0, 0, 0, 0, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 0, 0, 0, 0, 0…
## $ time_week4     <int> 0, 0, 0, 0, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3…
## $ time_mday7     <int> 5, 5, 1, 1, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 4, 4, 4…
## $ time_sin9_K1   <dbl> -0.9848077530122542056, -0.6427876096868415656, -0.0000…
## $ time_cos9_K1   <dbl> 0.1736482, 0.7660444, 1.0000000, 0.7660444, -0.9396926,…
## $ time_sin9_K2   <dbl> -0.3420201433251692791, -0.9848077530123450218, -0.0000…
## $ time_cos9_K2   <dbl> -0.9396926, 0.1736482, 1.0000000, 0.1736482, 0.7660444,…
## $ time_sin24_K1  <dbl> -0.9659258262892117530, -0.8660254037846263353, -0.7071…
## $ time_cos24_K1  <dbl> 0.2588190451019852234, 0.4999999999996749822, 0.7071067…
## $ time_sin24_K2  <dbl> -0.4999999999990397126, -0.8660254037840633412, -1.0000…
## $ time_cos24_K2  <dbl> -0.8660254037849930420, -0.5000000000006500356, -0.0000…
## $ time_sin48_K1  <dbl> -0.608761429008940591, -0.500000000000162537, -0.382683…
## $ time_cos48_K1  <dbl> 0.7933533402910664112, 0.8660254037843447827, 0.9238795…
## $ time_sin48_K2  <dbl> -0.9659258262892117530, -0.8660254037846263353, -0.7071…
## $ time_cos48_K2  <dbl> 0.2588190451019852234, 0.4999999999996749822, 0.7071067…
recipe_spec %>% prep() %>% juice() %>% glimpse()
## Rows: 2,235
## Columns: 18
## $ time           <date> 2011-11-29, 2011-11-30, 2011-12-01, 2011-12-02, 2011-1…
## $ close          <dbl> 6.882, 6.882, 6.415, 6.157, 6.157, 6.030, 6.029, 6.060,…
## $ time_index.num <dbl> 1322524800, 1322611200, 1322697600, 1322784000, 1323043…
## $ time_year      <int> 2011, 2011, 2011, 2011, 2011, 2011, 2011, 2011, 2011, 2…
## $ time_half      <int> 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2…
## $ time_quarter   <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4…
## $ time_month     <int> 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,…
## $ time_day       <int> 29, 30, 1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15, 16, 19, 20…
## $ time_wday      <int> 3, 4, 5, 6, 2, 3, 4, 5, 6, 2, 3, 4, 5, 6, 2, 3, 4, 5, 6…
## $ time_mday      <int> 29, 30, 1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15, 16, 19, 20…
## $ time_qday      <int> 60, 61, 62, 63, 66, 67, 68, 69, 70, 73, 74, 75, 76, 77,…
## $ time_yday      <int> 333, 334, 335, 336, 339, 340, 341, 342, 343, 346, 347, …
## $ time_mweek     <int> 5, 5, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4…
## $ time_week      <int> 48, 48, 48, 48, 49, 49, 49, 49, 49, 50, 50, 50, 50, 50,…
## $ time_week2     <int> 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1…
## $ time_week3     <int> 0, 0, 0, 0, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 0, 0, 0, 0, 0…
## $ time_week4     <int> 0, 0, 0, 0, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3…
## $ time_mday7     <int> 5, 5, 1, 1, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 4, 4, 4…

Resampling

resamples_tscv_no_acum <- time_series_cv(
    data = training(splits),
    cumulative  = F,
    initial     = "1 year", # train
    assess      = "3 month", # test
    skip        = "1 year",
    slice_limit = 5,
    date_var = time
)

resamples_tscv_no_acum %>%
    tk_time_series_cv_plan() %>%
    plot_time_series_cv_plan(time, close)

Modelling

Prophet Complete Season

model_fit_prophet_seasonality <- prophet_reg(seasonality_yearly = TRUE, 
                                 seasonality_weekly = TRUE, 
                                 seasonality_daily = TRUE) %>% 
  set_engine("prophet") %>%
  fit(close ~ time, data = training(splits))

model_fit_prophet_seasonality %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

Elastic Net Regression

model_spec_glmnet <- linear_reg(mode = "regression", 
           penalty = 0.01, 
           mixture = 0) %>% 
  set_engine("glmnet")

model_spec_glmnet <- linear_reg(penalty = 0, mixture = 0) %>% 
  set_mode("regression") %>% 
  set_engine("glmnet")

model_fit_glmnet <- workflow() %>% 
  add_model(model_spec_glmnet) %>% 
  add_recipe(recipe_spec %>%
               step_mutate(time = as.numeric(time))) %>%
  fit(training(splits))

model_fit_glmnet %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

SVM Polynominal

model_spec_svm_poly <- svm_poly(mode = "regression", 
                                cost = 10, 
                                degree = 1, 
                                scale_factor = 1, 
                                margin = 0.1) %>% 
  set_engine("kernlab")

set.seed(123)
model_fit_svm_poly <- workflow() %>% 
  add_model(model_spec_svm_poly) %>% 
  add_recipe(recipe_spec) %>% 
  fit(training(splits))

set.seed(123)
model_fit_svm_poly %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

SVM Radial Basis

model_spec_svm_rbf <- svm_rbf(mode = "regression", 
                              cost = 1, 
                              rbf_sigma = 0.01, 
                              margin = 0.1) %>% 
  set_engine("kernlab")

set.seed(123)
model_fit_svm_rbf <- workflow() %>% 
  add_model(model_spec_svm_rbf) %>% 
  add_recipe(recipe_spec) %>% 
  fit(training(splits))

set.seed(123)
model_fit_svm_rbf %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

KNN

model_spec_knn <- nearest_neighbor(mode = "regression", 
                                   neighbors = 50, 
                                   dist_power = 10, 
                                   weight_func = "optimal") %>% 
  set_engine("kknn")

set.seed(123)
model_fit_knn <- workflow() %>% 
  add_model(model_spec_knn) %>% 
  add_recipe(recipe_spec %>% 
               step_mutate(time = as.numeric(time))) %>% 
  fit(training(splits))

set.seed(123)
model_fit_knn %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

Random Forest

model_spect_rf <- rand_forest(mode = "regression", 
                              mtry = 25, 
                              trees = 1000, 
                              min_n = 25) %>% 
  set_engine("randomForest")

set.seed(123)
model_fit_spect_rf <- workflow() %>% 
  add_model(model_spect_rf) %>% 
  add_recipe(recipe_spec %>% 
               step_mutate(time = as.numeric(time))) %>% 
  fit(training(splits))
## Warning: 25 columns were requested but there were 17 predictors in the data. 17
## will be used.
set.seed(123)
model_fit_spect_rf %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

tune Random Forest

model_spect_rf_tune <- rand_forest(mode = "regression", 
                              mtry = tune(),
                              trees = tune(), 
                              min_n = tune()) %>% 
  set_engine("randomForest")

grid_spec_rf <- grid_latin_hypercube(
  # extract_parameter_dials(model_spec_prophet_boost_tune),
  parameters(model_spect_rf_tune) %>%
        update(mtry = mtry(range = c(1, 65))),
  size = 15
)
## Warning: `parameters.model_spec()` was deprecated in tune 0.1.6.9003.
## ℹ Please use `hardhat::extract_parameter_set_dials()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
model_fit_spect_rf_tune <- model_fit_spect_rf %>% 
  update_model(model_spect_rf_tune)

tic()
tune_result_rf <- model_fit_spect_rf_tune %>%
  tune_grid(
    resamples = resamples_tscv_no_acum,
    grid      = grid_spec_rf,
    metrics   = default_forecast_accuracy_metric_set(),
    control   = control_grid(verbose = TRUE, save_pred = TRUE)
  )
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/15
## ✓ Slice1: preprocessor 1/1, model 1/15
## i Slice1: preprocessor 1/1, model 1/15 (predictions)
## i Slice1: preprocessor 1/1, model 2/15
## ✓ Slice1: preprocessor 1/1, model 2/15
## i Slice1: preprocessor 1/1, model 2/15 (predictions)
## i Slice1: preprocessor 1/1, model 3/15
## ! Slice1: preprocessor 1/1, model 3/15: 44 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 3/15
## i Slice1: preprocessor 1/1, model 3/15 (predictions)
## i Slice1: preprocessor 1/1, model 4/15
## ✓ Slice1: preprocessor 1/1, model 4/15
## i Slice1: preprocessor 1/1, model 4/15 (predictions)
## i Slice1: preprocessor 1/1, model 5/15
## ! Slice1: preprocessor 1/1, model 5/15: 35 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 5/15
## i Slice1: preprocessor 1/1, model 5/15 (predictions)
## i Slice1: preprocessor 1/1, model 6/15
## ! Slice1: preprocessor 1/1, model 6/15: 51 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 6/15
## i Slice1: preprocessor 1/1, model 6/15 (predictions)
## i Slice1: preprocessor 1/1, model 7/15
## ! Slice1: preprocessor 1/1, model 7/15: 19 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 7/15
## i Slice1: preprocessor 1/1, model 7/15 (predictions)
## i Slice1: preprocessor 1/1, model 8/15
## ✓ Slice1: preprocessor 1/1, model 8/15
## i Slice1: preprocessor 1/1, model 8/15 (predictions)
## i Slice1: preprocessor 1/1, model 9/15
## ! Slice1: preprocessor 1/1, model 9/15: 29 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 9/15
## i Slice1: preprocessor 1/1, model 9/15 (predictions)
## i Slice1: preprocessor 1/1, model 10/15
## ! Slice1: preprocessor 1/1, model 10/15: 60 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 10/15
## i Slice1: preprocessor 1/1, model 10/15 (predictions)
## i Slice1: preprocessor 1/1, model 11/15
## ! Slice1: preprocessor 1/1, model 11/15: 24 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 11/15
## i Slice1: preprocessor 1/1, model 11/15 (predictions)
## i Slice1: preprocessor 1/1, model 12/15
## ! Slice1: preprocessor 1/1, model 12/15: 37 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 12/15
## i Slice1: preprocessor 1/1, model 12/15 (predictions)
## i Slice1: preprocessor 1/1, model 13/15
## ! Slice1: preprocessor 1/1, model 13/15: 64 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 13/15
## i Slice1: preprocessor 1/1, model 13/15 (predictions)
## i Slice1: preprocessor 1/1, model 14/15
## ! Slice1: preprocessor 1/1, model 14/15: 42 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 14/15
## i Slice1: preprocessor 1/1, model 14/15 (predictions)
## i Slice1: preprocessor 1/1, model 15/15
## ! Slice1: preprocessor 1/1, model 15/15: 56 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 15/15
## i Slice1: preprocessor 1/1, model 15/15 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/15
## ✓ Slice2: preprocessor 1/1, model 1/15
## i Slice2: preprocessor 1/1, model 1/15 (predictions)
## i Slice2: preprocessor 1/1, model 2/15
## ✓ Slice2: preprocessor 1/1, model 2/15
## i Slice2: preprocessor 1/1, model 2/15 (predictions)
## i Slice2: preprocessor 1/1, model 3/15
## ! Slice2: preprocessor 1/1, model 3/15: 44 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 3/15
## i Slice2: preprocessor 1/1, model 3/15 (predictions)
## i Slice2: preprocessor 1/1, model 4/15
## ✓ Slice2: preprocessor 1/1, model 4/15
## i Slice2: preprocessor 1/1, model 4/15 (predictions)
## i Slice2: preprocessor 1/1, model 5/15
## ! Slice2: preprocessor 1/1, model 5/15: 35 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 5/15
## i Slice2: preprocessor 1/1, model 5/15 (predictions)
## i Slice2: preprocessor 1/1, model 6/15
## ! Slice2: preprocessor 1/1, model 6/15: 51 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 6/15
## i Slice2: preprocessor 1/1, model 6/15 (predictions)
## i Slice2: preprocessor 1/1, model 7/15
## ! Slice2: preprocessor 1/1, model 7/15: 19 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 7/15
## i Slice2: preprocessor 1/1, model 7/15 (predictions)
## i Slice2: preprocessor 1/1, model 8/15
## ✓ Slice2: preprocessor 1/1, model 8/15
## i Slice2: preprocessor 1/1, model 8/15 (predictions)
## i Slice2: preprocessor 1/1, model 9/15
## ! Slice2: preprocessor 1/1, model 9/15: 29 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 9/15
## i Slice2: preprocessor 1/1, model 9/15 (predictions)
## i Slice2: preprocessor 1/1, model 10/15
## ! Slice2: preprocessor 1/1, model 10/15: 60 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 10/15
## i Slice2: preprocessor 1/1, model 10/15 (predictions)
## i Slice2: preprocessor 1/1, model 11/15
## ! Slice2: preprocessor 1/1, model 11/15: 24 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 11/15
## i Slice2: preprocessor 1/1, model 11/15 (predictions)
## i Slice2: preprocessor 1/1, model 12/15
## ! Slice2: preprocessor 1/1, model 12/15: 37 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 12/15
## i Slice2: preprocessor 1/1, model 12/15 (predictions)
## i Slice2: preprocessor 1/1, model 13/15
## ! Slice2: preprocessor 1/1, model 13/15: 64 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 13/15
## i Slice2: preprocessor 1/1, model 13/15 (predictions)
## i Slice2: preprocessor 1/1, model 14/15
## ! Slice2: preprocessor 1/1, model 14/15: 42 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 14/15
## i Slice2: preprocessor 1/1, model 14/15 (predictions)
## i Slice2: preprocessor 1/1, model 15/15
## ! Slice2: preprocessor 1/1, model 15/15: 56 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 15/15
## i Slice2: preprocessor 1/1, model 15/15 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/15
## ✓ Slice3: preprocessor 1/1, model 1/15
## i Slice3: preprocessor 1/1, model 1/15 (predictions)
## i Slice3: preprocessor 1/1, model 2/15
## ✓ Slice3: preprocessor 1/1, model 2/15
## i Slice3: preprocessor 1/1, model 2/15 (predictions)
## i Slice3: preprocessor 1/1, model 3/15
## ! Slice3: preprocessor 1/1, model 3/15: 44 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 3/15
## i Slice3: preprocessor 1/1, model 3/15 (predictions)
## i Slice3: preprocessor 1/1, model 4/15
## ✓ Slice3: preprocessor 1/1, model 4/15
## i Slice3: preprocessor 1/1, model 4/15 (predictions)
## i Slice3: preprocessor 1/1, model 5/15
## ! Slice3: preprocessor 1/1, model 5/15: 35 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 5/15
## i Slice3: preprocessor 1/1, model 5/15 (predictions)
## i Slice3: preprocessor 1/1, model 6/15
## ! Slice3: preprocessor 1/1, model 6/15: 51 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 6/15
## i Slice3: preprocessor 1/1, model 6/15 (predictions)
## i Slice3: preprocessor 1/1, model 7/15
## ! Slice3: preprocessor 1/1, model 7/15: 19 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 7/15
## i Slice3: preprocessor 1/1, model 7/15 (predictions)
## i Slice3: preprocessor 1/1, model 8/15
## ✓ Slice3: preprocessor 1/1, model 8/15
## i Slice3: preprocessor 1/1, model 8/15 (predictions)
## i Slice3: preprocessor 1/1, model 9/15
## ! Slice3: preprocessor 1/1, model 9/15: 29 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 9/15
## i Slice3: preprocessor 1/1, model 9/15 (predictions)
## i Slice3: preprocessor 1/1, model 10/15
## ! Slice3: preprocessor 1/1, model 10/15: 60 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 10/15
## i Slice3: preprocessor 1/1, model 10/15 (predictions)
## i Slice3: preprocessor 1/1, model 11/15
## ! Slice3: preprocessor 1/1, model 11/15: 24 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 11/15
## i Slice3: preprocessor 1/1, model 11/15 (predictions)
## i Slice3: preprocessor 1/1, model 12/15
## ! Slice3: preprocessor 1/1, model 12/15: 37 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 12/15
## i Slice3: preprocessor 1/1, model 12/15 (predictions)
## i Slice3: preprocessor 1/1, model 13/15
## ! Slice3: preprocessor 1/1, model 13/15: 64 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 13/15
## i Slice3: preprocessor 1/1, model 13/15 (predictions)
## i Slice3: preprocessor 1/1, model 14/15
## ! Slice3: preprocessor 1/1, model 14/15: 42 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 14/15
## i Slice3: preprocessor 1/1, model 14/15 (predictions)
## i Slice3: preprocessor 1/1, model 15/15
## ! Slice3: preprocessor 1/1, model 15/15: 56 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 15/15
## i Slice3: preprocessor 1/1, model 15/15 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/15
## ✓ Slice4: preprocessor 1/1, model 1/15
## i Slice4: preprocessor 1/1, model 1/15 (predictions)
## i Slice4: preprocessor 1/1, model 2/15
## ✓ Slice4: preprocessor 1/1, model 2/15
## i Slice4: preprocessor 1/1, model 2/15 (predictions)
## i Slice4: preprocessor 1/1, model 3/15
## ! Slice4: preprocessor 1/1, model 3/15: 44 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 3/15
## i Slice4: preprocessor 1/1, model 3/15 (predictions)
## i Slice4: preprocessor 1/1, model 4/15
## ✓ Slice4: preprocessor 1/1, model 4/15
## i Slice4: preprocessor 1/1, model 4/15 (predictions)
## i Slice4: preprocessor 1/1, model 5/15
## ! Slice4: preprocessor 1/1, model 5/15: 35 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 5/15
## i Slice4: preprocessor 1/1, model 5/15 (predictions)
## i Slice4: preprocessor 1/1, model 6/15
## ! Slice4: preprocessor 1/1, model 6/15: 51 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 6/15
## i Slice4: preprocessor 1/1, model 6/15 (predictions)
## i Slice4: preprocessor 1/1, model 7/15
## ! Slice4: preprocessor 1/1, model 7/15: 19 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 7/15
## i Slice4: preprocessor 1/1, model 7/15 (predictions)
## i Slice4: preprocessor 1/1, model 8/15
## ✓ Slice4: preprocessor 1/1, model 8/15
## i Slice4: preprocessor 1/1, model 8/15 (predictions)
## i Slice4: preprocessor 1/1, model 9/15
## ! Slice4: preprocessor 1/1, model 9/15: 29 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 9/15
## i Slice4: preprocessor 1/1, model 9/15 (predictions)
## i Slice4: preprocessor 1/1, model 10/15
## ! Slice4: preprocessor 1/1, model 10/15: 60 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 10/15
## i Slice4: preprocessor 1/1, model 10/15 (predictions)
## i Slice4: preprocessor 1/1, model 11/15
## ! Slice4: preprocessor 1/1, model 11/15: 24 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 11/15
## i Slice4: preprocessor 1/1, model 11/15 (predictions)
## i Slice4: preprocessor 1/1, model 12/15
## ! Slice4: preprocessor 1/1, model 12/15: 37 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 12/15
## i Slice4: preprocessor 1/1, model 12/15 (predictions)
## i Slice4: preprocessor 1/1, model 13/15
## ! Slice4: preprocessor 1/1, model 13/15: 64 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 13/15
## i Slice4: preprocessor 1/1, model 13/15 (predictions)
## i Slice4: preprocessor 1/1, model 14/15
## ! Slice4: preprocessor 1/1, model 14/15: 42 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 14/15
## i Slice4: preprocessor 1/1, model 14/15 (predictions)
## i Slice4: preprocessor 1/1, model 15/15
## ! Slice4: preprocessor 1/1, model 15/15: 56 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 15/15
## i Slice4: preprocessor 1/1, model 15/15 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/15
## ✓ Slice5: preprocessor 1/1, model 1/15
## i Slice5: preprocessor 1/1, model 1/15 (predictions)
## i Slice5: preprocessor 1/1, model 2/15
## ✓ Slice5: preprocessor 1/1, model 2/15
## i Slice5: preprocessor 1/1, model 2/15 (predictions)
## i Slice5: preprocessor 1/1, model 3/15
## ! Slice5: preprocessor 1/1, model 3/15: 44 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 3/15
## i Slice5: preprocessor 1/1, model 3/15 (predictions)
## i Slice5: preprocessor 1/1, model 4/15
## ✓ Slice5: preprocessor 1/1, model 4/15
## i Slice5: preprocessor 1/1, model 4/15 (predictions)
## i Slice5: preprocessor 1/1, model 5/15
## ! Slice5: preprocessor 1/1, model 5/15: 35 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 5/15
## i Slice5: preprocessor 1/1, model 5/15 (predictions)
## i Slice5: preprocessor 1/1, model 6/15
## ! Slice5: preprocessor 1/1, model 6/15: 51 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 6/15
## i Slice5: preprocessor 1/1, model 6/15 (predictions)
## i Slice5: preprocessor 1/1, model 7/15
## ! Slice5: preprocessor 1/1, model 7/15: 19 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 7/15
## i Slice5: preprocessor 1/1, model 7/15 (predictions)
## i Slice5: preprocessor 1/1, model 8/15
## ✓ Slice5: preprocessor 1/1, model 8/15
## i Slice5: preprocessor 1/1, model 8/15 (predictions)
## i Slice5: preprocessor 1/1, model 9/15
## ! Slice5: preprocessor 1/1, model 9/15: 29 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 9/15
## i Slice5: preprocessor 1/1, model 9/15 (predictions)
## i Slice5: preprocessor 1/1, model 10/15
## ! Slice5: preprocessor 1/1, model 10/15: 60 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 10/15
## i Slice5: preprocessor 1/1, model 10/15 (predictions)
## i Slice5: preprocessor 1/1, model 11/15
## ! Slice5: preprocessor 1/1, model 11/15: 24 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 11/15
## i Slice5: preprocessor 1/1, model 11/15 (predictions)
## i Slice5: preprocessor 1/1, model 12/15
## ! Slice5: preprocessor 1/1, model 12/15: 37 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 12/15
## i Slice5: preprocessor 1/1, model 12/15 (predictions)
## i Slice5: preprocessor 1/1, model 13/15
## ! Slice5: preprocessor 1/1, model 13/15: 64 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 13/15
## i Slice5: preprocessor 1/1, model 13/15 (predictions)
## i Slice5: preprocessor 1/1, model 14/15
## ! Slice5: preprocessor 1/1, model 14/15: 42 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 14/15
## i Slice5: preprocessor 1/1, model 14/15 (predictions)
## i Slice5: preprocessor 1/1, model 15/15
## ! Slice5: preprocessor 1/1, model 15/15: 56 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 15/15
## i Slice5: preprocessor 1/1, model 15/15 (predictions)
toc()
## 61.09 sec elapsed
tune_result_rf %>% 
  show_best(metric = "rmse", n = Inf)
## # A tibble: 15 × 9
##     mtry trees min_n .metric .estimator  mean     n std_err .config             
##    <int> <int> <int> <chr>   <chr>      <dbl> <int>   <dbl> <chr>               
##  1    44  1150    16 rmse    standard   0.429     5  0.0660 Preprocessor1_Model…
##  2    29   558    14 rmse    standard   0.431     5  0.0645 Preprocessor1_Model…
##  3    56  1414    19 rmse    standard   0.433     5  0.0630 Preprocessor1_Model…
##  4    42   745    22 rmse    standard   0.435     5  0.0635 Preprocessor1_Model…
##  5    14   203    24 rmse    standard   0.441     5  0.0717 Preprocessor1_Model…
##  6    24   885     8 rmse    standard   0.442     5  0.0725 Preprocessor1_Model…
##  7    37   935    31 rmse    standard   0.443     5  0.0625 Preprocessor1_Model…
##  8    60   528     4 rmse    standard   0.445     5  0.0734 Preprocessor1_Model…
##  9    64  1508    33 rmse    standard   0.445     5  0.0597 Preprocessor1_Model…
## 10    35  1894     5 rmse    standard   0.447     5  0.0722 Preprocessor1_Model…
## 11    19  1618    38 rmse    standard   0.447     5  0.0612 Preprocessor1_Model…
## 12    51  1253    37 rmse    standard   0.448     5  0.0620 Preprocessor1_Model…
## 13    10   101    27 rmse    standard   0.459     5  0.0632 Preprocessor1_Model…
## 14     9   376    27 rmse    standard   0.472     5  0.0618 Preprocessor1_Model…
## 15     3  1847    12 rmse    standard   0.578     5  0.124  Preprocessor1_Model…
tune_result_rf %>% write_rds("tune_result_rf")

model_fit_spect_rf_tune %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_rf %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  ) %>% 
  fit(training(splits)) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>%
  # modeltime_forecast(new_data = test_data, actual_data = ihsg_tbl) %>%
  # plot_modeltime_forecast()
  modeltime_refit(data = yield) %>%
  # modeltime_forecast(new_data = ihsg_future_tbl, actual_data = ihsg_tbl) %>%
  modeltime_forecast(h = "1 year", actual_data = yield) %>%
  plot_modeltime_forecast(.conf_interval_show = F)
## Warning: 44 columns were requested but there were 17 predictors in the data. 17
## will be used.
## Converting to Modeltime Table.
## Warning: There was 1 warning in `dplyr::mutate()`.
## ℹ In argument: `.model = purrr::map2(...)`.
## Caused by warning:
## ! 44 columns were requested but there were 17 predictors in the data. 17 will be used.
model_fit_spect_rf_tune <- model_fit_spect_rf %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_rf %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  )

XGBoost

model_spec_boost <- boost_tree(mode = "regression", 
                               mtry = 25, 
                               trees = 1000, 
                               min_n = 2, 
                               tree_depth = 12, 
                               learn_rate = 0.3, 
                               loss_reduction = 0) %>% 
  set_engine("xgboost")

set.seed(123)
model_fit_boost <- workflow() %>% 
  add_model(model_spec_boost) %>% 
  add_recipe(recipe_spec %>% 
               step_mutate(time = as.numeric(time))) %>% 
  fit(training(splits))

set.seed(123)
model_fit_boost %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.
set.seed(123)
model_fit_boost %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(h = "1 year", actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

tune XGBoost

model_spec_xgboost_tune <- boost_tree(
  mtry = tune(),
  trees = tune(), 
  min_n = tune(), 
  tree_depth = tune(),
  learn_rate = tune(), 
  loss_reduction = tune(), 
  sample_size = tune(),
  stop_iter = tune(), mode = "regression"
) %>%
  set_engine("xgboost")

grid_spec_xgboost <- grid_latin_hypercube(
  # extract_parameter_dials(model_spec_prophet_boost_tune),
  parameters(model_spec_xgboost_tune) %>%
        update(mtry = mtry(range = c(1, 65))),
  size = 15
)

set.seed(123)
model_fit_xgboost <- workflow() %>% 
  add_model(model_spec_boost) %>% 
  add_recipe(recipe_spec %>% 
               step_mutate(time = as.numeric(time))) %>% 
  fit(training(splits))

model_fit_xgboost_tune <- model_fit_boost %>% 
  update_model(model_spec_xgboost_tune)

tic()
tune_result_xgboost <- model_fit_xgboost_tune %>%
  tune_grid(
    resamples = resamples_tscv_no_acum,
    grid      = grid_spec_xgboost,
    metrics   = default_forecast_accuracy_metric_set(),
    control   = control_grid(verbose = TRUE, save_pred = TRUE)
  )
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/15
## ✓ Slice1: preprocessor 1/1, model 1/15
## i Slice1: preprocessor 1/1, model 1/15 (predictions)
## i Slice1: preprocessor 1/1, model 2/15
## ✓ Slice1: preprocessor 1/1, model 2/15
## i Slice1: preprocessor 1/1, model 2/15 (predictions)
## i Slice1: preprocessor 1/1, model 3/15
## ✓ Slice1: preprocessor 1/1, model 3/15
## i Slice1: preprocessor 1/1, model 3/15 (predictions)
## i Slice1: preprocessor 1/1, model 4/15
## ✓ Slice1: preprocessor 1/1, model 4/15
## i Slice1: preprocessor 1/1, model 4/15 (predictions)
## i Slice1: preprocessor 1/1, model 5/15
## ✓ Slice1: preprocessor 1/1, model 5/15
## i Slice1: preprocessor 1/1, model 5/15 (predictions)
## i Slice1: preprocessor 1/1, model 6/15
## ✓ Slice1: preprocessor 1/1, model 6/15
## i Slice1: preprocessor 1/1, model 6/15 (predictions)
## i Slice1: preprocessor 1/1, model 7/15
## ✓ Slice1: preprocessor 1/1, model 7/15
## i Slice1: preprocessor 1/1, model 7/15 (predictions)
## i Slice1: preprocessor 1/1, model 8/15
## ✓ Slice1: preprocessor 1/1, model 8/15
## i Slice1: preprocessor 1/1, model 8/15 (predictions)
## i Slice1: preprocessor 1/1, model 9/15
## ✓ Slice1: preprocessor 1/1, model 9/15
## i Slice1: preprocessor 1/1, model 9/15 (predictions)
## i Slice1: preprocessor 1/1, model 10/15
## ✓ Slice1: preprocessor 1/1, model 10/15
## i Slice1: preprocessor 1/1, model 10/15 (predictions)
## i Slice1: preprocessor 1/1, model 11/15
## ✓ Slice1: preprocessor 1/1, model 11/15
## i Slice1: preprocessor 1/1, model 11/15 (predictions)
## i Slice1: preprocessor 1/1, model 12/15
## ✓ Slice1: preprocessor 1/1, model 12/15
## i Slice1: preprocessor 1/1, model 12/15 (predictions)
## i Slice1: preprocessor 1/1, model 13/15
## ✓ Slice1: preprocessor 1/1, model 13/15
## i Slice1: preprocessor 1/1, model 13/15 (predictions)
## i Slice1: preprocessor 1/1, model 14/15
## ✓ Slice1: preprocessor 1/1, model 14/15
## i Slice1: preprocessor 1/1, model 14/15 (predictions)
## i Slice1: preprocessor 1/1, model 15/15
## ✓ Slice1: preprocessor 1/1, model 15/15
## i Slice1: preprocessor 1/1, model 15/15 (predictions)
## ! Slice1: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 1`, `trees = 736`, `min_n = 29`, `tree_depth = 13`,
##     `learn_rate = 0.03225819`, `loss_reduction = 16.83498`, `sample_size =
##     0.5189291`, `stop_iter = 16`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 8`, `trees = 1061`, `min_n = 27`, `tree_depth = ...
##     `learn_rate = 0.001048049`, `loss_reduction = 0.00000007315673`, `sa...
##     = 0.6213994`, `stop_iter = 15`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 16`, `trees = 612`, `min_n = 34`, `tree_depth = 4`,
##     `learn_rate = 0.003180815`, `loss_reduction = 0.000000009868423`,
##     `sample_size = 0.9649639`, `stop_iter = 3`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 50`, `trees = 381`, `min_n = 37`, `tree_depth = 3`,
##     `learn_rate = 0.088006`, `loss_reduction = 2.870107`, `sample_size =
##     0.7395197`, `stop_iter = 6`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 55`, `trees = 53`, `min_n = 12`, `tree_depth = 8`,
##     `learn_rate = 0.001624878`, `loss_reduction = 0.0004805082`, `sample...
##     0.4140767`, `stop_iter = 6`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 58`, `trees = 136`, `min_n = 16`, `tree_depth = 5`,
##     `learn_rate = 0.002525758`, `loss_reduction = 0.0000002544028`, `sam...
##     = 0.3725255`, `stop_iter = 5`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice1: internal
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/15
## ✓ Slice2: preprocessor 1/1, model 1/15
## i Slice2: preprocessor 1/1, model 1/15 (predictions)
## i Slice2: preprocessor 1/1, model 2/15
## ✓ Slice2: preprocessor 1/1, model 2/15
## i Slice2: preprocessor 1/1, model 2/15 (predictions)
## i Slice2: preprocessor 1/1, model 3/15
## ✓ Slice2: preprocessor 1/1, model 3/15
## i Slice2: preprocessor 1/1, model 3/15 (predictions)
## i Slice2: preprocessor 1/1, model 4/15
## ✓ Slice2: preprocessor 1/1, model 4/15
## i Slice2: preprocessor 1/1, model 4/15 (predictions)
## i Slice2: preprocessor 1/1, model 5/15
## ✓ Slice2: preprocessor 1/1, model 5/15
## i Slice2: preprocessor 1/1, model 5/15 (predictions)
## i Slice2: preprocessor 1/1, model 6/15
## ✓ Slice2: preprocessor 1/1, model 6/15
## i Slice2: preprocessor 1/1, model 6/15 (predictions)
## i Slice2: preprocessor 1/1, model 7/15
## ✓ Slice2: preprocessor 1/1, model 7/15
## i Slice2: preprocessor 1/1, model 7/15 (predictions)
## i Slice2: preprocessor 1/1, model 8/15
## ✓ Slice2: preprocessor 1/1, model 8/15
## i Slice2: preprocessor 1/1, model 8/15 (predictions)
## i Slice2: preprocessor 1/1, model 9/15
## ✓ Slice2: preprocessor 1/1, model 9/15
## i Slice2: preprocessor 1/1, model 9/15 (predictions)
## i Slice2: preprocessor 1/1, model 10/15
## ✓ Slice2: preprocessor 1/1, model 10/15
## i Slice2: preprocessor 1/1, model 10/15 (predictions)
## i Slice2: preprocessor 1/1, model 11/15
## ✓ Slice2: preprocessor 1/1, model 11/15
## i Slice2: preprocessor 1/1, model 11/15 (predictions)
## i Slice2: preprocessor 1/1, model 12/15
## ✓ Slice2: preprocessor 1/1, model 12/15
## i Slice2: preprocessor 1/1, model 12/15 (predictions)
## i Slice2: preprocessor 1/1, model 13/15
## ✓ Slice2: preprocessor 1/1, model 13/15
## i Slice2: preprocessor 1/1, model 13/15 (predictions)
## i Slice2: preprocessor 1/1, model 14/15
## ✓ Slice2: preprocessor 1/1, model 14/15
## i Slice2: preprocessor 1/1, model 14/15 (predictions)
## i Slice2: preprocessor 1/1, model 15/15
## ✓ Slice2: preprocessor 1/1, model 15/15
## i Slice2: preprocessor 1/1, model 15/15 (predictions)
## ! Slice2: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 1`, `trees = 736`, `min_n = 29`, `tree_depth = 13`,
##     `learn_rate = 0.03225819`, `loss_reduction = 16.83498`, `sample_size =
##     0.5189291`, `stop_iter = 16`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 55`, `trees = 53`, `min_n = 12`, `tree_depth = 8`,
##     `learn_rate = 0.001624878`, `loss_reduction = 0.0004805082`, `sample...
##     0.4140767`, `stop_iter = 6`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 58`, `trees = 136`, `min_n = 16`, `tree_depth = 5`,
##     `learn_rate = 0.002525758`, `loss_reduction = 0.0000002544028`, `sam...
##     = 0.3725255`, `stop_iter = 5`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice2: internal
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/15
## ✓ Slice3: preprocessor 1/1, model 1/15
## i Slice3: preprocessor 1/1, model 1/15 (predictions)
## i Slice3: preprocessor 1/1, model 2/15
## ✓ Slice3: preprocessor 1/1, model 2/15
## i Slice3: preprocessor 1/1, model 2/15 (predictions)
## i Slice3: preprocessor 1/1, model 3/15
## ✓ Slice3: preprocessor 1/1, model 3/15
## i Slice3: preprocessor 1/1, model 3/15 (predictions)
## i Slice3: preprocessor 1/1, model 4/15
## ✓ Slice3: preprocessor 1/1, model 4/15
## i Slice3: preprocessor 1/1, model 4/15 (predictions)
## i Slice3: preprocessor 1/1, model 5/15
## ✓ Slice3: preprocessor 1/1, model 5/15
## i Slice3: preprocessor 1/1, model 5/15 (predictions)
## i Slice3: preprocessor 1/1, model 6/15
## ✓ Slice3: preprocessor 1/1, model 6/15
## i Slice3: preprocessor 1/1, model 6/15 (predictions)
## i Slice3: preprocessor 1/1, model 7/15
## ✓ Slice3: preprocessor 1/1, model 7/15
## i Slice3: preprocessor 1/1, model 7/15 (predictions)
## i Slice3: preprocessor 1/1, model 8/15
## ✓ Slice3: preprocessor 1/1, model 8/15
## i Slice3: preprocessor 1/1, model 8/15 (predictions)
## i Slice3: preprocessor 1/1, model 9/15
## ✓ Slice3: preprocessor 1/1, model 9/15
## i Slice3: preprocessor 1/1, model 9/15 (predictions)
## i Slice3: preprocessor 1/1, model 10/15
## ✓ Slice3: preprocessor 1/1, model 10/15
## i Slice3: preprocessor 1/1, model 10/15 (predictions)
## i Slice3: preprocessor 1/1, model 11/15
## ✓ Slice3: preprocessor 1/1, model 11/15
## i Slice3: preprocessor 1/1, model 11/15 (predictions)
## i Slice3: preprocessor 1/1, model 12/15
## ✓ Slice3: preprocessor 1/1, model 12/15
## i Slice3: preprocessor 1/1, model 12/15 (predictions)
## i Slice3: preprocessor 1/1, model 13/15
## ✓ Slice3: preprocessor 1/1, model 13/15
## i Slice3: preprocessor 1/1, model 13/15 (predictions)
## i Slice3: preprocessor 1/1, model 14/15
## ✓ Slice3: preprocessor 1/1, model 14/15
## i Slice3: preprocessor 1/1, model 14/15 (predictions)
## i Slice3: preprocessor 1/1, model 15/15
## ✓ Slice3: preprocessor 1/1, model 15/15
## i Slice3: preprocessor 1/1, model 15/15 (predictions)
## ! Slice3: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 1`, `trees = 736`, `min_n = 29`, `tree_depth = 13`,
##     `learn_rate = 0.03225819`, `loss_reduction = 16.83498`, `sample_size =
##     0.5189291`, `stop_iter = 16`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 50`, `trees = 381`, `min_n = 37`, `tree_depth = 3`,
##     `learn_rate = 0.088006`, `loss_reduction = 2.870107`, `sample_size =
##     0.7395197`, `stop_iter = 6`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 55`, `trees = 53`, `min_n = 12`, `tree_depth = 8`,
##     `learn_rate = 0.001624878`, `loss_reduction = 0.0004805082`, `sample...
##     0.4140767`, `stop_iter = 6`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 58`, `trees = 136`, `min_n = 16`, `tree_depth = 5`,
##     `learn_rate = 0.002525758`, `loss_reduction = 0.0000002544028`, `sam...
##     = 0.3725255`, `stop_iter = 5`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice3: internal
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/15
## ✓ Slice4: preprocessor 1/1, model 1/15
## i Slice4: preprocessor 1/1, model 1/15 (predictions)
## i Slice4: preprocessor 1/1, model 2/15
## ✓ Slice4: preprocessor 1/1, model 2/15
## i Slice4: preprocessor 1/1, model 2/15 (predictions)
## i Slice4: preprocessor 1/1, model 3/15
## ✓ Slice4: preprocessor 1/1, model 3/15
## i Slice4: preprocessor 1/1, model 3/15 (predictions)
## i Slice4: preprocessor 1/1, model 4/15
## ✓ Slice4: preprocessor 1/1, model 4/15
## i Slice4: preprocessor 1/1, model 4/15 (predictions)
## i Slice4: preprocessor 1/1, model 5/15
## ✓ Slice4: preprocessor 1/1, model 5/15
## i Slice4: preprocessor 1/1, model 5/15 (predictions)
## i Slice4: preprocessor 1/1, model 6/15
## ✓ Slice4: preprocessor 1/1, model 6/15
## i Slice4: preprocessor 1/1, model 6/15 (predictions)
## i Slice4: preprocessor 1/1, model 7/15
## ✓ Slice4: preprocessor 1/1, model 7/15
## i Slice4: preprocessor 1/1, model 7/15 (predictions)
## i Slice4: preprocessor 1/1, model 8/15
## ✓ Slice4: preprocessor 1/1, model 8/15
## i Slice4: preprocessor 1/1, model 8/15 (predictions)
## i Slice4: preprocessor 1/1, model 9/15
## ✓ Slice4: preprocessor 1/1, model 9/15
## i Slice4: preprocessor 1/1, model 9/15 (predictions)
## i Slice4: preprocessor 1/1, model 10/15
## ✓ Slice4: preprocessor 1/1, model 10/15
## i Slice4: preprocessor 1/1, model 10/15 (predictions)
## i Slice4: preprocessor 1/1, model 11/15
## ✓ Slice4: preprocessor 1/1, model 11/15
## i Slice4: preprocessor 1/1, model 11/15 (predictions)
## i Slice4: preprocessor 1/1, model 12/15
## ✓ Slice4: preprocessor 1/1, model 12/15
## i Slice4: preprocessor 1/1, model 12/15 (predictions)
## i Slice4: preprocessor 1/1, model 13/15
## ✓ Slice4: preprocessor 1/1, model 13/15
## i Slice4: preprocessor 1/1, model 13/15 (predictions)
## i Slice4: preprocessor 1/1, model 14/15
## ✓ Slice4: preprocessor 1/1, model 14/15
## i Slice4: preprocessor 1/1, model 14/15 (predictions)
## i Slice4: preprocessor 1/1, model 15/15
## ✓ Slice4: preprocessor 1/1, model 15/15
## i Slice4: preprocessor 1/1, model 15/15 (predictions)
## ! Slice4: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 1`, `trees = 736`, `min_n = 29`, `tree_depth = 13`,
##     `learn_rate = 0.03225819`, `loss_reduction = 16.83498`, `sample_size =
##     0.5189291`, `stop_iter = 16`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 8`, `trees = 1061`, `min_n = 27`, `tree_depth = ...
##     `learn_rate = 0.001048049`, `loss_reduction = 0.00000007315673`, `sa...
##     = 0.6213994`, `stop_iter = 15`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 16`, `trees = 612`, `min_n = 34`, `tree_depth = 4`,
##     `learn_rate = 0.003180815`, `loss_reduction = 0.000000009868423`,
##     `sample_size = 0.9649639`, `stop_iter = 3`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 29`, `trees = 1491`, `min_n = 32`, `tree_depth =...
##     `learn_rate = 0.02451377`, `loss_reduction = 0.00000000103823`, `sam...
##     = 0.1995801`, `stop_iter = 11`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 50`, `trees = 381`, `min_n = 37`, `tree_depth = 3`,
##     `learn_rate = 0.088006`, `loss_reduction = 2.870107`, `sample_size =
##     0.7395197`, `stop_iter = 6`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 55`, `trees = 53`, `min_n = 12`, `tree_depth = 8`,
##     `learn_rate = 0.001624878`, `loss_reduction = 0.0004805082`, `sample...
##     0.4140767`, `stop_iter = 6`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 58`, `trees = 136`, `min_n = 16`, `tree_depth = 5`,
##     `learn_rate = 0.002525758`, `loss_reduction = 0.0000002544028`, `sam...
##     = 0.3725255`, `stop_iter = 5`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice4: internal
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/15
## ✓ Slice5: preprocessor 1/1, model 1/15
## i Slice5: preprocessor 1/1, model 1/15 (predictions)
## i Slice5: preprocessor 1/1, model 2/15
## ✓ Slice5: preprocessor 1/1, model 2/15
## i Slice5: preprocessor 1/1, model 2/15 (predictions)
## i Slice5: preprocessor 1/1, model 3/15
## ✓ Slice5: preprocessor 1/1, model 3/15
## i Slice5: preprocessor 1/1, model 3/15 (predictions)
## i Slice5: preprocessor 1/1, model 4/15
## ✓ Slice5: preprocessor 1/1, model 4/15
## i Slice5: preprocessor 1/1, model 4/15 (predictions)
## i Slice5: preprocessor 1/1, model 5/15
## ✓ Slice5: preprocessor 1/1, model 5/15
## i Slice5: preprocessor 1/1, model 5/15 (predictions)
## i Slice5: preprocessor 1/1, model 6/15
## ✓ Slice5: preprocessor 1/1, model 6/15
## i Slice5: preprocessor 1/1, model 6/15 (predictions)
## i Slice5: preprocessor 1/1, model 7/15
## ✓ Slice5: preprocessor 1/1, model 7/15
## i Slice5: preprocessor 1/1, model 7/15 (predictions)
## i Slice5: preprocessor 1/1, model 8/15
## ✓ Slice5: preprocessor 1/1, model 8/15
## i Slice5: preprocessor 1/1, model 8/15 (predictions)
## i Slice5: preprocessor 1/1, model 9/15
## ✓ Slice5: preprocessor 1/1, model 9/15
## i Slice5: preprocessor 1/1, model 9/15 (predictions)
## i Slice5: preprocessor 1/1, model 10/15
## ✓ Slice5: preprocessor 1/1, model 10/15
## i Slice5: preprocessor 1/1, model 10/15 (predictions)
## i Slice5: preprocessor 1/1, model 11/15
## ✓ Slice5: preprocessor 1/1, model 11/15
## i Slice5: preprocessor 1/1, model 11/15 (predictions)
## i Slice5: preprocessor 1/1, model 12/15
## ✓ Slice5: preprocessor 1/1, model 12/15
## i Slice5: preprocessor 1/1, model 12/15 (predictions)
## i Slice5: preprocessor 1/1, model 13/15
## ✓ Slice5: preprocessor 1/1, model 13/15
## i Slice5: preprocessor 1/1, model 13/15 (predictions)
## i Slice5: preprocessor 1/1, model 14/15
## ✓ Slice5: preprocessor 1/1, model 14/15
## i Slice5: preprocessor 1/1, model 14/15 (predictions)
## i Slice5: preprocessor 1/1, model 15/15
## ✓ Slice5: preprocessor 1/1, model 15/15
## i Slice5: preprocessor 1/1, model 15/15 (predictions)
## ! Slice5: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 1`, `trees = 736`, `min_n = 29`, `tree_depth = 13`,
##     `learn_rate = 0.03225819`, `loss_reduction = 16.83498`, `sample_size =
##     0.5189291`, `stop_iter = 16`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 29`, `trees = 1491`, `min_n = 32`, `tree_depth =...
##     `learn_rate = 0.02451377`, `loss_reduction = 0.00000000103823`, `sam...
##     = 0.1995801`, `stop_iter = 11`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 55`, `trees = 53`, `min_n = 12`, `tree_depth = 8`,
##     `learn_rate = 0.001624878`, `loss_reduction = 0.0004805082`, `sample...
##     0.4140767`, `stop_iter = 6`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `mtry = 58`, `trees = 136`, `min_n = 16`, `tree_depth = 5`,
##     `learn_rate = 0.002525758`, `loss_reduction = 0.0000002544028`, `sam...
##     = 0.3725255`, `stop_iter = 5`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice5: internal
toc()
## 53.89 sec elapsed
tune_result_xgboost %>% 
  show_best(metric = "rmse", n = Inf)
## # A tibble: 15 × 14
##     mtry trees min_n tree_depth learn_rate loss_reduction sample_size stop_iter
##    <int> <int> <int>      <int>      <dbl>          <dbl>       <dbl>     <int>
##  1    13   909     9          6    0.0521        8.18e- 7       0.566        10
##  2    36  1833     2         14    0.121         3.66e- 3       0.926        18
##  3    43  1281    14         10    0.0112        1.47e- 5       0.850         8
##  4    45  1951    18          7    0.00680       4.59e-10       0.793        20
##  5    35  1094     5          1    0.0213        4.03e- 5       0.156        10
##  6    61  1352    38          4    0.282         5.09e- 2       0.644        17
##  7    21  1641    21          9    0.00871       1.84e- 2       0.320        14
##  8    23   484    24         10    0.147         1.98e- 1       0.221        13
##  9    50   381    37          3    0.0880        2.87e+ 0       0.740         6
## 10    16   612    34          4    0.00318       9.87e- 9       0.965         3
## 11     1   736    29         13    0.0323        1.68e+ 1       0.519        16
## 12    29  1491    32         12    0.0245        1.04e- 9       0.200        11
## 13     8  1061    27         14    0.00105       7.32e- 8       0.621        15
## 14    58   136    16          5    0.00253       2.54e- 7       0.373         5
## 15    55    53    12          8    0.00162       4.81e- 4       0.414         6
## # ℹ 6 more variables: .metric <chr>, .estimator <chr>, mean <dbl>, n <int>,
## #   std_err <dbl>, .config <chr>
tune_result_xgboost %>% write_rds("tune_result_xgboost")

model_fit_xgboost_tune %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_xgboost %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  ) %>% 
  fit(training(splits)) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>%
  # modeltime_forecast(new_data = test_data, actual_data = ihsg_tbl) %>%
  # plot_modeltime_forecast()
  modeltime_refit(data = yield) %>%
  # modeltime_forecast(new_data = ihsg_future_tbl, actual_data = ihsg_tbl) %>%
  modeltime_forecast(h = "1 year", actual_data = yield) %>%
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.
model_fit_xgboost_best <- model_fit_xgboost %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_xgboost %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  )

Cubist

model_spec_cubist <- cubist_rules(committees = 100, 
                                  neighbors = 20, 
                                  max_rules = 1000) %>% 
  set_engine("Cubist")

set.seed(123)
model_fit_cubist <- workflow() %>% 
  add_model(model_spec_cubist) %>% 
  add_recipe(recipe_spec %>% 
               step_mutate(time = as.numeric(time))) %>% 
  fit(training(splits))
## Warning: The number of neighbors should be >= 0 and <= 9. Truncating the value.
set.seed(123)
model_fit_cubist %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.
set.seed(123)
model_fit_cubist %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(h = "1 year", actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

tune Cubist

model_spec_cubist_tune <- cubist_rules(committees = tune(), 
                                  neighbors = tune(), 
                                  max_rules = tune()) %>% 
  set_engine("Cubist")

grid_spec_cubist <- grid_latin_hypercube(
  # extract_parameter_dials(model_spec_prophet_boost_tune),
  parameters(model_spec_cubist_tune),
  size = 15
)

model_fit_cubist_tune <- model_fit_cubist %>% 
  update_model(model_spec_cubist_tune)

tic()
tune_result_cubist <- model_fit_cubist_tune %>%
  tune_grid(
    resamples = resamples_tscv_no_acum,
    grid      = grid_spec_cubist,
    metrics   = default_forecast_accuracy_metric_set(),
    control   = control_grid(verbose = TRUE, save_pred = TRUE)
  )
## Warning: package 'Cubist' was built under R version 4.2.3
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/15
## ✓ Slice1: preprocessor 1/1, model 1/15
## i Slice1: preprocessor 1/1, model 1/15 (predictions)
## i Slice1: preprocessor 1/1, model 2/15
## ✓ Slice1: preprocessor 1/1, model 2/15
## i Slice1: preprocessor 1/1, model 2/15 (predictions)
## i Slice1: preprocessor 1/1, model 3/15
## ✓ Slice1: preprocessor 1/1, model 3/15
## i Slice1: preprocessor 1/1, model 3/15 (predictions)
## i Slice1: preprocessor 1/1, model 4/15
## ✓ Slice1: preprocessor 1/1, model 4/15
## i Slice1: preprocessor 1/1, model 4/15 (predictions)
## i Slice1: preprocessor 1/1, model 5/15
## ✓ Slice1: preprocessor 1/1, model 5/15
## i Slice1: preprocessor 1/1, model 5/15 (predictions)
## i Slice1: preprocessor 1/1, model 6/15
## ✓ Slice1: preprocessor 1/1, model 6/15
## i Slice1: preprocessor 1/1, model 6/15 (predictions)
## i Slice1: preprocessor 1/1, model 7/15
## ✓ Slice1: preprocessor 1/1, model 7/15
## i Slice1: preprocessor 1/1, model 7/15 (predictions)
## i Slice1: preprocessor 1/1, model 8/15
## ✓ Slice1: preprocessor 1/1, model 8/15
## i Slice1: preprocessor 1/1, model 8/15 (predictions)
## i Slice1: preprocessor 1/1, model 9/15
## ✓ Slice1: preprocessor 1/1, model 9/15
## i Slice1: preprocessor 1/1, model 9/15 (predictions)
## i Slice1: preprocessor 1/1, model 10/15
## ✓ Slice1: preprocessor 1/1, model 10/15
## i Slice1: preprocessor 1/1, model 10/15 (predictions)
## i Slice1: preprocessor 1/1, model 11/15
## ✓ Slice1: preprocessor 1/1, model 11/15
## i Slice1: preprocessor 1/1, model 11/15 (predictions)
## i Slice1: preprocessor 1/1, model 12/15
## ✓ Slice1: preprocessor 1/1, model 12/15
## i Slice1: preprocessor 1/1, model 12/15 (predictions)
## i Slice1: preprocessor 1/1, model 13/15
## ✓ Slice1: preprocessor 1/1, model 13/15
## i Slice1: preprocessor 1/1, model 13/15 (predictions)
## i Slice1: preprocessor 1/1, model 14/15
## ✓ Slice1: preprocessor 1/1, model 14/15
## i Slice1: preprocessor 1/1, model 14/15 (predictions)
## i Slice1: preprocessor 1/1, model 15/15
## ✓ Slice1: preprocessor 1/1, model 15/15
## i Slice1: preprocessor 1/1, model 15/15 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/15
## ✓ Slice2: preprocessor 1/1, model 1/15
## i Slice2: preprocessor 1/1, model 1/15 (predictions)
## i Slice2: preprocessor 1/1, model 2/15
## ✓ Slice2: preprocessor 1/1, model 2/15
## i Slice2: preprocessor 1/1, model 2/15 (predictions)
## i Slice2: preprocessor 1/1, model 3/15
## ✓ Slice2: preprocessor 1/1, model 3/15
## i Slice2: preprocessor 1/1, model 3/15 (predictions)
## i Slice2: preprocessor 1/1, model 4/15
## ✓ Slice2: preprocessor 1/1, model 4/15
## i Slice2: preprocessor 1/1, model 4/15 (predictions)
## i Slice2: preprocessor 1/1, model 5/15
## ✓ Slice2: preprocessor 1/1, model 5/15
## i Slice2: preprocessor 1/1, model 5/15 (predictions)
## i Slice2: preprocessor 1/1, model 6/15
## ✓ Slice2: preprocessor 1/1, model 6/15
## i Slice2: preprocessor 1/1, model 6/15 (predictions)
## i Slice2: preprocessor 1/1, model 7/15
## ✓ Slice2: preprocessor 1/1, model 7/15
## i Slice2: preprocessor 1/1, model 7/15 (predictions)
## i Slice2: preprocessor 1/1, model 8/15
## ✓ Slice2: preprocessor 1/1, model 8/15
## i Slice2: preprocessor 1/1, model 8/15 (predictions)
## i Slice2: preprocessor 1/1, model 9/15
## ✓ Slice2: preprocessor 1/1, model 9/15
## i Slice2: preprocessor 1/1, model 9/15 (predictions)
## i Slice2: preprocessor 1/1, model 10/15
## ✓ Slice2: preprocessor 1/1, model 10/15
## i Slice2: preprocessor 1/1, model 10/15 (predictions)
## i Slice2: preprocessor 1/1, model 11/15
## ✓ Slice2: preprocessor 1/1, model 11/15
## i Slice2: preprocessor 1/1, model 11/15 (predictions)
## i Slice2: preprocessor 1/1, model 12/15
## ✓ Slice2: preprocessor 1/1, model 12/15
## i Slice2: preprocessor 1/1, model 12/15 (predictions)
## i Slice2: preprocessor 1/1, model 13/15
## ✓ Slice2: preprocessor 1/1, model 13/15
## i Slice2: preprocessor 1/1, model 13/15 (predictions)
## i Slice2: preprocessor 1/1, model 14/15
## ✓ Slice2: preprocessor 1/1, model 14/15
## i Slice2: preprocessor 1/1, model 14/15 (predictions)
## i Slice2: preprocessor 1/1, model 15/15
## ✓ Slice2: preprocessor 1/1, model 15/15
## i Slice2: preprocessor 1/1, model 15/15 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/15
## ✓ Slice3: preprocessor 1/1, model 1/15
## i Slice3: preprocessor 1/1, model 1/15 (predictions)
## i Slice3: preprocessor 1/1, model 2/15
## ✓ Slice3: preprocessor 1/1, model 2/15
## i Slice3: preprocessor 1/1, model 2/15 (predictions)
## i Slice3: preprocessor 1/1, model 3/15
## ✓ Slice3: preprocessor 1/1, model 3/15
## i Slice3: preprocessor 1/1, model 3/15 (predictions)
## i Slice3: preprocessor 1/1, model 4/15
## ✓ Slice3: preprocessor 1/1, model 4/15
## i Slice3: preprocessor 1/1, model 4/15 (predictions)
## i Slice3: preprocessor 1/1, model 5/15
## ✓ Slice3: preprocessor 1/1, model 5/15
## i Slice3: preprocessor 1/1, model 5/15 (predictions)
## i Slice3: preprocessor 1/1, model 6/15
## ✓ Slice3: preprocessor 1/1, model 6/15
## i Slice3: preprocessor 1/1, model 6/15 (predictions)
## i Slice3: preprocessor 1/1, model 7/15
## ✓ Slice3: preprocessor 1/1, model 7/15
## i Slice3: preprocessor 1/1, model 7/15 (predictions)
## i Slice3: preprocessor 1/1, model 8/15
## ✓ Slice3: preprocessor 1/1, model 8/15
## i Slice3: preprocessor 1/1, model 8/15 (predictions)
## i Slice3: preprocessor 1/1, model 9/15
## ✓ Slice3: preprocessor 1/1, model 9/15
## i Slice3: preprocessor 1/1, model 9/15 (predictions)
## i Slice3: preprocessor 1/1, model 10/15
## ✓ Slice3: preprocessor 1/1, model 10/15
## i Slice3: preprocessor 1/1, model 10/15 (predictions)
## i Slice3: preprocessor 1/1, model 11/15
## ✓ Slice3: preprocessor 1/1, model 11/15
## i Slice3: preprocessor 1/1, model 11/15 (predictions)
## i Slice3: preprocessor 1/1, model 12/15
## ✓ Slice3: preprocessor 1/1, model 12/15
## i Slice3: preprocessor 1/1, model 12/15 (predictions)
## i Slice3: preprocessor 1/1, model 13/15
## ✓ Slice3: preprocessor 1/1, model 13/15
## i Slice3: preprocessor 1/1, model 13/15 (predictions)
## i Slice3: preprocessor 1/1, model 14/15
## ✓ Slice3: preprocessor 1/1, model 14/15
## i Slice3: preprocessor 1/1, model 14/15 (predictions)
## i Slice3: preprocessor 1/1, model 15/15
## ✓ Slice3: preprocessor 1/1, model 15/15
## i Slice3: preprocessor 1/1, model 15/15 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/15
## ✓ Slice4: preprocessor 1/1, model 1/15
## i Slice4: preprocessor 1/1, model 1/15 (predictions)
## i Slice4: preprocessor 1/1, model 2/15
## ✓ Slice4: preprocessor 1/1, model 2/15
## i Slice4: preprocessor 1/1, model 2/15 (predictions)
## i Slice4: preprocessor 1/1, model 3/15
## ✓ Slice4: preprocessor 1/1, model 3/15
## i Slice4: preprocessor 1/1, model 3/15 (predictions)
## i Slice4: preprocessor 1/1, model 4/15
## ✓ Slice4: preprocessor 1/1, model 4/15
## i Slice4: preprocessor 1/1, model 4/15 (predictions)
## i Slice4: preprocessor 1/1, model 5/15
## ✓ Slice4: preprocessor 1/1, model 5/15
## i Slice4: preprocessor 1/1, model 5/15 (predictions)
## i Slice4: preprocessor 1/1, model 6/15
## ✓ Slice4: preprocessor 1/1, model 6/15
## i Slice4: preprocessor 1/1, model 6/15 (predictions)
## i Slice4: preprocessor 1/1, model 7/15
## ✓ Slice4: preprocessor 1/1, model 7/15
## i Slice4: preprocessor 1/1, model 7/15 (predictions)
## i Slice4: preprocessor 1/1, model 8/15
## ✓ Slice4: preprocessor 1/1, model 8/15
## i Slice4: preprocessor 1/1, model 8/15 (predictions)
## i Slice4: preprocessor 1/1, model 9/15
## ✓ Slice4: preprocessor 1/1, model 9/15
## i Slice4: preprocessor 1/1, model 9/15 (predictions)
## i Slice4: preprocessor 1/1, model 10/15
## ✓ Slice4: preprocessor 1/1, model 10/15
## i Slice4: preprocessor 1/1, model 10/15 (predictions)
## i Slice4: preprocessor 1/1, model 11/15
## ✓ Slice4: preprocessor 1/1, model 11/15
## i Slice4: preprocessor 1/1, model 11/15 (predictions)
## i Slice4: preprocessor 1/1, model 12/15
## ✓ Slice4: preprocessor 1/1, model 12/15
## i Slice4: preprocessor 1/1, model 12/15 (predictions)
## i Slice4: preprocessor 1/1, model 13/15
## ✓ Slice4: preprocessor 1/1, model 13/15
## i Slice4: preprocessor 1/1, model 13/15 (predictions)
## i Slice4: preprocessor 1/1, model 14/15
## ✓ Slice4: preprocessor 1/1, model 14/15
## i Slice4: preprocessor 1/1, model 14/15 (predictions)
## i Slice4: preprocessor 1/1, model 15/15
## ✓ Slice4: preprocessor 1/1, model 15/15
## i Slice4: preprocessor 1/1, model 15/15 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/15
## ✓ Slice5: preprocessor 1/1, model 1/15
## i Slice5: preprocessor 1/1, model 1/15 (predictions)
## i Slice5: preprocessor 1/1, model 2/15
## ✓ Slice5: preprocessor 1/1, model 2/15
## i Slice5: preprocessor 1/1, model 2/15 (predictions)
## i Slice5: preprocessor 1/1, model 3/15
## ✓ Slice5: preprocessor 1/1, model 3/15
## i Slice5: preprocessor 1/1, model 3/15 (predictions)
## i Slice5: preprocessor 1/1, model 4/15
## ✓ Slice5: preprocessor 1/1, model 4/15
## i Slice5: preprocessor 1/1, model 4/15 (predictions)
## i Slice5: preprocessor 1/1, model 5/15
## ✓ Slice5: preprocessor 1/1, model 5/15
## i Slice5: preprocessor 1/1, model 5/15 (predictions)
## i Slice5: preprocessor 1/1, model 6/15
## ✓ Slice5: preprocessor 1/1, model 6/15
## i Slice5: preprocessor 1/1, model 6/15 (predictions)
## i Slice5: preprocessor 1/1, model 7/15
## ✓ Slice5: preprocessor 1/1, model 7/15
## i Slice5: preprocessor 1/1, model 7/15 (predictions)
## i Slice5: preprocessor 1/1, model 8/15
## ✓ Slice5: preprocessor 1/1, model 8/15
## i Slice5: preprocessor 1/1, model 8/15 (predictions)
## i Slice5: preprocessor 1/1, model 9/15
## ✓ Slice5: preprocessor 1/1, model 9/15
## i Slice5: preprocessor 1/1, model 9/15 (predictions)
## i Slice5: preprocessor 1/1, model 10/15
## ✓ Slice5: preprocessor 1/1, model 10/15
## i Slice5: preprocessor 1/1, model 10/15 (predictions)
## i Slice5: preprocessor 1/1, model 11/15
## ✓ Slice5: preprocessor 1/1, model 11/15
## i Slice5: preprocessor 1/1, model 11/15 (predictions)
## i Slice5: preprocessor 1/1, model 12/15
## ✓ Slice5: preprocessor 1/1, model 12/15
## i Slice5: preprocessor 1/1, model 12/15 (predictions)
## i Slice5: preprocessor 1/1, model 13/15
## ✓ Slice5: preprocessor 1/1, model 13/15
## i Slice5: preprocessor 1/1, model 13/15 (predictions)
## i Slice5: preprocessor 1/1, model 14/15
## ✓ Slice5: preprocessor 1/1, model 14/15
## i Slice5: preprocessor 1/1, model 14/15 (predictions)
## i Slice5: preprocessor 1/1, model 15/15
## ✓ Slice5: preprocessor 1/1, model 15/15
## i Slice5: preprocessor 1/1, model 15/15 (predictions)
toc()
## 43 sec elapsed
tune_result_cubist %>% 
  show_best(metric = "rmse", n = Inf)
## # A tibble: 15 × 9
##    committees neighbors max_rules .metric .estimator  mean     n std_err .config
##         <int>     <int>     <int> <chr>   <chr>      <dbl> <int>   <dbl> <chr>  
##  1          4         8       129 rmse    standard   0.348     5   0.117 Prepro…
##  2         15         0       336 rmse    standard   0.382     5   0.120 Prepro…
##  3         98         7       414 rmse    standard   0.385     5   0.123 Prepro…
##  4         28         7       476 rmse    standard   0.386     5   0.120 Prepro…
##  5         36         4        82 rmse    standard   0.387     5   0.118 Prepro…
##  6         53         9        37 rmse    standard   0.387     5   0.122 Prepro…
##  7         68         5       185 rmse    standard   0.387     5   0.120 Prepro…
##  8         78         6       464 rmse    standard   0.388     5   0.121 Prepro…
##  9         44         3       161 rmse    standard   0.388     5   0.120 Prepro…
## 10         86         6       221 rmse    standard   0.389     5   0.123 Prepro…
## 11         56         4       380 rmse    standard   0.389     5   0.121 Prepro…
## 12         64         3       261 rmse    standard   0.390     5   0.120 Prepro…
## 13         13         2       330 rmse    standard   0.393     5   0.118 Prepro…
## 14         92         2        25 rmse    standard   0.396     5   0.122 Prepro…
## 15         21         1       284 rmse    standard   0.398     5   0.121 Prepro…
tune_result_cubist %>% write_rds("tune_result_cubist")

model_fit_cubist_tune %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_cubist %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  ) %>% 
  fit(training(splits)) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>%
  # modeltime_forecast(new_data = test_data, actual_data = ihsg_tbl) %>%
  # plot_modeltime_forecast()
  modeltime_refit(data = yield) %>%
  # modeltime_forecast(new_data = ihsg_future_tbl, actual_data = ihsg_tbl) %>%
  modeltime_forecast(h = "1 year", actual_data = yield) %>%
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.
model_fit_cubist_tune <- model_fit_cubist %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_cubist %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  )

NNETAR

model_spec_nnetar <- nnetar_reg(
    non_seasonal_ar = 2,
    seasonal_ar     = 1, 
    hidden_units    = 10,
    penalty         = 10,
    num_networks    = 10,
    epochs          = 50
) %>%
    set_engine("nnetar")

set.seed(123)
model_fit_nnetar <- workflow() %>% 
  add_model(model_spec_nnetar) %>% 
  add_recipe(recipe_spec) %>% # harus ada data Date
  fit(training(splits) %>% drop_na())
## frequency = 5 observations per 1 week
set.seed(123)
model_fit_nnetar %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

Prophet Boost

model_spec_prophet_boost <- prophet_boost(
  
  # Prophet Params
  changepoint_num = 25, 
  changepoint_range = 0.8,
  seasonality_daily = F, 
  seasonality_weekly = F, 
  seasonality_yearly = F,
  
  # XGBoost
  mtry = 0.75, 
  min_n = 20,
  tree_depth = 3, 
  learn_rate = 0.35, 
  loss_reduction = 0.15, 
  trees = 300) %>% 
  
  set_engine("prophet_xgboost", counts = F)
                
# Workflow

set.seed(123)
model_fit_prophet_boost <- workflow() %>% 
  add_model(model_spec_prophet_boost) %>% 
  # add_recipe(recipe_spec_base_ihsg %>% step_mutate(date = as.numeric(date))) %>% 
  add_recipe(recipe_spec) %>% 
  fit(training(splits))

set.seed(123)
model_fit_prophet_boost %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  # modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  modeltime_forecast(h = "1 year", actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

tune Prophet Boost

# model_spec_prophet_boost_tune <- prophet_boost(
#                                        growth = "linear",
#                                        changepoint_num = tune(), 
#                                        changepoint_range = tune(), 
#                                        season = "additive",
#                                        seasonality_yearly = T, 
#                                        seasonality_weekly = T, 
#                                        seasonality_daily = T, 
#                                        prior_scale_changepoints = tune(), 
#                                        prior_scale_seasonality = tune(), 
#                                        trees = tune(), 
#                                        min_n = tune(), 
#                                        tree_depth = tune(), 
#                                        learn_rate = tune(), 
#                                        loss_reduction = tune(), 
#                                        sample_size = tune(),
#                                        stop_iter = tune(), 
#                                        # mode = "regression", 
#                                        mtry = tune()
# ) %>%
#   set_mode("regression") %>% 
# set_engine("prophet_xgboost")
# 
# grid_spec_prophet_boost <- grid_latin_hypercube(
#   # extract_parameter_dials(model_spec_prophet_boost_tune),
#   parameters(model_spec_prophet_boost_tune) %>%
#         update(mtry = mtry(range = c(0, 65)), sample_size = sample_size(range = c(0, 100))),
#   size = 15
# )
# 
# model_fit_prophet_boost_tune <- model_fit_prophet_boost %>% 
#   update_model(model_spec_prophet_boost_tune)
# 
# tic()
# tune_result_prophet_boost <- model_fit_prophet_boost_tune %>%
#   tune_grid(
#     resamples = resamples_tscv_no_acum,
#     grid      = grid_spec_prophet_boost,
#     metrics   = default_forecast_accuracy_metric_set(),
#     control   = control_grid(verbose = TRUE, save_pred = TRUE)
#   )
# toc()
# 
# tune_result_prophet_boost %>% 
#   show_best(metric = "rmse", n = Inf)
# 
# tune_result_prophet_boost %>% write_rds("tune_result_prophet_boost")
# 
# model_fit_prophet_boost_tune %>% 
#   # update_model(model_spec_prophet) %>% 
#   finalize_workflow(
#     tune_result_prophet_boost %>% 
#       show_best(metric = "rmse") %>%
#       dplyr::slice(1)
#   ) %>% 
#   fit(training(splits)) %>% 
#   modeltime_calibrate(new_data = testing(splits)) %>%
#   # modeltime_forecast(new_data = test_data, actual_data = ihsg_tbl) %>%
#   # plot_modeltime_forecast()
#   modeltime_refit(data = yield) %>%
#   # modeltime_forecast(new_data = ihsg_future_tbl, actual_data = ihsg_tbl) %>%
#   modeltime_forecast(h = "1 year", actual_data = yield) %>%
#   plot_modeltime_forecast(.conf_interval_show = F)
# 
# model_fit_prophet_boost_tune <- model_fit_prophet_boost %>% 
#   # update_model(model_spec_prophet) %>% 
#   finalize_workflow(
#     tune_result_prophet_boost %>% 
#       show_best(metric = "rmse") %>%
#       dplyr::slice(1)
#   )
# 
# model_fit_prophet_boost_tune %>% 
#   modeltime_calibrate(new_data = testing(splits)) %>% 
#   modeltime_refit(data = yield) %>% 
#   modeltime_forecast(h = "1 year", actual_data = yield) %>% 
#   plot_modeltime_forecast(.conf_interval_show = F)

BART

bt_reg_spec <- 
  bart(trees = 15) %>% 
  # This model can be used for classification or regression, so set mode
  set_mode("regression") %>% 
  set_engine("dbarts")

set.seed(123)
bt_reg_fit <- bt_reg_spec %>% 
  fit(close ~ time, data = training(splits))

model_fit_bart <- workflow() %>% 
  add_model(bt_reg_spec) %>% 
  add_recipe(recipe_spec %>%
               step_mutate(time = as.numeric(time))) %>%
  fit(training(splits))

model_fit_bart %>% 
  modeltime_calibrate(new_data = testing(splits)) %>%
  modeltime_forecast(new_data = testing(splits), actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

tune BART

bart_tune_spec <- 
  bart(trees = tune(), 
       prior_terminal_node_coef = tune(), 
       prior_terminal_node_expo = tune(), 
       prior_outcome_range = tune()) %>% 
  # This model can be used for classification or regression, so set mode
  set_mode("regression") %>% 
  set_engine("dbarts")

grid_spec_bart <- grid_latin_hypercube(
  # extract_parameter_dials(model_spec_prophet_boost_tune),
  parameters(bart_tune_spec),
  size = 15
)

model_fit_bart_tune <- model_fit_bart %>% 
  update_model(bart_tune_spec)

tic()
tune_result_bart <- model_fit_bart_tune %>%
  tune_grid(
    resamples = resamples_tscv_no_acum,
    grid      = grid_spec_bart,
    metrics   = default_forecast_accuracy_metric_set(),
    control   = control_grid(verbose = TRUE, save_pred = TRUE)
  )
## Warning: package 'dbarts' was built under R version 4.2.3
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/15
## ✓ Slice1: preprocessor 1/1, model 1/15
## i Slice1: preprocessor 1/1, model 1/15 (predictions)
## i Slice1: preprocessor 1/1, model 2/15
## ✓ Slice1: preprocessor 1/1, model 2/15
## i Slice1: preprocessor 1/1, model 2/15 (predictions)
## i Slice1: preprocessor 1/1, model 3/15
## ✓ Slice1: preprocessor 1/1, model 3/15
## i Slice1: preprocessor 1/1, model 3/15 (predictions)
## i Slice1: preprocessor 1/1, model 4/15
## ✓ Slice1: preprocessor 1/1, model 4/15
## i Slice1: preprocessor 1/1, model 4/15 (predictions)
## i Slice1: preprocessor 1/1, model 5/15
## ✓ Slice1: preprocessor 1/1, model 5/15
## i Slice1: preprocessor 1/1, model 5/15 (predictions)
## i Slice1: preprocessor 1/1, model 6/15
## ✓ Slice1: preprocessor 1/1, model 6/15
## i Slice1: preprocessor 1/1, model 6/15 (predictions)
## i Slice1: preprocessor 1/1, model 7/15
## ✓ Slice1: preprocessor 1/1, model 7/15
## i Slice1: preprocessor 1/1, model 7/15 (predictions)
## i Slice1: preprocessor 1/1, model 8/15
## ✓ Slice1: preprocessor 1/1, model 8/15
## i Slice1: preprocessor 1/1, model 8/15 (predictions)
## i Slice1: preprocessor 1/1, model 9/15
## ✓ Slice1: preprocessor 1/1, model 9/15
## i Slice1: preprocessor 1/1, model 9/15 (predictions)
## i Slice1: preprocessor 1/1, model 10/15
## ✓ Slice1: preprocessor 1/1, model 10/15
## i Slice1: preprocessor 1/1, model 10/15 (predictions)
## i Slice1: preprocessor 1/1, model 11/15
## ✓ Slice1: preprocessor 1/1, model 11/15
## i Slice1: preprocessor 1/1, model 11/15 (predictions)
## i Slice1: preprocessor 1/1, model 12/15
## ✓ Slice1: preprocessor 1/1, model 12/15
## i Slice1: preprocessor 1/1, model 12/15 (predictions)
## i Slice1: preprocessor 1/1, model 13/15
## ✓ Slice1: preprocessor 1/1, model 13/15
## i Slice1: preprocessor 1/1, model 13/15 (predictions)
## i Slice1: preprocessor 1/1, model 14/15
## ✓ Slice1: preprocessor 1/1, model 14/15
## i Slice1: preprocessor 1/1, model 14/15 (predictions)
## i Slice1: preprocessor 1/1, model 15/15
## ✓ Slice1: preprocessor 1/1, model 15/15
## i Slice1: preprocessor 1/1, model 15/15 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/15
## ✓ Slice2: preprocessor 1/1, model 1/15
## i Slice2: preprocessor 1/1, model 1/15 (predictions)
## i Slice2: preprocessor 1/1, model 2/15
## ✓ Slice2: preprocessor 1/1, model 2/15
## i Slice2: preprocessor 1/1, model 2/15 (predictions)
## i Slice2: preprocessor 1/1, model 3/15
## ✓ Slice2: preprocessor 1/1, model 3/15
## i Slice2: preprocessor 1/1, model 3/15 (predictions)
## i Slice2: preprocessor 1/1, model 4/15
## ✓ Slice2: preprocessor 1/1, model 4/15
## i Slice2: preprocessor 1/1, model 4/15 (predictions)
## i Slice2: preprocessor 1/1, model 5/15
## ✓ Slice2: preprocessor 1/1, model 5/15
## i Slice2: preprocessor 1/1, model 5/15 (predictions)
## i Slice2: preprocessor 1/1, model 6/15
## ✓ Slice2: preprocessor 1/1, model 6/15
## i Slice2: preprocessor 1/1, model 6/15 (predictions)
## i Slice2: preprocessor 1/1, model 7/15
## ✓ Slice2: preprocessor 1/1, model 7/15
## i Slice2: preprocessor 1/1, model 7/15 (predictions)
## i Slice2: preprocessor 1/1, model 8/15
## ✓ Slice2: preprocessor 1/1, model 8/15
## i Slice2: preprocessor 1/1, model 8/15 (predictions)
## i Slice2: preprocessor 1/1, model 9/15
## ✓ Slice2: preprocessor 1/1, model 9/15
## i Slice2: preprocessor 1/1, model 9/15 (predictions)
## i Slice2: preprocessor 1/1, model 10/15
## ✓ Slice2: preprocessor 1/1, model 10/15
## i Slice2: preprocessor 1/1, model 10/15 (predictions)
## i Slice2: preprocessor 1/1, model 11/15
## ✓ Slice2: preprocessor 1/1, model 11/15
## i Slice2: preprocessor 1/1, model 11/15 (predictions)
## i Slice2: preprocessor 1/1, model 12/15
## ✓ Slice2: preprocessor 1/1, model 12/15
## i Slice2: preprocessor 1/1, model 12/15 (predictions)
## i Slice2: preprocessor 1/1, model 13/15
## ✓ Slice2: preprocessor 1/1, model 13/15
## i Slice2: preprocessor 1/1, model 13/15 (predictions)
## i Slice2: preprocessor 1/1, model 14/15
## ✓ Slice2: preprocessor 1/1, model 14/15
## i Slice2: preprocessor 1/1, model 14/15 (predictions)
## i Slice2: preprocessor 1/1, model 15/15
## ✓ Slice2: preprocessor 1/1, model 15/15
## i Slice2: preprocessor 1/1, model 15/15 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/15
## ✓ Slice3: preprocessor 1/1, model 1/15
## i Slice3: preprocessor 1/1, model 1/15 (predictions)
## i Slice3: preprocessor 1/1, model 2/15
## ✓ Slice3: preprocessor 1/1, model 2/15
## i Slice3: preprocessor 1/1, model 2/15 (predictions)
## i Slice3: preprocessor 1/1, model 3/15
## ✓ Slice3: preprocessor 1/1, model 3/15
## i Slice3: preprocessor 1/1, model 3/15 (predictions)
## i Slice3: preprocessor 1/1, model 4/15
## ✓ Slice3: preprocessor 1/1, model 4/15
## i Slice3: preprocessor 1/1, model 4/15 (predictions)
## i Slice3: preprocessor 1/1, model 5/15
## ✓ Slice3: preprocessor 1/1, model 5/15
## i Slice3: preprocessor 1/1, model 5/15 (predictions)
## i Slice3: preprocessor 1/1, model 6/15
## ✓ Slice3: preprocessor 1/1, model 6/15
## i Slice3: preprocessor 1/1, model 6/15 (predictions)
## i Slice3: preprocessor 1/1, model 7/15
## ✓ Slice3: preprocessor 1/1, model 7/15
## i Slice3: preprocessor 1/1, model 7/15 (predictions)
## i Slice3: preprocessor 1/1, model 8/15
## ✓ Slice3: preprocessor 1/1, model 8/15
## i Slice3: preprocessor 1/1, model 8/15 (predictions)
## i Slice3: preprocessor 1/1, model 9/15
## ✓ Slice3: preprocessor 1/1, model 9/15
## i Slice3: preprocessor 1/1, model 9/15 (predictions)
## i Slice3: preprocessor 1/1, model 10/15
## ✓ Slice3: preprocessor 1/1, model 10/15
## i Slice3: preprocessor 1/1, model 10/15 (predictions)
## i Slice3: preprocessor 1/1, model 11/15
## ✓ Slice3: preprocessor 1/1, model 11/15
## i Slice3: preprocessor 1/1, model 11/15 (predictions)
## i Slice3: preprocessor 1/1, model 12/15
## ✓ Slice3: preprocessor 1/1, model 12/15
## i Slice3: preprocessor 1/1, model 12/15 (predictions)
## i Slice3: preprocessor 1/1, model 13/15
## ✓ Slice3: preprocessor 1/1, model 13/15
## i Slice3: preprocessor 1/1, model 13/15 (predictions)
## i Slice3: preprocessor 1/1, model 14/15
## ✓ Slice3: preprocessor 1/1, model 14/15
## i Slice3: preprocessor 1/1, model 14/15 (predictions)
## i Slice3: preprocessor 1/1, model 15/15
## ✓ Slice3: preprocessor 1/1, model 15/15
## i Slice3: preprocessor 1/1, model 15/15 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/15
## ✓ Slice4: preprocessor 1/1, model 1/15
## i Slice4: preprocessor 1/1, model 1/15 (predictions)
## i Slice4: preprocessor 1/1, model 2/15
## ✓ Slice4: preprocessor 1/1, model 2/15
## i Slice4: preprocessor 1/1, model 2/15 (predictions)
## i Slice4: preprocessor 1/1, model 3/15
## ✓ Slice4: preprocessor 1/1, model 3/15
## i Slice4: preprocessor 1/1, model 3/15 (predictions)
## i Slice4: preprocessor 1/1, model 4/15
## ✓ Slice4: preprocessor 1/1, model 4/15
## i Slice4: preprocessor 1/1, model 4/15 (predictions)
## i Slice4: preprocessor 1/1, model 5/15
## ✓ Slice4: preprocessor 1/1, model 5/15
## i Slice4: preprocessor 1/1, model 5/15 (predictions)
## i Slice4: preprocessor 1/1, model 6/15
## ✓ Slice4: preprocessor 1/1, model 6/15
## i Slice4: preprocessor 1/1, model 6/15 (predictions)
## i Slice4: preprocessor 1/1, model 7/15
## ✓ Slice4: preprocessor 1/1, model 7/15
## i Slice4: preprocessor 1/1, model 7/15 (predictions)
## i Slice4: preprocessor 1/1, model 8/15
## ✓ Slice4: preprocessor 1/1, model 8/15
## i Slice4: preprocessor 1/1, model 8/15 (predictions)
## i Slice4: preprocessor 1/1, model 9/15
## ✓ Slice4: preprocessor 1/1, model 9/15
## i Slice4: preprocessor 1/1, model 9/15 (predictions)
## i Slice4: preprocessor 1/1, model 10/15
## ✓ Slice4: preprocessor 1/1, model 10/15
## i Slice4: preprocessor 1/1, model 10/15 (predictions)
## i Slice4: preprocessor 1/1, model 11/15
## ✓ Slice4: preprocessor 1/1, model 11/15
## i Slice4: preprocessor 1/1, model 11/15 (predictions)
## i Slice4: preprocessor 1/1, model 12/15
## ✓ Slice4: preprocessor 1/1, model 12/15
## i Slice4: preprocessor 1/1, model 12/15 (predictions)
## i Slice4: preprocessor 1/1, model 13/15
## ✓ Slice4: preprocessor 1/1, model 13/15
## i Slice4: preprocessor 1/1, model 13/15 (predictions)
## i Slice4: preprocessor 1/1, model 14/15
## ✓ Slice4: preprocessor 1/1, model 14/15
## i Slice4: preprocessor 1/1, model 14/15 (predictions)
## i Slice4: preprocessor 1/1, model 15/15
## ✓ Slice4: preprocessor 1/1, model 15/15
## i Slice4: preprocessor 1/1, model 15/15 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/15
## ✓ Slice5: preprocessor 1/1, model 1/15
## i Slice5: preprocessor 1/1, model 1/15 (predictions)
## i Slice5: preprocessor 1/1, model 2/15
## ✓ Slice5: preprocessor 1/1, model 2/15
## i Slice5: preprocessor 1/1, model 2/15 (predictions)
## i Slice5: preprocessor 1/1, model 3/15
## ✓ Slice5: preprocessor 1/1, model 3/15
## i Slice5: preprocessor 1/1, model 3/15 (predictions)
## i Slice5: preprocessor 1/1, model 4/15
## ✓ Slice5: preprocessor 1/1, model 4/15
## i Slice5: preprocessor 1/1, model 4/15 (predictions)
## i Slice5: preprocessor 1/1, model 5/15
## ✓ Slice5: preprocessor 1/1, model 5/15
## i Slice5: preprocessor 1/1, model 5/15 (predictions)
## i Slice5: preprocessor 1/1, model 6/15
## ✓ Slice5: preprocessor 1/1, model 6/15
## i Slice5: preprocessor 1/1, model 6/15 (predictions)
## i Slice5: preprocessor 1/1, model 7/15
## ✓ Slice5: preprocessor 1/1, model 7/15
## i Slice5: preprocessor 1/1, model 7/15 (predictions)
## i Slice5: preprocessor 1/1, model 8/15
## ✓ Slice5: preprocessor 1/1, model 8/15
## i Slice5: preprocessor 1/1, model 8/15 (predictions)
## i Slice5: preprocessor 1/1, model 9/15
## ✓ Slice5: preprocessor 1/1, model 9/15
## i Slice5: preprocessor 1/1, model 9/15 (predictions)
## i Slice5: preprocessor 1/1, model 10/15
## ✓ Slice5: preprocessor 1/1, model 10/15
## i Slice5: preprocessor 1/1, model 10/15 (predictions)
## i Slice5: preprocessor 1/1, model 11/15
## ✓ Slice5: preprocessor 1/1, model 11/15
## i Slice5: preprocessor 1/1, model 11/15 (predictions)
## i Slice5: preprocessor 1/1, model 12/15
## ✓ Slice5: preprocessor 1/1, model 12/15
## i Slice5: preprocessor 1/1, model 12/15 (predictions)
## i Slice5: preprocessor 1/1, model 13/15
## ✓ Slice5: preprocessor 1/1, model 13/15
## i Slice5: preprocessor 1/1, model 13/15 (predictions)
## i Slice5: preprocessor 1/1, model 14/15
## ✓ Slice5: preprocessor 1/1, model 14/15
## i Slice5: preprocessor 1/1, model 14/15 (predictions)
## i Slice5: preprocessor 1/1, model 15/15
## ✓ Slice5: preprocessor 1/1, model 15/15
## i Slice5: preprocessor 1/1, model 15/15 (predictions)
toc()
## 92.87 sec elapsed
tune_result_bart %>% 
  show_best(metric = "rmse", n = Inf)
## # A tibble: 15 × 10
##    trees prior_terminal_node_coef prior_terminal_node_expo prior_outcome_range
##    <int>                    <dbl>                    <dbl>               <dbl>
##  1   465                   0.967                      2.60               1.66 
##  2   386                   0.447                      2.84               3.00 
##  3   227                   0.369                      2.16               4.52 
##  4   351                   0.766                      2.67               2.43 
##  5   348                   0.253                      1.99               3.75 
##  6   416                   0.630                      1.57               2.14 
##  7   145                   0.120                      2.94               3.38 
##  8   108                   0.730                      1.80               4.16 
##  9   283                   0.282                      2.46               3.03 
## 10   480                   0.561                      1.22               4.80 
## 11    79                   0.801                      1.49               1.86 
## 12   299                   0.894                      1.37               1.08 
## 13   235                   0.0423                     2.24               0.765
## 14   181                   0.519                      1.12               0.638
## 15   120                   0.173                      1.81               0.195
## # ℹ 6 more variables: .metric <chr>, .estimator <chr>, mean <dbl>, n <int>,
## #   std_err <dbl>, .config <chr>
tune_result_bart %>% write_rds("tune_result_bart")

model_fit_bart_tune %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_bart %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  ) %>% 
  fit(training(splits)) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>%
  # modeltime_forecast(new_data = test_data, actual_data = ihsg_tbl) %>%
  # plot_modeltime_forecast()
  modeltime_refit(data = yield) %>%
  # modeltime_forecast(new_data = ihsg_future_tbl, actual_data = ihsg_tbl) %>%
  modeltime_forecast(h = "1 year", actual_data = yield) %>%
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.
model_fit_bart_best <- model_fit_bart %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_bart %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  )

Combine Models

all_model_fit <- modeltime_table(model_fit_prophet_seasonality, 
model_fit_glmnet, 
model_fit_svm_poly,
model_fit_svm_rbf,
model_fit_knn,
model_fit_spect_rf,
model_fit_boost,
model_fit_cubist,
model_fit_nnetar,
model_fit_prophet_boost,
model_fit_bart)

all_model_fit_calibrate <- all_model_fit %>% 
  modeltime_calibrate(new_data = testing(splits))

all_model_fit_calibrate %>% 
  modeltime_accuracy(new_data = testing(splits))
## # A tibble: 11 × 9
##    .model_id .model_desc             .type   mae  mape  mase smape  rmse     rsq
##        <int> <chr>                   <chr> <dbl> <dbl> <dbl> <dbl> <dbl>   <dbl>
##  1         1 PROPHET                 Test  0.851 12.5   26.9 13.7  1.04  0.141  
##  2         2 GLMNET                  Test  1.20  18.5   38.1 16.7  1.27  0.0337 
##  3         3 KERNLAB                 Test  0.836 12.9   26.4 12.0  0.926 0.0191 
##  4         4 KERNLAB                 Test  0.634  9.31  20.0  9.84 0.783 0.125  
##  5         5 KKNN                    Test  0.716 11.1   22.6 10.4  0.805 0.00177
##  6         6 RANDOMFOREST            Test  0.507  7.73  16.0  7.41 0.587 0.00624
##  7         7 XGBOOST                 Test  0.369  5.62  11.7  5.51 0.419 0.0147 
##  8         8 CUBIST                  Test  0.357  5.35  11.3  5.34 0.419 0.0278 
##  9         9 NNAR(2,1,10)[5]         Test  1.38  21.1   43.8 18.8  1.48  0.105  
## 10        10 PROPHET W/ XGBOOST ERR… Test  0.788 11.6   24.9 12.4  0.978 0.109  
## 11        11 DBARTS                  Test  0.578  8.86  18.3  8.39 0.686 0.00408
all_model_fit_refit <- all_model_fit_calibrate %>% 
  modeltime_refit(data = yield) 
## frequency = 5 observations per 1 week
## Warning: There were 2 warnings in `dplyr::mutate()`.
## The first warning was:
## ℹ In argument: `.model = purrr::map2(...)`.
## Caused by warning:
## ! 25 columns were requested but there were 17 predictors in the data. 17 will be used.
## ℹ Run ]8;;ide:run:dplyr::last_dplyr_warnings()dplyr::last_dplyr_warnings()]8;; to see the 1 remaining warning.
all_model_fit_refit %>% write_rds("all_model_fit_refit")

all_model_fit_refit %>% 
  modeltime_forecast(h = "1 year", actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
all_model_fit_calibrate %>% 
  modeltime_residuals() %>% 
  plot_modeltime_residuals()

Combine Tune Models

all_model_fit_tune <- modeltime_table(model_fit_bart_best, 
                model_fit_cubist_tune, 
                # model_fit_prophet_boost_tune, 
                model_fit_spect_rf_tune, 
                model_fit_xgboost_best)

all_model_fit_tune_calibrate <- all_model_fit_tune %>% 
  modeltime_calibrate(new_data = testing(splits))

all_model_fit_tune_calibrate %>% 
  modeltime_accuracy(new_data = testing(splits))
## # A tibble: 4 × 9
##   .model_id .model_desc  .type   mae  mape  mase smape  rmse     rsq
##       <int> <chr>        <chr> <dbl> <dbl> <dbl> <dbl> <dbl>   <dbl>
## 1         1 DBARTS       Test  0.579  8.87  18.3  8.40 0.686 0.00397
## 2         2 CUBIST       Test  0.357  5.35  11.3  5.34 0.419 0.0278 
## 3         3 RANDOMFOREST Test  0.507  7.73  16.0  7.41 0.587 0.00624
## 4         4 XGBOOST      Test  0.369  5.62  11.7  5.51 0.419 0.0147
all_model_fit_tune_refit <- all_model_fit_tune_calibrate %>% 
  modeltime_refit(data = yield) 
## Warning: There were 2 warnings in `dplyr::mutate()`.
## The first warning was:
## ℹ In argument: `.model = purrr::map2(...)`.
## Caused by warning:
## ! The number of neighbors should be >= 0 and <= 9. Truncating the value.
## ℹ Run ]8;;ide:run:dplyr::last_dplyr_warnings()dplyr::last_dplyr_warnings()]8;; to see the 1 remaining warning.
all_model_fit_tune_refit %>% write_rds("all_model_fit_tune_refit")

all_model_fit_tune_refit %>% 
  modeltime_forecast(h = "1 year", actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
all_model_fit_tune_calibrate %>% 
  modeltime_residuals() %>% 
  plot_modeltime_residuals()

Resampling

Resample

all_model_fit_resample <- all_model_fit %>% 
  modeltime_fit_resamples(resamples = resamples_tscv_no_acum, 
                          control = control_resamples(verbose = FALSE))

all_model_fit_resample %>% 
  modeltime_resample_accuracy(summary_fns = mean) %>% 
  table_modeltime_accuracy(.interactive = FALSE)
## Warning: There was 1 warning in `dplyr::summarise()`.
## ℹ In argument: `dplyr::across(.fns = summary_fns, ...)`.
## Caused by warning:
## ! Using `across()` without supplying `.cols` was deprecated in dplyr 1.1.0.
## ℹ Please supply `.cols` instead.
Accuracy Table
.model_id .model_desc .type n mae mape mase smape rmse rsq
1 PROPHET Resamples 5 0.69 9.24 14.50 9.65 0.77 0.26
2 GLMNET Resamples 5 0.29 4.05 7.04 4.00 0.33 0.17
3 KERNLAB Resamples 5 0.25 3.49 6.17 3.49 0.30 0.23
4 KERNLAB Resamples 5 0.34 4.71 7.77 4.70 0.38 0.15
5 KKNN Resamples 5 0.56 7.68 13.05 7.63 0.59 0.11
6 RANDOMFOREST Resamples 5 0.36 5.01 8.54 4.89 0.44 0.07
7 XGBOOST Resamples 5 0.32 4.34 7.25 4.35 0.37 0.14
8 CUBIST Resamples 5 0.32 4.37 7.49 4.55 0.38 0.24
9 NNAR(2,1,10)[5] Resamples 5 0.43 5.93 9.00 5.87 0.47 0.24
10 PROPHET W/ XGBOOST ERRORS Resamples 5 0.29 4.06 8.02 4.20 0.35 0.33
11 DBARTS Resamples 5 0.36 5.03 7.96 4.97 0.43 0.05
# model_id with smallest RMSE : 3, 2, 10, 7 dan 4

all_model_fit_resample %>% 
  plot_modeltime_resamples()

Visual each model w/ best RMSE

# model_id with smallest RMSE : 3, 2, 10, 7 dan 4

all_model_fit_resample %>% 
  pull_modeltime_model(3) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_refit(data = yield) %>% 
  modeltime_forecast(h = "1 year", actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.
all_model_fit_resample %>% 
  pull_modeltime_model(2) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_refit(data = yield) %>% 
  modeltime_forecast(h = "1 year", actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.
all_model_fit_resample %>% 
  pull_modeltime_model(10) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_refit(data = yield) %>% 
  modeltime_forecast(h = "1 year", actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.
# XGBoost
all_model_fit_resample %>% 
  pull_modeltime_model(7) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_refit(data = yield) %>% 
  modeltime_forecast(h = "1 year", actual_data = yield) %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

Hyperparameter Tuning

XGBoost

wflw_fit_xgboost <- all_model_fit_resample %>% 
  pull_modeltime_model(7)

wflw_fit_xgboost
## ══ Workflow [trained] ══════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: boost_tree()
## 
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 4 Recipe Steps
## 
## • step_timeseries_signature()
## • step_rm()
## • step_rm()
## • step_mutate()
## 
## ── Model ───────────────────────────────────────────────────────────────────────
## ##### xgb.Booster
## raw: 1.6 Mb 
## call:
##   xgboost::xgb.train(params = list(eta = 0.3, max_depth = 12, gamma = 0, 
##     colsample_bytree = 1, colsample_bynode = 1, min_child_weight = 2, 
##     subsample = 1), data = x$data, nrounds = 1000, watchlist = x$watchlist, 
##     verbose = 0, nthread = 1, objective = "reg:squarederror")
## params (as set within xgb.train):
##   eta = "0.3", max_depth = "12", gamma = "0", colsample_bytree = "1", colsample_bynode = "1", min_child_weight = "2", subsample = "1", nthread = "1", objective = "reg:squarederror", validate_parameters = "TRUE"
## xgb.attributes:
##   niter
## callbacks:
##   cb.evaluation.log()
## # of features: 17 
## niter: 1000
## nfeatures : 17 
## evaluation_log:
##     iter training_rmse
##        1   4.827094942
##        2   3.394336196
## ---                   
##      999   0.002649495
##     1000   0.002649495
model_spec_xgboost_tune <- boost_tree(
  # mtry = tune(), 
  trees = tune(), 
  min_n = tune(), 
  tree_depth = tune(),
  learn_rate = tune(),
  loss_reduction = tune(),
  sample_size = tune(),
  stop_iter = tune()
) %>%
 set_engine("xgboost") %>%
 set_mode("regression")

grid_spec_xgboost <- grid_latin_hypercube(
  # extract_parameter_dials(model_spec_prophet_boost_tune),
  parameters(model_spec_xgboost_tune),
  size = 15
)

wflw_tune_xgboost <- wflw_fit_xgboost %>% 
  update_model(model_spec_xgboost_tune)

tic()
tune_result_xgboost <- wflw_tune_xgboost %>%
  tune_grid(
    resamples = resamples_tscv_no_acum,
    grid      = grid_spec_xgboost,
    metrics   = default_forecast_accuracy_metric_set(),
    control   = control_grid(verbose = TRUE, save_pred = TRUE)
  )
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/15
## ✓ Slice1: preprocessor 1/1, model 1/15
## i Slice1: preprocessor 1/1, model 1/15 (predictions)
## i Slice1: preprocessor 1/1, model 2/15
## ✓ Slice1: preprocessor 1/1, model 2/15
## i Slice1: preprocessor 1/1, model 2/15 (predictions)
## i Slice1: preprocessor 1/1, model 3/15
## ✓ Slice1: preprocessor 1/1, model 3/15
## i Slice1: preprocessor 1/1, model 3/15 (predictions)
## i Slice1: preprocessor 1/1, model 4/15
## ✓ Slice1: preprocessor 1/1, model 4/15
## i Slice1: preprocessor 1/1, model 4/15 (predictions)
## i Slice1: preprocessor 1/1, model 5/15
## ✓ Slice1: preprocessor 1/1, model 5/15
## i Slice1: preprocessor 1/1, model 5/15 (predictions)
## i Slice1: preprocessor 1/1, model 6/15
## ✓ Slice1: preprocessor 1/1, model 6/15
## i Slice1: preprocessor 1/1, model 6/15 (predictions)
## i Slice1: preprocessor 1/1, model 7/15
## ✓ Slice1: preprocessor 1/1, model 7/15
## i Slice1: preprocessor 1/1, model 7/15 (predictions)
## i Slice1: preprocessor 1/1, model 8/15
## ✓ Slice1: preprocessor 1/1, model 8/15
## i Slice1: preprocessor 1/1, model 8/15 (predictions)
## i Slice1: preprocessor 1/1, model 9/15
## ✓ Slice1: preprocessor 1/1, model 9/15
## i Slice1: preprocessor 1/1, model 9/15 (predictions)
## i Slice1: preprocessor 1/1, model 10/15
## ✓ Slice1: preprocessor 1/1, model 10/15
## i Slice1: preprocessor 1/1, model 10/15 (predictions)
## i Slice1: preprocessor 1/1, model 11/15
## ✓ Slice1: preprocessor 1/1, model 11/15
## i Slice1: preprocessor 1/1, model 11/15 (predictions)
## i Slice1: preprocessor 1/1, model 12/15
## ✓ Slice1: preprocessor 1/1, model 12/15
## i Slice1: preprocessor 1/1, model 12/15 (predictions)
## i Slice1: preprocessor 1/1, model 13/15
## ✓ Slice1: preprocessor 1/1, model 13/15
## i Slice1: preprocessor 1/1, model 13/15 (predictions)
## i Slice1: preprocessor 1/1, model 14/15
## ✓ Slice1: preprocessor 1/1, model 14/15
## i Slice1: preprocessor 1/1, model 14/15 (predictions)
## i Slice1: preprocessor 1/1, model 15/15
## ✓ Slice1: preprocessor 1/1, model 15/15
## i Slice1: preprocessor 1/1, model 15/15 (predictions)
## ! Slice1: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 192`, `min_n = 15`, `tree_depth = 4`, `learn_ra...
##     0.01319149`, `loss_reduction = 11.78566`, `sample_size = 0.8779609`,
##     `stop_iter = 14`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 845`, `min_n = 19`, `tree_depth = 13`, `learn_r...
##     0.001414412`, `loss_reduction = 0.002559648`, `sample_size = 0.65600...
##     `stop_iter = 18`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 699`, `min_n = 25`, `tree_depth = 6`, `learn_ra...
##     0.003217589`, `loss_reduction = 0.0000004164966`, `sample_size = 0.9...
##     `stop_iter = 16`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 414`, `min_n = 28`, `tree_depth = 12`, `learn_r...
##     0.001655483`, `loss_reduction = 4.36582`, `sample_size = 0.1117492`,
##     `stop_iter = 19`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 605`, `min_n = 34`, `tree_depth = 9`, `learn_ra...
##     0.002951011`, `loss_reduction = 0.00002736923`, `sample_size = 0.547...
##     `stop_iter = 3`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 88`, `min_n = 40`, `tree_depth = 12`, `learn_ra...
##     0.009637999`, `loss_reduction = 0.7692781`, `sample_size = 0.3752403`,
##     `stop_iter = 17`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice1: internal
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/15
## ✓ Slice2: preprocessor 1/1, model 1/15
## i Slice2: preprocessor 1/1, model 1/15 (predictions)
## i Slice2: preprocessor 1/1, model 2/15
## ✓ Slice2: preprocessor 1/1, model 2/15
## i Slice2: preprocessor 1/1, model 2/15 (predictions)
## i Slice2: preprocessor 1/1, model 3/15
## ✓ Slice2: preprocessor 1/1, model 3/15
## i Slice2: preprocessor 1/1, model 3/15 (predictions)
## i Slice2: preprocessor 1/1, model 4/15
## ✓ Slice2: preprocessor 1/1, model 4/15
## i Slice2: preprocessor 1/1, model 4/15 (predictions)
## i Slice2: preprocessor 1/1, model 5/15
## ✓ Slice2: preprocessor 1/1, model 5/15
## i Slice2: preprocessor 1/1, model 5/15 (predictions)
## i Slice2: preprocessor 1/1, model 6/15
## ✓ Slice2: preprocessor 1/1, model 6/15
## i Slice2: preprocessor 1/1, model 6/15 (predictions)
## i Slice2: preprocessor 1/1, model 7/15
## ✓ Slice2: preprocessor 1/1, model 7/15
## i Slice2: preprocessor 1/1, model 7/15 (predictions)
## i Slice2: preprocessor 1/1, model 8/15
## ✓ Slice2: preprocessor 1/1, model 8/15
## i Slice2: preprocessor 1/1, model 8/15 (predictions)
## i Slice2: preprocessor 1/1, model 9/15
## ✓ Slice2: preprocessor 1/1, model 9/15
## i Slice2: preprocessor 1/1, model 9/15 (predictions)
## i Slice2: preprocessor 1/1, model 10/15
## ✓ Slice2: preprocessor 1/1, model 10/15
## i Slice2: preprocessor 1/1, model 10/15 (predictions)
## i Slice2: preprocessor 1/1, model 11/15
## ✓ Slice2: preprocessor 1/1, model 11/15
## i Slice2: preprocessor 1/1, model 11/15 (predictions)
## i Slice2: preprocessor 1/1, model 12/15
## ✓ Slice2: preprocessor 1/1, model 12/15
## i Slice2: preprocessor 1/1, model 12/15 (predictions)
## i Slice2: preprocessor 1/1, model 13/15
## ✓ Slice2: preprocessor 1/1, model 13/15
## i Slice2: preprocessor 1/1, model 13/15 (predictions)
## i Slice2: preprocessor 1/1, model 14/15
## ✓ Slice2: preprocessor 1/1, model 14/15
## i Slice2: preprocessor 1/1, model 14/15 (predictions)
## i Slice2: preprocessor 1/1, model 15/15
## ✓ Slice2: preprocessor 1/1, model 15/15
## i Slice2: preprocessor 1/1, model 15/15 (predictions)
## ! Slice2: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 192`, `min_n = 15`, `tree_depth = 4`, `learn_ra...
##     0.01319149`, `loss_reduction = 11.78566`, `sample_size = 0.8779609`,
##     `stop_iter = 14`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 414`, `min_n = 28`, `tree_depth = 12`, `learn_r...
##     0.001655483`, `loss_reduction = 4.36582`, `sample_size = 0.1117492`,
##     `stop_iter = 19`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 88`, `min_n = 40`, `tree_depth = 12`, `learn_ra...
##     0.009637999`, `loss_reduction = 0.7692781`, `sample_size = 0.3752403`,
##     `stop_iter = 17`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice2: internal
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/15
## ✓ Slice3: preprocessor 1/1, model 1/15
## i Slice3: preprocessor 1/1, model 1/15 (predictions)
## i Slice3: preprocessor 1/1, model 2/15
## ✓ Slice3: preprocessor 1/1, model 2/15
## i Slice3: preprocessor 1/1, model 2/15 (predictions)
## i Slice3: preprocessor 1/1, model 3/15
## ✓ Slice3: preprocessor 1/1, model 3/15
## i Slice3: preprocessor 1/1, model 3/15 (predictions)
## i Slice3: preprocessor 1/1, model 4/15
## ✓ Slice3: preprocessor 1/1, model 4/15
## i Slice3: preprocessor 1/1, model 4/15 (predictions)
## i Slice3: preprocessor 1/1, model 5/15
## ✓ Slice3: preprocessor 1/1, model 5/15
## i Slice3: preprocessor 1/1, model 5/15 (predictions)
## i Slice3: preprocessor 1/1, model 6/15
## ✓ Slice3: preprocessor 1/1, model 6/15
## i Slice3: preprocessor 1/1, model 6/15 (predictions)
## i Slice3: preprocessor 1/1, model 7/15
## ✓ Slice3: preprocessor 1/1, model 7/15
## i Slice3: preprocessor 1/1, model 7/15 (predictions)
## i Slice3: preprocessor 1/1, model 8/15
## ✓ Slice3: preprocessor 1/1, model 8/15
## i Slice3: preprocessor 1/1, model 8/15 (predictions)
## i Slice3: preprocessor 1/1, model 9/15
## ✓ Slice3: preprocessor 1/1, model 9/15
## i Slice3: preprocessor 1/1, model 9/15 (predictions)
## i Slice3: preprocessor 1/1, model 10/15
## ✓ Slice3: preprocessor 1/1, model 10/15
## i Slice3: preprocessor 1/1, model 10/15 (predictions)
## i Slice3: preprocessor 1/1, model 11/15
## ✓ Slice3: preprocessor 1/1, model 11/15
## i Slice3: preprocessor 1/1, model 11/15 (predictions)
## i Slice3: preprocessor 1/1, model 12/15
## ✓ Slice3: preprocessor 1/1, model 12/15
## i Slice3: preprocessor 1/1, model 12/15 (predictions)
## i Slice3: preprocessor 1/1, model 13/15
## ✓ Slice3: preprocessor 1/1, model 13/15
## i Slice3: preprocessor 1/1, model 13/15 (predictions)
## i Slice3: preprocessor 1/1, model 14/15
## ✓ Slice3: preprocessor 1/1, model 14/15
## i Slice3: preprocessor 1/1, model 14/15 (predictions)
## i Slice3: preprocessor 1/1, model 15/15
## ✓ Slice3: preprocessor 1/1, model 15/15
## i Slice3: preprocessor 1/1, model 15/15 (predictions)
## ! Slice3: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 192`, `min_n = 15`, `tree_depth = 4`, `learn_ra...
##     0.01319149`, `loss_reduction = 11.78566`, `sample_size = 0.8779609`,
##     `stop_iter = 14`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 414`, `min_n = 28`, `tree_depth = 12`, `learn_r...
##     0.001655483`, `loss_reduction = 4.36582`, `sample_size = 0.1117492`,
##     `stop_iter = 19`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 88`, `min_n = 40`, `tree_depth = 12`, `learn_ra...
##     0.009637999`, `loss_reduction = 0.7692781`, `sample_size = 0.3752403`,
##     `stop_iter = 17`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice3: internal
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/15
## ✓ Slice4: preprocessor 1/1, model 1/15
## i Slice4: preprocessor 1/1, model 1/15 (predictions)
## i Slice4: preprocessor 1/1, model 2/15
## ✓ Slice4: preprocessor 1/1, model 2/15
## i Slice4: preprocessor 1/1, model 2/15 (predictions)
## i Slice4: preprocessor 1/1, model 3/15
## ✓ Slice4: preprocessor 1/1, model 3/15
## i Slice4: preprocessor 1/1, model 3/15 (predictions)
## i Slice4: preprocessor 1/1, model 4/15
## ✓ Slice4: preprocessor 1/1, model 4/15
## i Slice4: preprocessor 1/1, model 4/15 (predictions)
## i Slice4: preprocessor 1/1, model 5/15
## ✓ Slice4: preprocessor 1/1, model 5/15
## i Slice4: preprocessor 1/1, model 5/15 (predictions)
## i Slice4: preprocessor 1/1, model 6/15
## ✓ Slice4: preprocessor 1/1, model 6/15
## i Slice4: preprocessor 1/1, model 6/15 (predictions)
## i Slice4: preprocessor 1/1, model 7/15
## ✓ Slice4: preprocessor 1/1, model 7/15
## i Slice4: preprocessor 1/1, model 7/15 (predictions)
## i Slice4: preprocessor 1/1, model 8/15
## ✓ Slice4: preprocessor 1/1, model 8/15
## i Slice4: preprocessor 1/1, model 8/15 (predictions)
## i Slice4: preprocessor 1/1, model 9/15
## ✓ Slice4: preprocessor 1/1, model 9/15
## i Slice4: preprocessor 1/1, model 9/15 (predictions)
## i Slice4: preprocessor 1/1, model 10/15
## ✓ Slice4: preprocessor 1/1, model 10/15
## i Slice4: preprocessor 1/1, model 10/15 (predictions)
## i Slice4: preprocessor 1/1, model 11/15
## ✓ Slice4: preprocessor 1/1, model 11/15
## i Slice4: preprocessor 1/1, model 11/15 (predictions)
## i Slice4: preprocessor 1/1, model 12/15
## ✓ Slice4: preprocessor 1/1, model 12/15
## i Slice4: preprocessor 1/1, model 12/15 (predictions)
## i Slice4: preprocessor 1/1, model 13/15
## ✓ Slice4: preprocessor 1/1, model 13/15
## i Slice4: preprocessor 1/1, model 13/15 (predictions)
## i Slice4: preprocessor 1/1, model 14/15
## ✓ Slice4: preprocessor 1/1, model 14/15
## i Slice4: preprocessor 1/1, model 14/15 (predictions)
## i Slice4: preprocessor 1/1, model 15/15
## ✓ Slice4: preprocessor 1/1, model 15/15
## i Slice4: preprocessor 1/1, model 15/15 (predictions)
## ! Slice4: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 192`, `min_n = 15`, `tree_depth = 4`, `learn_ra...
##     0.01319149`, `loss_reduction = 11.78566`, `sample_size = 0.8779609`,
##     `stop_iter = 14`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 845`, `min_n = 19`, `tree_depth = 13`, `learn_r...
##     0.001414412`, `loss_reduction = 0.002559648`, `sample_size = 0.65600...
##     `stop_iter = 18`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 699`, `min_n = 25`, `tree_depth = 6`, `learn_ra...
##     0.003217589`, `loss_reduction = 0.0000004164966`, `sample_size = 0.9...
##     `stop_iter = 16`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 414`, `min_n = 28`, `tree_depth = 12`, `learn_r...
##     0.001655483`, `loss_reduction = 4.36582`, `sample_size = 0.1117492`,
##     `stop_iter = 19`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 88`, `min_n = 40`, `tree_depth = 12`, `learn_ra...
##     0.009637999`, `loss_reduction = 0.7692781`, `sample_size = 0.3752403`,
##     `stop_iter = 17`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice4: internal
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/15
## ✓ Slice5: preprocessor 1/1, model 1/15
## i Slice5: preprocessor 1/1, model 1/15 (predictions)
## i Slice5: preprocessor 1/1, model 2/15
## ✓ Slice5: preprocessor 1/1, model 2/15
## i Slice5: preprocessor 1/1, model 2/15 (predictions)
## i Slice5: preprocessor 1/1, model 3/15
## ✓ Slice5: preprocessor 1/1, model 3/15
## i Slice5: preprocessor 1/1, model 3/15 (predictions)
## i Slice5: preprocessor 1/1, model 4/15
## ✓ Slice5: preprocessor 1/1, model 4/15
## i Slice5: preprocessor 1/1, model 4/15 (predictions)
## i Slice5: preprocessor 1/1, model 5/15
## ✓ Slice5: preprocessor 1/1, model 5/15
## i Slice5: preprocessor 1/1, model 5/15 (predictions)
## i Slice5: preprocessor 1/1, model 6/15
## ✓ Slice5: preprocessor 1/1, model 6/15
## i Slice5: preprocessor 1/1, model 6/15 (predictions)
## i Slice5: preprocessor 1/1, model 7/15
## ✓ Slice5: preprocessor 1/1, model 7/15
## i Slice5: preprocessor 1/1, model 7/15 (predictions)
## i Slice5: preprocessor 1/1, model 8/15
## ✓ Slice5: preprocessor 1/1, model 8/15
## i Slice5: preprocessor 1/1, model 8/15 (predictions)
## i Slice5: preprocessor 1/1, model 9/15
## ✓ Slice5: preprocessor 1/1, model 9/15
## i Slice5: preprocessor 1/1, model 9/15 (predictions)
## i Slice5: preprocessor 1/1, model 10/15
## ✓ Slice5: preprocessor 1/1, model 10/15
## i Slice5: preprocessor 1/1, model 10/15 (predictions)
## i Slice5: preprocessor 1/1, model 11/15
## ✓ Slice5: preprocessor 1/1, model 11/15
## i Slice5: preprocessor 1/1, model 11/15 (predictions)
## i Slice5: preprocessor 1/1, model 12/15
## ✓ Slice5: preprocessor 1/1, model 12/15
## i Slice5: preprocessor 1/1, model 12/15 (predictions)
## i Slice5: preprocessor 1/1, model 13/15
## ✓ Slice5: preprocessor 1/1, model 13/15
## i Slice5: preprocessor 1/1, model 13/15 (predictions)
## i Slice5: preprocessor 1/1, model 14/15
## ✓ Slice5: preprocessor 1/1, model 14/15
## i Slice5: preprocessor 1/1, model 14/15 (predictions)
## i Slice5: preprocessor 1/1, model 15/15
## ✓ Slice5: preprocessor 1/1, model 15/15
## i Slice5: preprocessor 1/1, model 15/15 (predictions)
## ! Slice5: internal:
##   There was 1 warning in `dplyr::summarise()`.
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 192`, `min_n = 15`, `tree_depth = 4`, `learn_ra...
##     0.01319149`, `loss_reduction = 11.78566`, `sample_size = 0.8779609`,
##     `stop_iter = 14`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 845`, `min_n = 19`, `tree_depth = 13`, `learn_r...
##     0.001414412`, `loss_reduction = 0.002559648`, `sample_size = 0.65600...
##     `stop_iter = 18`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 414`, `min_n = 28`, `tree_depth = 12`, `learn_r...
##     0.001655483`, `loss_reduction = 4.36582`, `sample_size = 0.1117492`,
##     `stop_iter = 19`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
##   ℹ In argument: `.estimate = metric_fn(truth = close, estimate = .pred,...
##     na_rm)`.
##   ℹ In group 1: `trees = 88`, `min_n = 40`, `tree_depth = 12`, `learn_ra...
##     0.009637999`, `loss_reduction = 0.7692781`, `sample_size = 0.3752403`,
##     `stop_iter = 17`.
##   Caused by warning:
##   ! A correlation computation is required, but `estimate` is constant an...
## ✓ Slice5: internal
toc()
## 48.91 sec elapsed
tune_result_xgboost %>% write_rds("tune_result_xgboost")
tune_result_xgboost <- read_rds("tune_result_xgboost")

tune_result_xgboost %>% 
  show_best(metric = "rmse", n = Inf)
## # A tibble: 15 × 13
##    trees min_n tree_depth learn_rate loss_reduction sample_size stop_iter
##    <int> <int>      <int>      <dbl>          <dbl>       <dbl>     <int>
##  1  1383     6          1    0.242         4.60e- 6       0.485        12
##  2  1492     3          5    0.0579        4.74e- 2       0.964        11
##  3   304    11          3    0.140         1.64e- 2       0.598        15
##  4  1008    24          8    0.0342        4.80e-10       0.811         9
##  5  1855     7         11    0.0990        6.95e- 9       0.160         8
##  6  1137    31          3    0.0182        7.14e- 8       0.757         5
##  7   192    15          4    0.0132        1.18e+ 1       0.878        14
##  8  1875    20         15    0.160         3.65e- 4       0.436        12
##  9  1656    13          7    0.00555       7.30e-10       0.237         7
## 10   699    25          6    0.00322       4.16e- 7       0.933        16
## 11  1296    37         10    0.0298        8.71e- 7       0.285         5
## 12   605    34          9    0.00295       2.74e- 5       0.548         3
## 13   845    19         13    0.00141       2.56e- 3       0.656        18
## 14    88    40         12    0.00964       7.69e- 1       0.375        17
## 15   414    28         12    0.00166       4.37e+ 0       0.112        19
## # ℹ 6 more variables: .metric <chr>, .estimator <chr>, mean <dbl>, n <int>,
## #   std_err <dbl>, .config <chr>
wflw_fit_xgboost %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_xgboost %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  ) %>% 
  fit(training(splits)) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>%
  # modeltime_forecast(new_data = test_data, actual_data = ihsg_tbl) %>%
  # plot_modeltime_forecast()
  modeltime_refit(data = yield) %>%
  # modeltime_forecast(new_data = ihsg_future_tbl, actual_data = ihsg_tbl) %>%
  modeltime_forecast(h = "1 year", actual_data = yield) %>%
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.
wflw_fit_xgboost_best <- wflw_fit_xgboost %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_xgboost %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  )

wflw_fit_xgboost_best %>% write_rds("wflw_fit_xgboost_best")

Prophet w/ Boost (Done)

wflw_fit_prophet_boost <-  all_model_fit_resample %>% 
  pull_modeltime_model(10)

model_spec_prophet_boost_tune <- prophet_boost(
                                       growth = tune(),
                                       changepoint_num = tune(), 
                                       changepoint_range = tune(), 
                                       season = tune(), 
                                       seasonality_yearly = T, 
                                       seasonality_weekly = T, 
                                       seasonality_daily = T, 
                                       prior_scale_changepoints = tune(), 
                                       prior_scale_seasonality = tune(), 
                                       trees = tune(), 
                                       min_n = tune(), 
                                       tree_depth = tune(), 
                                       learn_rate = tune(), 
                                       loss_reduction = tune(), 
                                       # sample_size = tune(), 
                                       stop_iter = tune()
) %>%
set_engine("prophet_xgboost")


grid_spec_prophet_boost <- grid_latin_hypercube(
  # extract_parameter_dials(model_spec_prophet_boost_tune),
  parameters(model_spec_prophet_boost_tune),
  size = 15
)
## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `object = purrr::map(call_info, eval_call_info)`.
## Caused by warning:
## ! The `default` argument of `new_qual_param()` is deprecated as of dials 1.0.1.
## ℹ The deprecated feature was likely used in the modeltime package.
##   Please report the issue at
##   <]8;;https://github.com/business-science/modeltime/issueshttps://github.com/business-science/modeltime/issues]8;;>.
wflw_tune_prophet_boost <- wflw_fit_prophet_boost %>% 
  update_model(model_spec_prophet_boost_tune)

tic()
tune_result_prophet_boost <- wflw_tune_prophet_boost %>%
  tune_grid(
    resamples = resamples_tscv_no_acum,
    grid      = grid_spec_prophet_boost,
    metrics   = default_forecast_accuracy_metric_set(),
    control   = control_grid(verbose = TRUE, save_pred = TRUE)
  )
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/15
## x Slice1: preprocessor 1/1, model 1/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice1: preprocessor 1/1, model 2/15
## ✓ Slice1: preprocessor 1/1, model 2/15
## i Slice1: preprocessor 1/1, model 2/15 (predictions)
## i Slice1: preprocessor 1/1, model 3/15
## x Slice1: preprocessor 1/1, model 3/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice1: preprocessor 1/1, model 4/15
## ✓ Slice1: preprocessor 1/1, model 4/15
## i Slice1: preprocessor 1/1, model 4/15 (predictions)
## i Slice1: preprocessor 1/1, model 5/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice1: preprocessor 1/1, model 5/15
## i Slice1: preprocessor 1/1, model 5/15 (predictions)
## i Slice1: preprocessor 1/1, model 6/15
## x Slice1: preprocessor 1/1, model 6/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice1: preprocessor 1/1, model 7/15
## x Slice1: preprocessor 1/1, model 7/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice1: preprocessor 1/1, model 8/15
## x Slice1: preprocessor 1/1, model 8/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice1: preprocessor 1/1, model 9/15
## ✓ Slice1: preprocessor 1/1, model 9/15
## i Slice1: preprocessor 1/1, model 9/15 (predictions)
## i Slice1: preprocessor 1/1, model 10/15
## x Slice1: preprocessor 1/1, model 10/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice1: preprocessor 1/1, model 11/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice1: preprocessor 1/1, model 11/15
## i Slice1: preprocessor 1/1, model 11/15 (predictions)
## i Slice1: preprocessor 1/1, model 12/15
## ✓ Slice1: preprocessor 1/1, model 12/15
## i Slice1: preprocessor 1/1, model 12/15 (predictions)
## i Slice1: preprocessor 1/1, model 13/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## x Slice1: preprocessor 1/1, model 13/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice1: preprocessor 1/1, model 14/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice1: preprocessor 1/1, model 14/15
## i Slice1: preprocessor 1/1, model 14/15 (predictions)
## i Slice1: preprocessor 1/1, model 15/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice1: preprocessor 1/1, model 15/15
## i Slice1: preprocessor 1/1, model 15/15 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/15
## x Slice2: preprocessor 1/1, model 1/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice2: preprocessor 1/1, model 2/15
## ✓ Slice2: preprocessor 1/1, model 2/15
## i Slice2: preprocessor 1/1, model 2/15 (predictions)
## i Slice2: preprocessor 1/1, model 3/15
## x Slice2: preprocessor 1/1, model 3/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice2: preprocessor 1/1, model 4/15
## ✓ Slice2: preprocessor 1/1, model 4/15
## i Slice2: preprocessor 1/1, model 4/15 (predictions)
## i Slice2: preprocessor 1/1, model 5/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice2: preprocessor 1/1, model 5/15
## i Slice2: preprocessor 1/1, model 5/15 (predictions)
## i Slice2: preprocessor 1/1, model 6/15
## x Slice2: preprocessor 1/1, model 6/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice2: preprocessor 1/1, model 7/15
## x Slice2: preprocessor 1/1, model 7/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice2: preprocessor 1/1, model 8/15
## x Slice2: preprocessor 1/1, model 8/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice2: preprocessor 1/1, model 9/15
## ✓ Slice2: preprocessor 1/1, model 9/15
## i Slice2: preprocessor 1/1, model 9/15 (predictions)
## i Slice2: preprocessor 1/1, model 10/15
## x Slice2: preprocessor 1/1, model 10/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice2: preprocessor 1/1, model 11/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice2: preprocessor 1/1, model 11/15
## i Slice2: preprocessor 1/1, model 11/15 (predictions)
## i Slice2: preprocessor 1/1, model 12/15
## ✓ Slice2: preprocessor 1/1, model 12/15
## i Slice2: preprocessor 1/1, model 12/15 (predictions)
## i Slice2: preprocessor 1/1, model 13/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## x Slice2: preprocessor 1/1, model 13/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice2: preprocessor 1/1, model 14/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice2: preprocessor 1/1, model 14/15
## i Slice2: preprocessor 1/1, model 14/15 (predictions)
## i Slice2: preprocessor 1/1, model 15/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice2: preprocessor 1/1, model 15/15
## i Slice2: preprocessor 1/1, model 15/15 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/15
## x Slice3: preprocessor 1/1, model 1/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice3: preprocessor 1/1, model 2/15
## ✓ Slice3: preprocessor 1/1, model 2/15
## i Slice3: preprocessor 1/1, model 2/15 (predictions)
## i Slice3: preprocessor 1/1, model 3/15
## x Slice3: preprocessor 1/1, model 3/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice3: preprocessor 1/1, model 4/15
## ✓ Slice3: preprocessor 1/1, model 4/15
## i Slice3: preprocessor 1/1, model 4/15 (predictions)
## i Slice3: preprocessor 1/1, model 5/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice3: preprocessor 1/1, model 5/15
## i Slice3: preprocessor 1/1, model 5/15 (predictions)
## i Slice3: preprocessor 1/1, model 6/15
## x Slice3: preprocessor 1/1, model 6/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice3: preprocessor 1/1, model 7/15
## x Slice3: preprocessor 1/1, model 7/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice3: preprocessor 1/1, model 8/15
## x Slice3: preprocessor 1/1, model 8/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice3: preprocessor 1/1, model 9/15
## ✓ Slice3: preprocessor 1/1, model 9/15
## i Slice3: preprocessor 1/1, model 9/15 (predictions)
## i Slice3: preprocessor 1/1, model 10/15
## x Slice3: preprocessor 1/1, model 10/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice3: preprocessor 1/1, model 11/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice3: preprocessor 1/1, model 11/15
## i Slice3: preprocessor 1/1, model 11/15 (predictions)
## i Slice3: preprocessor 1/1, model 12/15
## ✓ Slice3: preprocessor 1/1, model 12/15
## i Slice3: preprocessor 1/1, model 12/15 (predictions)
## i Slice3: preprocessor 1/1, model 13/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## x Slice3: preprocessor 1/1, model 13/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice3: preprocessor 1/1, model 14/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice3: preprocessor 1/1, model 14/15
## i Slice3: preprocessor 1/1, model 14/15 (predictions)
## i Slice3: preprocessor 1/1, model 15/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice3: preprocessor 1/1, model 15/15
## i Slice3: preprocessor 1/1, model 15/15 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/15
## x Slice4: preprocessor 1/1, model 1/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice4: preprocessor 1/1, model 2/15
## ✓ Slice4: preprocessor 1/1, model 2/15
## i Slice4: preprocessor 1/1, model 2/15 (predictions)
## i Slice4: preprocessor 1/1, model 3/15
## x Slice4: preprocessor 1/1, model 3/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice4: preprocessor 1/1, model 4/15
## ✓ Slice4: preprocessor 1/1, model 4/15
## i Slice4: preprocessor 1/1, model 4/15 (predictions)
## i Slice4: preprocessor 1/1, model 5/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice4: preprocessor 1/1, model 5/15
## i Slice4: preprocessor 1/1, model 5/15 (predictions)
## i Slice4: preprocessor 1/1, model 6/15
## x Slice4: preprocessor 1/1, model 6/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice4: preprocessor 1/1, model 7/15
## x Slice4: preprocessor 1/1, model 7/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice4: preprocessor 1/1, model 8/15
## x Slice4: preprocessor 1/1, model 8/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice4: preprocessor 1/1, model 9/15
## ✓ Slice4: preprocessor 1/1, model 9/15
## i Slice4: preprocessor 1/1, model 9/15 (predictions)
## i Slice4: preprocessor 1/1, model 10/15
## x Slice4: preprocessor 1/1, model 10/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice4: preprocessor 1/1, model 11/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice4: preprocessor 1/1, model 11/15
## i Slice4: preprocessor 1/1, model 11/15 (predictions)
## i Slice4: preprocessor 1/1, model 12/15
## ✓ Slice4: preprocessor 1/1, model 12/15
## i Slice4: preprocessor 1/1, model 12/15 (predictions)
## i Slice4: preprocessor 1/1, model 13/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## x Slice4: preprocessor 1/1, model 13/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice4: preprocessor 1/1, model 14/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice4: preprocessor 1/1, model 14/15
## i Slice4: preprocessor 1/1, model 14/15 (predictions)
## i Slice4: preprocessor 1/1, model 15/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice4: preprocessor 1/1, model 15/15
## i Slice4: preprocessor 1/1, model 15/15 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/15
## x Slice5: preprocessor 1/1, model 1/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice5: preprocessor 1/1, model 2/15
## ✓ Slice5: preprocessor 1/1, model 2/15
## i Slice5: preprocessor 1/1, model 2/15 (predictions)
## i Slice5: preprocessor 1/1, model 3/15
## x Slice5: preprocessor 1/1, model 3/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice5: preprocessor 1/1, model 4/15
## ✓ Slice5: preprocessor 1/1, model 4/15
## i Slice5: preprocessor 1/1, model 4/15 (predictions)
## i Slice5: preprocessor 1/1, model 5/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice5: preprocessor 1/1, model 5/15
## i Slice5: preprocessor 1/1, model 5/15 (predictions)
## i Slice5: preprocessor 1/1, model 6/15
## x Slice5: preprocessor 1/1, model 6/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice5: preprocessor 1/1, model 7/15
## x Slice5: preprocessor 1/1, model 7/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice5: preprocessor 1/1, model 8/15
## x Slice5: preprocessor 1/1, model 8/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice5: preprocessor 1/1, model 9/15
## ✓ Slice5: preprocessor 1/1, model 9/15
## i Slice5: preprocessor 1/1, model 9/15 (predictions)
## i Slice5: preprocessor 1/1, model 10/15
## x Slice5: preprocessor 1/1, model 10/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice5: preprocessor 1/1, model 11/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice5: preprocessor 1/1, model 11/15
## i Slice5: preprocessor 1/1, model 11/15 (predictions)
## i Slice5: preprocessor 1/1, model 12/15
## ✓ Slice5: preprocessor 1/1, model 12/15
## i Slice5: preprocessor 1/1, model 12/15 (predictions)
## i Slice5: preprocessor 1/1, model 13/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## x Slice5: preprocessor 1/1, model 13/15:
##   Error in `glubort()`:
##   ! Capacities must be supplied for `growth = 'logistic'`. Try specifyin...
## i Slice5: preprocessor 1/1, model 14/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice5: preprocessor 1/1, model 14/15
## i Slice5: preprocessor 1/1, model 14/15 (predictions)
## i Slice5: preprocessor 1/1, model 15/15
## seasonality.mode must be 'additive' or 'multiplicative'. Defaulting to 'additive'.
## ✓ Slice5: preprocessor 1/1, model 15/15
## i Slice5: preprocessor 1/1, model 15/15 (predictions)
toc()
## 77.03 sec elapsed
tune_result_prophet_boost %>% write_rds("tune_result_prophet_boost")
tune_result_prophet_boost <- read_rds("tune_result_prophet_boost")

tune_result_prophet_boost %>% 
  show_best(metric = "rmse", n = Inf)
## # A tibble: 8 × 18
##   growth changepoint_num changepoint_range season         prior_scale_changepo…¹
##   <chr>            <int>             <dbl> <chr>                           <dbl>
## 1 linear              21             0.885 additive                     33.1    
## 2 linear              15             0.781 none                          0.00144
## 3 linear              36             0.831 multiplicative                0.0222 
## 4 linear               2             0.676 multiplicative                0.00506
## 5 linear              31             0.636 none                          0.781  
## 6 linear              48             0.748 none                         10.5    
## 7 linear              11             0.616 none                          1.02   
## 8 linear              37             0.770 multiplicative                3.22   
## # ℹ abbreviated name: ¹​prior_scale_changepoints
## # ℹ 13 more variables: prior_scale_seasonality <dbl>, trees <int>, min_n <int>,
## #   tree_depth <int>, learn_rate <dbl>, loss_reduction <dbl>, stop_iter <int>,
## #   .metric <chr>, .estimator <chr>, mean <dbl>, n <int>, std_err <dbl>,
## #   .config <chr>
wflw_fit_prophet_boost %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_prophet_boost %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  ) %>% 
  fit(training(splits)) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>%
  # modeltime_forecast(new_data = test_data, actual_data = ihsg_tbl) %>%
  # plot_modeltime_forecast()
  modeltime_refit(data = yield) %>%
  # modeltime_forecast(new_data = ihsg_future_tbl, actual_data = ihsg_tbl) %>%
  modeltime_forecast(h = "1 year", actual_data = yield) %>%
  plot_modeltime_forecast()
## Converting to Modeltime Table.
wflw_fit_prophet_boost_best <- wflw_fit_prophet_boost %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_prophet_boost %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  )

wflw_fit_prophet_boost_best %>% write_rds("wflw_fit_prophet_boost_best")

Randomforest (Done)

wflw_fit_randomforest <- all_model_fit_resample %>% 
  pull_modeltime_model(6)

model_spec_rf_tune <- rand_forest(
  # mtry = tune(),
  trees = tune(),
  min_n = tune()
) %>%
set_engine("randomForest") %>%
set_mode("regression")


grid_spec_rf <- grid_latin_hypercube(
  # extract_parameter_dials(model_spec_prophet_boost_tune),
  parameters(model_spec_rf_tune),
  size = 15
)

wflw_tune_rf <- wflw_fit_randomforest %>% 
  update_model(model_spec_rf_tune)

tic()
tune_result_rf <- wflw_tune_rf %>%
  tune_grid(
    resamples = resamples_tscv_no_acum,
    grid      = grid_spec_rf,
    metrics   = default_forecast_accuracy_metric_set(),
    control   = control_grid(verbose = TRUE, save_pred = TRUE)
  )
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/15
## ✓ Slice1: preprocessor 1/1, model 1/15
## i Slice1: preprocessor 1/1, model 1/15 (predictions)
## i Slice1: preprocessor 1/1, model 2/15
## ✓ Slice1: preprocessor 1/1, model 2/15
## i Slice1: preprocessor 1/1, model 2/15 (predictions)
## i Slice1: preprocessor 1/1, model 3/15
## ✓ Slice1: preprocessor 1/1, model 3/15
## i Slice1: preprocessor 1/1, model 3/15 (predictions)
## i Slice1: preprocessor 1/1, model 4/15
## ✓ Slice1: preprocessor 1/1, model 4/15
## i Slice1: preprocessor 1/1, model 4/15 (predictions)
## i Slice1: preprocessor 1/1, model 5/15
## ✓ Slice1: preprocessor 1/1, model 5/15
## i Slice1: preprocessor 1/1, model 5/15 (predictions)
## i Slice1: preprocessor 1/1, model 6/15
## ✓ Slice1: preprocessor 1/1, model 6/15
## i Slice1: preprocessor 1/1, model 6/15 (predictions)
## i Slice1: preprocessor 1/1, model 7/15
## ✓ Slice1: preprocessor 1/1, model 7/15
## i Slice1: preprocessor 1/1, model 7/15 (predictions)
## i Slice1: preprocessor 1/1, model 8/15
## ✓ Slice1: preprocessor 1/1, model 8/15
## i Slice1: preprocessor 1/1, model 8/15 (predictions)
## i Slice1: preprocessor 1/1, model 9/15
## ✓ Slice1: preprocessor 1/1, model 9/15
## i Slice1: preprocessor 1/1, model 9/15 (predictions)
## i Slice1: preprocessor 1/1, model 10/15
## ✓ Slice1: preprocessor 1/1, model 10/15
## i Slice1: preprocessor 1/1, model 10/15 (predictions)
## i Slice1: preprocessor 1/1, model 11/15
## ✓ Slice1: preprocessor 1/1, model 11/15
## i Slice1: preprocessor 1/1, model 11/15 (predictions)
## i Slice1: preprocessor 1/1, model 12/15
## ✓ Slice1: preprocessor 1/1, model 12/15
## i Slice1: preprocessor 1/1, model 12/15 (predictions)
## i Slice1: preprocessor 1/1, model 13/15
## ✓ Slice1: preprocessor 1/1, model 13/15
## i Slice1: preprocessor 1/1, model 13/15 (predictions)
## i Slice1: preprocessor 1/1, model 14/15
## ✓ Slice1: preprocessor 1/1, model 14/15
## i Slice1: preprocessor 1/1, model 14/15 (predictions)
## i Slice1: preprocessor 1/1, model 15/15
## ✓ Slice1: preprocessor 1/1, model 15/15
## i Slice1: preprocessor 1/1, model 15/15 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/15
## ✓ Slice2: preprocessor 1/1, model 1/15
## i Slice2: preprocessor 1/1, model 1/15 (predictions)
## i Slice2: preprocessor 1/1, model 2/15
## ✓ Slice2: preprocessor 1/1, model 2/15
## i Slice2: preprocessor 1/1, model 2/15 (predictions)
## i Slice2: preprocessor 1/1, model 3/15
## ✓ Slice2: preprocessor 1/1, model 3/15
## i Slice2: preprocessor 1/1, model 3/15 (predictions)
## i Slice2: preprocessor 1/1, model 4/15
## ✓ Slice2: preprocessor 1/1, model 4/15
## i Slice2: preprocessor 1/1, model 4/15 (predictions)
## i Slice2: preprocessor 1/1, model 5/15
## ✓ Slice2: preprocessor 1/1, model 5/15
## i Slice2: preprocessor 1/1, model 5/15 (predictions)
## i Slice2: preprocessor 1/1, model 6/15
## ✓ Slice2: preprocessor 1/1, model 6/15
## i Slice2: preprocessor 1/1, model 6/15 (predictions)
## i Slice2: preprocessor 1/1, model 7/15
## ✓ Slice2: preprocessor 1/1, model 7/15
## i Slice2: preprocessor 1/1, model 7/15 (predictions)
## i Slice2: preprocessor 1/1, model 8/15
## ✓ Slice2: preprocessor 1/1, model 8/15
## i Slice2: preprocessor 1/1, model 8/15 (predictions)
## i Slice2: preprocessor 1/1, model 9/15
## ✓ Slice2: preprocessor 1/1, model 9/15
## i Slice2: preprocessor 1/1, model 9/15 (predictions)
## i Slice2: preprocessor 1/1, model 10/15
## ✓ Slice2: preprocessor 1/1, model 10/15
## i Slice2: preprocessor 1/1, model 10/15 (predictions)
## i Slice2: preprocessor 1/1, model 11/15
## ✓ Slice2: preprocessor 1/1, model 11/15
## i Slice2: preprocessor 1/1, model 11/15 (predictions)
## i Slice2: preprocessor 1/1, model 12/15
## ✓ Slice2: preprocessor 1/1, model 12/15
## i Slice2: preprocessor 1/1, model 12/15 (predictions)
## i Slice2: preprocessor 1/1, model 13/15
## ✓ Slice2: preprocessor 1/1, model 13/15
## i Slice2: preprocessor 1/1, model 13/15 (predictions)
## i Slice2: preprocessor 1/1, model 14/15
## ✓ Slice2: preprocessor 1/1, model 14/15
## i Slice2: preprocessor 1/1, model 14/15 (predictions)
## i Slice2: preprocessor 1/1, model 15/15
## ✓ Slice2: preprocessor 1/1, model 15/15
## i Slice2: preprocessor 1/1, model 15/15 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/15
## ✓ Slice3: preprocessor 1/1, model 1/15
## i Slice3: preprocessor 1/1, model 1/15 (predictions)
## i Slice3: preprocessor 1/1, model 2/15
## ✓ Slice3: preprocessor 1/1, model 2/15
## i Slice3: preprocessor 1/1, model 2/15 (predictions)
## i Slice3: preprocessor 1/1, model 3/15
## ✓ Slice3: preprocessor 1/1, model 3/15
## i Slice3: preprocessor 1/1, model 3/15 (predictions)
## i Slice3: preprocessor 1/1, model 4/15
## ✓ Slice3: preprocessor 1/1, model 4/15
## i Slice3: preprocessor 1/1, model 4/15 (predictions)
## i Slice3: preprocessor 1/1, model 5/15
## ✓ Slice3: preprocessor 1/1, model 5/15
## i Slice3: preprocessor 1/1, model 5/15 (predictions)
## i Slice3: preprocessor 1/1, model 6/15
## ✓ Slice3: preprocessor 1/1, model 6/15
## i Slice3: preprocessor 1/1, model 6/15 (predictions)
## i Slice3: preprocessor 1/1, model 7/15
## ✓ Slice3: preprocessor 1/1, model 7/15
## i Slice3: preprocessor 1/1, model 7/15 (predictions)
## i Slice3: preprocessor 1/1, model 8/15
## ✓ Slice3: preprocessor 1/1, model 8/15
## i Slice3: preprocessor 1/1, model 8/15 (predictions)
## i Slice3: preprocessor 1/1, model 9/15
## ✓ Slice3: preprocessor 1/1, model 9/15
## i Slice3: preprocessor 1/1, model 9/15 (predictions)
## i Slice3: preprocessor 1/1, model 10/15
## ✓ Slice3: preprocessor 1/1, model 10/15
## i Slice3: preprocessor 1/1, model 10/15 (predictions)
## i Slice3: preprocessor 1/1, model 11/15
## ✓ Slice3: preprocessor 1/1, model 11/15
## i Slice3: preprocessor 1/1, model 11/15 (predictions)
## i Slice3: preprocessor 1/1, model 12/15
## ✓ Slice3: preprocessor 1/1, model 12/15
## i Slice3: preprocessor 1/1, model 12/15 (predictions)
## i Slice3: preprocessor 1/1, model 13/15
## ✓ Slice3: preprocessor 1/1, model 13/15
## i Slice3: preprocessor 1/1, model 13/15 (predictions)
## i Slice3: preprocessor 1/1, model 14/15
## ✓ Slice3: preprocessor 1/1, model 14/15
## i Slice3: preprocessor 1/1, model 14/15 (predictions)
## i Slice3: preprocessor 1/1, model 15/15
## ✓ Slice3: preprocessor 1/1, model 15/15
## i Slice3: preprocessor 1/1, model 15/15 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/15
## ✓ Slice4: preprocessor 1/1, model 1/15
## i Slice4: preprocessor 1/1, model 1/15 (predictions)
## i Slice4: preprocessor 1/1, model 2/15
## ✓ Slice4: preprocessor 1/1, model 2/15
## i Slice4: preprocessor 1/1, model 2/15 (predictions)
## i Slice4: preprocessor 1/1, model 3/15
## ✓ Slice4: preprocessor 1/1, model 3/15
## i Slice4: preprocessor 1/1, model 3/15 (predictions)
## i Slice4: preprocessor 1/1, model 4/15
## ✓ Slice4: preprocessor 1/1, model 4/15
## i Slice4: preprocessor 1/1, model 4/15 (predictions)
## i Slice4: preprocessor 1/1, model 5/15
## ✓ Slice4: preprocessor 1/1, model 5/15
## i Slice4: preprocessor 1/1, model 5/15 (predictions)
## i Slice4: preprocessor 1/1, model 6/15
## ✓ Slice4: preprocessor 1/1, model 6/15
## i Slice4: preprocessor 1/1, model 6/15 (predictions)
## i Slice4: preprocessor 1/1, model 7/15
## ✓ Slice4: preprocessor 1/1, model 7/15
## i Slice4: preprocessor 1/1, model 7/15 (predictions)
## i Slice4: preprocessor 1/1, model 8/15
## ✓ Slice4: preprocessor 1/1, model 8/15
## i Slice4: preprocessor 1/1, model 8/15 (predictions)
## i Slice4: preprocessor 1/1, model 9/15
## ✓ Slice4: preprocessor 1/1, model 9/15
## i Slice4: preprocessor 1/1, model 9/15 (predictions)
## i Slice4: preprocessor 1/1, model 10/15
## ✓ Slice4: preprocessor 1/1, model 10/15
## i Slice4: preprocessor 1/1, model 10/15 (predictions)
## i Slice4: preprocessor 1/1, model 11/15
## ✓ Slice4: preprocessor 1/1, model 11/15
## i Slice4: preprocessor 1/1, model 11/15 (predictions)
## i Slice4: preprocessor 1/1, model 12/15
## ✓ Slice4: preprocessor 1/1, model 12/15
## i Slice4: preprocessor 1/1, model 12/15 (predictions)
## i Slice4: preprocessor 1/1, model 13/15
## ✓ Slice4: preprocessor 1/1, model 13/15
## i Slice4: preprocessor 1/1, model 13/15 (predictions)
## i Slice4: preprocessor 1/1, model 14/15
## ✓ Slice4: preprocessor 1/1, model 14/15
## i Slice4: preprocessor 1/1, model 14/15 (predictions)
## i Slice4: preprocessor 1/1, model 15/15
## ✓ Slice4: preprocessor 1/1, model 15/15
## i Slice4: preprocessor 1/1, model 15/15 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/15
## ✓ Slice5: preprocessor 1/1, model 1/15
## i Slice5: preprocessor 1/1, model 1/15 (predictions)
## i Slice5: preprocessor 1/1, model 2/15
## ✓ Slice5: preprocessor 1/1, model 2/15
## i Slice5: preprocessor 1/1, model 2/15 (predictions)
## i Slice5: preprocessor 1/1, model 3/15
## ✓ Slice5: preprocessor 1/1, model 3/15
## i Slice5: preprocessor 1/1, model 3/15 (predictions)
## i Slice5: preprocessor 1/1, model 4/15
## ✓ Slice5: preprocessor 1/1, model 4/15
## i Slice5: preprocessor 1/1, model 4/15 (predictions)
## i Slice5: preprocessor 1/1, model 5/15
## ✓ Slice5: preprocessor 1/1, model 5/15
## i Slice5: preprocessor 1/1, model 5/15 (predictions)
## i Slice5: preprocessor 1/1, model 6/15
## ✓ Slice5: preprocessor 1/1, model 6/15
## i Slice5: preprocessor 1/1, model 6/15 (predictions)
## i Slice5: preprocessor 1/1, model 7/15
## ✓ Slice5: preprocessor 1/1, model 7/15
## i Slice5: preprocessor 1/1, model 7/15 (predictions)
## i Slice5: preprocessor 1/1, model 8/15
## ✓ Slice5: preprocessor 1/1, model 8/15
## i Slice5: preprocessor 1/1, model 8/15 (predictions)
## i Slice5: preprocessor 1/1, model 9/15
## ✓ Slice5: preprocessor 1/1, model 9/15
## i Slice5: preprocessor 1/1, model 9/15 (predictions)
## i Slice5: preprocessor 1/1, model 10/15
## ✓ Slice5: preprocessor 1/1, model 10/15
## i Slice5: preprocessor 1/1, model 10/15 (predictions)
## i Slice5: preprocessor 1/1, model 11/15
## ✓ Slice5: preprocessor 1/1, model 11/15
## i Slice5: preprocessor 1/1, model 11/15 (predictions)
## i Slice5: preprocessor 1/1, model 12/15
## ✓ Slice5: preprocessor 1/1, model 12/15
## i Slice5: preprocessor 1/1, model 12/15 (predictions)
## i Slice5: preprocessor 1/1, model 13/15
## ✓ Slice5: preprocessor 1/1, model 13/15
## i Slice5: preprocessor 1/1, model 13/15 (predictions)
## i Slice5: preprocessor 1/1, model 14/15
## ✓ Slice5: preprocessor 1/1, model 14/15
## i Slice5: preprocessor 1/1, model 14/15 (predictions)
## i Slice5: preprocessor 1/1, model 15/15
## ✓ Slice5: preprocessor 1/1, model 15/15
## i Slice5: preprocessor 1/1, model 15/15 (predictions)
toc()
## 37.36 sec elapsed
tune_result_rf %>% write_rds("tune_result_rf")
tune_result_rf <- read_rds("tune_result_rf")

tune_result_rf %>% 
  show_best(metric = "rmse", n = Inf)
## # A tibble: 15 × 8
##    trees min_n .metric .estimator  mean     n std_err .config              
##    <int> <int> <chr>   <chr>      <dbl> <int>   <dbl> <chr>                
##  1   316    15 rmse    standard   0.521     5  0.0870 Preprocessor1_Model05
##  2   841    22 rmse    standard   0.527     5  0.0919 Preprocessor1_Model02
##  3  1226     9 rmse    standard   0.528     5  0.0916 Preprocessor1_Model12
##  4  1727    11 rmse    standard   0.529     5  0.0922 Preprocessor1_Model11
##  5   602     3 rmse    standard   0.530     5  0.0911 Preprocessor1_Model10
##  6  1742    23 rmse    standard   0.530     5  0.0934 Preprocessor1_Model08
##  7   936    33 rmse    standard   0.532     5  0.0863 Preprocessor1_Model04
##  8  1440     6 rmse    standard   0.535     5  0.0979 Preprocessor1_Model07
##  9  1195    25 rmse    standard   0.541     5  0.0961 Preprocessor1_Model14
## 10  1585    32 rmse    standard   0.541     5  0.0924 Preprocessor1_Model15
## 11   141    13 rmse    standard   0.542     5  0.106  Preprocessor1_Model06
## 12  1975    38 rmse    standard   0.545     5  0.0928 Preprocessor1_Model01
## 13   800    27 rmse    standard   0.547     5  0.0957 Preprocessor1_Model09
## 14   456    36 rmse    standard   0.548     5  0.0912 Preprocessor1_Model13
## 15     4    18 rmse    standard   0.572     5  0.102  Preprocessor1_Model03
wflw_fit_randomforest %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_rf %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  ) %>% 
  fit(training(splits)) %>% 
  modeltime_calibrate(new_data = testing(splits)) %>%
  # modeltime_forecast(new_data = test_data, actual_data = ihsg_tbl) %>%
  # plot_modeltime_forecast()
  modeltime_refit(data = yield) %>%
  # modeltime_forecast(new_data = ihsg_future_tbl, actual_data = ihsg_tbl) %>%
  modeltime_forecast(h = "1 year", actual_data = yield) %>%
  plot_modeltime_forecast()
## Warning: 25 columns were requested but there were 17 predictors in the data. 17
## will be used.
## Converting to Modeltime Table.
## Warning: There was 1 warning in `dplyr::mutate()`.
## ℹ In argument: `.model = purrr::map2(...)`.
## Caused by warning:
## ! 25 columns were requested but there were 17 predictors in the data. 17 will be used.
wflw_fit_randomforest_best <- wflw_fit_randomforest %>% 
  # update_model(model_spec_prophet) %>% 
  finalize_workflow(
    tune_result_rf %>% 
      show_best(metric = "rmse") %>%
      dplyr::slice(1)
  )

wflw_fit_randomforest_best %>% write_rds("wflw_fit_randomforest_best")

Ensemble

Median

library(dbarts)

all_model_fit_refit %>% 
  ensemble_average(type = "median") %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(actual_data = yield, h = "1 year") %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

Mean

all_model_fit_refit %>% 
  ensemble_average(type = "mean") %>% 
  modeltime_calibrate(new_data = testing(splits)) %>% 
  modeltime_forecast(actual_data = yield, h = "1 year") %>% 
  plot_modeltime_forecast(.conf_interval_show = F)
## Converting to Modeltime Table.

Stacking

Submodels Resample

all_model_fit_refit %>% 
  filter(.model_desc != "DBARTS")
## # Modeltime Table
## # A tibble: 10 × 5
##    .model_id .model     .model_desc               .type .calibration_data 
##        <int> <list>     <chr>                     <chr> <list>            
##  1         1 <fit[+]>   PROPHET                   Test  <tibble [744 × 4]>
##  2         2 <workflow> GLMNET                    Test  <tibble [744 × 4]>
##  3         3 <workflow> KERNLAB                   Test  <tibble [744 × 4]>
##  4         4 <workflow> KERNLAB                   Test  <tibble [744 × 4]>
##  5         5 <workflow> KKNN                      Test  <tibble [744 × 4]>
##  6         6 <workflow> RANDOMFOREST              Test  <tibble [744 × 4]>
##  7         7 <workflow> XGBOOST                   Test  <tibble [744 × 4]>
##  8         8 <workflow> CUBIST                    Test  <tibble [744 × 4]>
##  9         9 <workflow> NNAR(2,1,10)[5]           Test  <tibble [744 × 4]>
## 10        10 <workflow> PROPHET W/ XGBOOST ERRORS Test  <tibble [744 × 4]>
submodels_resample <- all_model_fit_refit %>% 
  filter(.model_desc != "DBARTS") %>%
    modeltime_fit_resamples(
        resamples = resamples_tscv_no_acum,
        control   = control_resamples(
            verbose   = TRUE, 
            # allow_par = FALSE, 
            allow_par = TRUE,
            pkgs      = c("Cubist", "rules", "tidymodels", "ranger", "parsnip", "modeltime")
        )
    )
## ── Fitting Resamples ────────────────────────────────────────────
## • Model ID: 1 PROPHET
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## • Model ID: 2 GLMNET
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## • Model ID: 3 KERNLAB
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## • Model ID: 4 KERNLAB
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## • Model ID: 5 KKNN
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## • Model ID: 6 RANDOMFOREST
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## ! Slice1: preprocessor 1/1, model 1/1: 25 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## ! Slice2: preprocessor 1/1, model 1/1: 25 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## ! Slice3: preprocessor 1/1, model 1/1: 25 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## ! Slice4: preprocessor 1/1, model 1/1: 25 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## ! Slice5: preprocessor 1/1, model 1/1: 25 columns were requested but there were 17 predictors in the data. 17 w...
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## • Model ID: 7 XGBOOST
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## • Model ID: 8 CUBIST
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## ! Slice1: preprocessor 1/1, model 1/1: The number of neighbors should be >= 0 and <= 9. Truncating the value.
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## ! Slice2: preprocessor 1/1, model 1/1: The number of neighbors should be >= 0 and <= 9. Truncating the value.
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## ! Slice3: preprocessor 1/1, model 1/1: The number of neighbors should be >= 0 and <= 9. Truncating the value.
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## ! Slice4: preprocessor 1/1, model 1/1: The number of neighbors should be >= 0 and <= 9. Truncating the value.
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## ! Slice5: preprocessor 1/1, model 1/1: The number of neighbors should be >= 0 and <= 9. Truncating the value.
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## • Model ID: 9 NNAR(2,1,10)[5]
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## frequency = 5 observations per 1 week
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## frequency = 5 observations per 1 week
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## frequency = 5 observations per 1 week
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## frequency = 5 observations per 1 week
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## frequency = 5 observations per 1 week
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## • Model ID: 10 PROPHET W/ XGBOOST ERRORS
## i Slice1: preprocessor 1/1
## ✓ Slice1: preprocessor 1/1
## i Slice1: preprocessor 1/1, model 1/1
## ✓ Slice1: preprocessor 1/1, model 1/1
## i Slice1: preprocessor 1/1, model 1/1 (predictions)
## i Slice2: preprocessor 1/1
## ✓ Slice2: preprocessor 1/1
## i Slice2: preprocessor 1/1, model 1/1
## ✓ Slice2: preprocessor 1/1, model 1/1
## i Slice2: preprocessor 1/1, model 1/1 (predictions)
## i Slice3: preprocessor 1/1
## ✓ Slice3: preprocessor 1/1
## i Slice3: preprocessor 1/1, model 1/1
## ✓ Slice3: preprocessor 1/1, model 1/1
## i Slice3: preprocessor 1/1, model 1/1 (predictions)
## i Slice4: preprocessor 1/1
## ✓ Slice4: preprocessor 1/1
## i Slice4: preprocessor 1/1, model 1/1
## ✓ Slice4: preprocessor 1/1, model 1/1
## i Slice4: preprocessor 1/1, model 1/1 (predictions)
## i Slice5: preprocessor 1/1
## ✓ Slice5: preprocessor 1/1
## i Slice5: preprocessor 1/1, model 1/1
## ✓ Slice5: preprocessor 1/1, model 1/1
## i Slice5: preprocessor 1/1, model 1/1 (predictions)
## 33.83 sec elapsed
submodels_resample %>% write_rds("submodels_resample")

submodels_resample$.resample_results[[1]]$.predictions
## [[1]]
## # A tibble: 64 × 4
##    .pred  .row close .config             
##    <dbl> <int> <dbl> <chr>               
##  1  7.16  2172  7.07 Preprocessor1_Model1
##  2  7.18  2173  7.04 Preprocessor1_Model1
##  3  7.20  2174  7.06 Preprocessor1_Model1
##  4  7.26  2175  7.07 Preprocessor1_Model1
##  5  7.29  2176  7.05 Preprocessor1_Model1
##  6  7.29  2177  6.99 Preprocessor1_Model1
##  7  7.32  2178  6.91 Preprocessor1_Model1
##  8  7.34  2179  6.87 Preprocessor1_Model1
##  9  7.41  2180  6.87 Preprocessor1_Model1
## 10  7.44  2181  6.85 Preprocessor1_Model1
## # ℹ 54 more rows
## 
## [[2]]
## # A tibble: 64 × 4
##    .pred  .row close .config             
##    <dbl> <int> <dbl> <chr>               
##  1  7.29  1920  7.10 Preprocessor1_Model1
##  2  7.29  1921  7.12 Preprocessor1_Model1
##  3  7.29  1922  7.14 Preprocessor1_Model1
##  4  7.32  1923  7.14 Preprocessor1_Model1
##  5  7.38  1924  7.18 Preprocessor1_Model1
##  6  7.42  1925  7.26 Preprocessor1_Model1
##  7  7.42  1926  7.27 Preprocessor1_Model1
##  8  7.42  1927  7.19 Preprocessor1_Model1
##  9  7.44  1928  7.22 Preprocessor1_Model1
## 10  7.47  1929  7.26 Preprocessor1_Model1
## # ℹ 54 more rows
## 
## [[3]]
## # A tibble: 64 × 4
##    .pred  .row close .config             
##    <dbl> <int> <dbl> <chr>               
##  1  7.38  1668  7.52 Preprocessor1_Model1
##  2  7.32  1669  7.51 Preprocessor1_Model1
##  3  7.24  1670  7.55 Preprocessor1_Model1
##  4  7.02  1671  7.55 Preprocessor1_Model1
##  5  6.96  1672  7.59 Preprocessor1_Model1
##  6  6.89  1673  7.73 Preprocessor1_Model1
##  7  6.82  1674  7.82 Preprocessor1_Model1
##  8  6.74  1675  7.88 Preprocessor1_Model1
##  9  6.56  1676  7.79 Preprocessor1_Model1
## 10  6.53  1677  7.81 Preprocessor1_Model1
## # ℹ 54 more rows
## 
## [[4]]
## # A tibble: 64 × 4
##    .pred  .row close .config             
##    <dbl> <int> <dbl> <chr>               
##  1  6.99  1416  6.93 Preprocessor1_Model1
##  2  6.97  1417  6.96 Preprocessor1_Model1
##  3  6.96  1418  7.00 Preprocessor1_Model1
##  4  6.96  1419  6.98 Preprocessor1_Model1
##  5  6.96  1420  7.00 Preprocessor1_Model1
##  6  6.92  1421  6.95 Preprocessor1_Model1
##  7  6.89  1422  6.95 Preprocessor1_Model1
##  8  6.87  1423  6.92 Preprocessor1_Model1
##  9  6.86  1424  6.91 Preprocessor1_Model1
## 10  6.86  1425  6.90 Preprocessor1_Model1
## # ℹ 54 more rows
## 
## [[5]]
## # A tibble: 64 × 4
##    .pred  .row close .config             
##    <dbl> <int> <dbl> <chr>               
##  1  7.04  1164  6.96 Preprocessor1_Model1
##  2  7.06  1165  6.87 Preprocessor1_Model1
##  3  7.05  1166  6.97 Preprocessor1_Model1
##  4  7.06  1167  6.86 Preprocessor1_Model1
##  5  7.07  1168  6.88 Preprocessor1_Model1
##  6  7.14  1169  6.93 Preprocessor1_Model1
##  7  7.17  1170  6.94 Preprocessor1_Model1
##  8  7.17  1171  6.91 Preprocessor1_Model1
##  9  7.18  1172  6.97 Preprocessor1_Model1
## 10  7.19  1173  6.97 Preprocessor1_Model1
## # ℹ 54 more rows
summary(submodels_resample)
##    .model_id       .model.Length      .model.Class        .model.Mode   
##  Min.   : 1.00   6                  _prophet_fit_impl  list             
##  1st Qu.: 3.25   4                  workflow           list             
##  Median : 5.50   4                  workflow           list             
##  Mean   : 5.50   4                  workflow           list             
##  3rd Qu.: 7.75   4                  workflow           list             
##  Max.   :10.00   4                  workflow           list             
##                  4                  workflow           list             
##                  4                  workflow           list             
##                  4                  workflow           list             
##                  4                  workflow           list             
##  .model_desc           .type          
##  Length:10          Length:10         
##  Class :character   Class :character  
##  Mode  :character   Mode  :character  
##                                       
##                                       
##                                       
##                                       
##                                       
##                                       
##                                       
##  .calibration_data.Length  .calibration_data.Class  .calibration_data.Mode
##  4       tbl_df  list                                                     
##  4       tbl_df  list                                                     
##  4       tbl_df  list                                                     
##  4       tbl_df  list                                                     
##  4       tbl_df  list                                                     
##  4       tbl_df  list                                                     
##  4       tbl_df  list                                                     
##  4       tbl_df  list                                                     
##  4       tbl_df  list                                                     
##  4       tbl_df  list                                                     
##  .resample_results.Length  .resample_results.Class  .resample_results.Mode
##  5                 resample_results  list                                 
##  5                 resample_results  list                                 
##  5                 resample_results  list                                 
##  5                 resample_results  list                                 
##  5                 resample_results  list                                 
##  5                 resample_results  list                                 
##  5                 resample_results  list                                 
##  5                 resample_results  list                                 
##  5                 resample_results  list                                 
##  5                 resample_results  list
str(submodels_resample)
## mdl_tm_t [10 × 6] (S3: mdl_time_tbl/tbl_df/tbl/data.frame)
##  $ .model_id        : int [1:10] 1 2 3 4 5 6 7 8 9 10
##  $ .model           :List of 10
##   ..$ :List of 6
##   .. ..$ lvl         : NULL
##   .. ..$ spec        :List of 8
##   .. .. ..$ args                 :List of 12
##   .. .. .. ..$ growth                  : language ~NULL
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ changepoint_num         : language ~NULL
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ changepoint_range       : language ~NULL
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ seasonality_yearly      : language ~TRUE
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ seasonality_weekly      : language ~TRUE
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ seasonality_daily       : language ~TRUE
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ season                  : language ~NULL
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ prior_scale_changepoints: language ~NULL
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ prior_scale_seasonality : language ~NULL
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ prior_scale_holidays    : language ~NULL
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ logistic_cap            : language ~NULL
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. ..$ logistic_floor          : language ~NULL
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. ..$ eng_args             : Named list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. ..$ mode                 : chr "regression"
##   .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. ..$ method               :List of 3
##   .. .. .. ..$ libs: chr [1:2] "prophet" "modeltime"
##   .. .. .. ..$ fit :List of 5
##   .. .. .. .. ..$ interface: chr "data.frame"
##   .. .. .. .. ..$ protect  : chr [1:2] "x" "y"
##   .. .. .. .. ..$ func     : Named chr "prophet_fit_impl"
##   .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. ..$ defaults :List of 1
##   .. .. .. .. .. ..$ uncertainty.samples: num 0
##   .. .. .. .. ..$ args     :List of 6
##   .. .. .. .. .. ..$ x                  : language missing_arg()
##   .. .. .. .. .. ..$ y                  : language missing_arg()
##   .. .. .. .. .. ..$ yearly.seasonality : language ~TRUE
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ weekly.seasonality : language ~TRUE
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ daily.seasonality  : language ~TRUE
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ uncertainty.samples: num 0
##   .. .. .. ..$ pred:List of 1
##   .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. ..$ object  : language object$fit
##   .. .. .. .. .. .. ..$ new_data: symbol new_data
##   .. .. ..$ engine               : chr "prophet"
##   .. .. ..$ user_specified_engine: logi TRUE
##   .. .. ..$ defaults             :List of 1
##   .. .. .. ..$ uncertainty.samples: num 0
##   .. .. ..- attr(*, "class")= chr [1:2] "prophet_reg" "model_spec"
##   .. ..$ fit         :List of 4
##   .. .. ..$ models:List of 1
##   .. .. .. ..$ model_1:List of 32
##   .. .. .. .. ..$ growth                 : chr "linear"
##   .. .. .. .. ..$ changepoints           : POSIXct[1:25], format: "2012-04-16" ...
##   .. .. .. .. ..$ n.changepoints         : num 25
##   .. .. .. .. ..$ changepoint.range      : num 0.8
##   .. .. .. .. ..$ yearly.seasonality     : logi TRUE
##   .. .. .. .. ..$ weekly.seasonality     : logi TRUE
##   .. .. .. .. ..$ daily.seasonality      : logi TRUE
##   .. .. .. .. ..$ holidays               : NULL
##   .. .. .. .. ..$ seasonality.mode       : chr "additive"
##   .. .. .. .. ..$ seasonality.prior.scale: num 10
##   .. .. .. .. ..$ changepoint.prior.scale: num 0.05
##   .. .. .. .. ..$ holidays.prior.scale   : num 10
##   .. .. .. .. ..$ mcmc.samples           : num 0
##   .. .. .. .. ..$ interval.width         : num 0.8
##   .. .. .. .. ..$ uncertainty.samples    : num 0
##   .. .. .. .. ..$ specified.changepoints : logi FALSE
##   .. .. .. .. ..$ start                  : POSIXct[1:1], format: "2011-11-29"
##   .. .. .. .. ..$ y.scale                : num 9.77
##   .. .. .. .. ..$ logistic.floor         : logi FALSE
##   .. .. .. .. ..$ t.scale                : num 375494400
##   .. .. .. .. ..$ changepoints.t         : num [1:25] 0.032 0.0642 0.0966 0.1295 0.1618 ...
##   .. .. .. .. ..$ seasonalities          :List of 3
##   .. .. .. .. .. ..$ yearly:List of 5
##   .. .. .. .. .. .. ..$ period        : num 365
##   .. .. .. .. .. .. ..$ fourier.order : num 10
##   .. .. .. .. .. .. ..$ prior.scale   : num 10
##   .. .. .. .. .. .. ..$ mode          : chr "additive"
##   .. .. .. .. .. .. ..$ condition.name: NULL
##   .. .. .. .. .. ..$ weekly:List of 5
##   .. .. .. .. .. .. ..$ period        : num 7
##   .. .. .. .. .. .. ..$ fourier.order : num 3
##   .. .. .. .. .. .. ..$ prior.scale   : num 10
##   .. .. .. .. .. .. ..$ mode          : chr "additive"
##   .. .. .. .. .. .. ..$ condition.name: NULL
##   .. .. .. .. .. ..$ daily :List of 5
##   .. .. .. .. .. .. ..$ period        : num 1
##   .. .. .. .. .. .. ..$ fourier.order : num 4
##   .. .. .. .. .. .. ..$ prior.scale   : num 10
##   .. .. .. .. .. .. ..$ mode          : chr "additive"
##   .. .. .. .. .. .. ..$ condition.name: NULL
##   .. .. .. .. ..$ extra_regressors       : list()
##   .. .. .. .. ..$ country_holidays       : NULL
##   .. .. .. .. ..$ stan.fit               :List of 4
##   .. .. .. .. .. ..$ par        :List of 6
##   .. .. .. .. .. .. ..$ k        : num -0.863
##   .. .. .. .. .. .. ..$ m        : num 0.685
##   .. .. .. .. .. .. ..$ delta    : num [1:25(1d)] -0.00061259024 -0.00000075219 5.37550302501 0.00000000553 -4.14023514055 ...
##   .. .. .. .. .. .. ..$ sigma_obs: num 0.0377
##   .. .. .. .. .. .. ..$ beta     : num [1:34(1d)] -0.011589 -0.0036 -0.004973 0.001538 0.000756 ...
##   .. .. .. .. .. .. ..$ trend    : num [1:2979(1d)] 0.685 0.685 0.684 0.684 0.684 ...
##   .. .. .. .. .. ..$ value      : num 7725
##   .. .. .. .. .. ..$ return_code: int 0
##   .. .. .. .. .. ..$ theta_tilde: num [1, 1:3041] -0.863052931 0.684873191 -0.00061259 -0.000000752 5.375503025 ...
##   .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. ..$ : chr [1:3041] "k" "m" "delta[1]" "delta[2]" ...
##   .. .. .. .. ..$ params                 :List of 6
##   .. .. .. .. .. ..$ k        : num -0.863
##   .. .. .. .. .. ..$ m        : num 0.685
##   .. .. .. .. .. ..$ delta    : num [1, 1:25] -0.00061259024 -0.00000075219 5.37550302501 0.00000000553 -4.14023514055 ...
##   .. .. .. .. .. ..$ sigma_obs: num 0.0377
##   .. .. .. .. .. ..$ beta     : num [1, 1:34] -0.011589 -0.0036 -0.004973 0.001538 0.000756 ...
##   .. .. .. .. .. ..$ trend    : num [1:2979(1d)] 0.685 0.685 0.684 0.684 0.684 ...
##   .. .. .. .. ..$ history                : tibble [2,979 × 5] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. ..$ y       : num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ ds      : POSIXct[1:2979], format: "2011-11-29" ...
##   .. .. .. .. .. ..$ floor   : num [1:2979] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. ..$ t       : num [1:2979] 0 0.00023 0.00046 0.00069 0.00138 ...
##   .. .. .. .. .. ..$ y_scaled: num [1:2979] 0.704 0.704 0.657 0.63 0.63 ...
##   .. .. .. .. ..$ history.dates          : POSIXct[1:2979], format: "2011-11-29" ...
##   .. .. .. .. ..$ train.holiday.names    : NULL
##   .. .. .. .. ..$ train.component.cols   :'data.frame':  34 obs. of  5 variables:
##   .. .. .. .. .. ..$ additive_terms      : int [1:34] 1 1 1 1 1 1 1 1 1 1 ...
##   .. .. .. .. .. ..$ daily               : int [1:34] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. ..$ weekly              : int [1:34] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. ..$ yearly              : int [1:34] 1 1 1 1 1 1 1 1 1 1 ...
##   .. .. .. .. .. ..$ multiplicative_terms: num [1:34] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. ..$ component.modes        :List of 2
##   .. .. .. .. .. ..$ additive      : chr [1:6] "yearly" "weekly" "daily" "additive_terms" ...
##   .. .. .. .. .. ..$ multiplicative: chr [1:2] "multiplicative_terms" "extra_regressors_multiplicative"
##   .. .. .. .. ..$ fit.kwargs             : list()
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "prophet" "list"
##   .. .. ..$ data  : tibble [2,979 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ time      : Date[1:2979], format: "2011-11-29" ...
##   .. .. .. ..$ .actual   : num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ .fitted   : num [1:2979] 6.27 6.26 6.25 6.25 6.26 ...
##   .. .. .. ..$ .residuals: num [1:2979] 0.6151 0.6261 0.1612 -0.0916 -0.1033 ...
##   .. .. ..$ extras:List of 2
##   .. .. .. ..$ xreg_recipe    : NULL
##   .. .. .. ..$ logistic_params:List of 3
##   .. .. .. .. ..$ growth        : chr "linear"
##   .. .. .. .. ..$ logistic_cap  : NULL
##   .. .. .. .. ..$ logistic_floor: NULL
##   .. .. ..$ desc  : chr "PROPHET"
##   .. .. ..- attr(*, "class")= chr [1:2] "prophet_fit_impl" "modeltime_bridge"
##   .. ..$ preproc     :List of 4
##   .. .. ..$ terms  :Classes 'terms', 'formula'  language close ~ time
##   .. .. .. .. ..- attr(*, "variables")= language list(close, time)
##   .. .. .. .. ..- attr(*, "factors")= int [1:2, 1] 0 1
##   .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. ..$ : chr [1:2] "close" "time"
##   .. .. .. .. .. .. ..$ : chr "time"
##   .. .. .. .. ..- attr(*, "term.labels")= chr "time"
##   .. .. .. .. ..- attr(*, "order")= int 1
##   .. .. .. .. ..- attr(*, "intercept")= int 1
##   .. .. .. .. ..- attr(*, "response")= int 1
##   .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180cf392c78> 
##   .. .. .. .. ..- attr(*, "predvars")= language list(close, time)
##   .. .. .. .. ..- attr(*, "dataClasses")= Named chr [1:2] "numeric" "other"
##   .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "close" "time"
##   .. .. ..$ xlevels: Named list()
##   .. .. ..$ options:List of 3
##   .. .. .. ..$ indicators      : chr "none"
##   .. .. .. ..$ composition     : chr "data.frame"
##   .. .. .. ..$ remove_intercept: logi FALSE
##   .. .. ..$ y_var  : chr "close"
##   .. ..$ elapsed     :List of 1
##   .. .. ..$ elapsed: num NA
##   .. ..$ censor_probs: list()
##   .. ..- attr(*, "class")= chr [1:2] "_prophet_fit_impl" "model_fit"
##   ..$ :List of 4
##   .. ..$ pre    :List of 3
##   .. .. ..$ actions     :List of 1
##   .. .. .. ..$ recipe:List of 2
##   .. .. .. .. ..$ recipe   :List of 7
##   .. .. .. .. .. ..$ var_info    : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info   : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ steps       :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ columns: NULL
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180cb9ab108> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_mA7me"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ template    : tibble [2,235 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ levels      : NULL
##   .. .. .. .. .. ..$ retained    : logi NA
##   .. .. .. .. .. ..$ requirements:List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ blueprint:List of 8
##   .. .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. .. ..$ ptypes            : NULL
##   .. .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. .. ..$ recipe            : NULL
##   .. .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_recipe" "action_pre" "action"
##   .. .. ..$ mold        :List of 4
##   .. .. .. ..$ predictors: tibble [2,979 × 17] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ time          : num [1:2979] 15307 15308 15309 15310 15313 ...
##   .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. ..$ outcomes  : tibble [2,979 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ close: num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ blueprint :List of 8
##   .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. ..$ ptypes            :List of 2
##   .. .. .. .. .. ..$ predictors: tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time: 'Date' num(0) 
##   .. .. .. .. .. ..$ outcomes  : tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ close: num(0) 
##   .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. ..$ recipe            :List of 8
##   .. .. .. .. .. ..$ var_info      : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info     : tibble [18 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "close" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:18] "predictor" "outcome" "predictor" "predictor" ...
##   .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. ..$ steps         :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ columns: Named chr "time"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180cb9ab108> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_mA7me"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ retained      : logi FALSE
##   .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..$ tr_info       :'data.frame':    1 obs. of  2 variables:
##   .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. ..$ orig_lvls     :List of 2
##   .. .. .. .. .. .. ..$ time :List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ close:List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. ..$ last_term_info: gropd_df [29 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. ..$ type    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr "outcome"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. ..$ source  : chr [1:29] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. .. ..$ number  : num [1:29] 4 4 1 4 4 1 1 4 4 4 ...
##   .. .. .. .. .. .. ..$ skip    : logi [1:29] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. ..- attr(*, "groups")= tibble [29 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:29] 
##   .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. ..$ : int 19
##   .. .. .. .. .. .. .. .. ..$ : int 20
##   .. .. .. .. .. .. .. .. ..$ : int 21
##   .. .. .. .. .. .. .. .. ..$ : int 22
##   .. .. .. .. .. .. .. .. ..$ : int 23
##   .. .. .. .. .. .. .. .. ..$ : int 24
##   .. .. .. .. .. .. .. .. ..$ : int 25
##   .. .. .. .. .. .. .. .. ..$ : int 26
##   .. .. .. .. .. .. .. .. ..$ : int 27
##   .. .. .. .. .. .. .. .. ..$ : int 28
##   .. .. .. .. .. .. .. .. ..$ : int 29
##   .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. ..$ extras    :List of 1
##   .. .. .. .. ..$ roles: NULL
##   .. .. ..$ case_weights: NULL
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_pre" "stage"
##   .. ..$ fit    :List of 2
##   .. .. ..$ actions:List of 1
##   .. .. .. ..$ model:List of 2
##   .. .. .. .. ..$ spec   :List of 7
##   .. .. .. .. .. ..$ args                 :List of 2
##   .. .. .. .. .. .. ..$ penalty: language ~0
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ mixture: language ~0
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. .. ..$ method               : NULL
##   .. .. .. .. .. ..$ engine               : chr "glmnet"
##   .. .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "linear_reg" "model_spec"
##   .. .. .. .. ..$ formula: NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_model" "action_fit" "action"
##   .. .. ..$ fit    :List of 6
##   .. .. .. ..$ lvl         : NULL
##   .. .. .. ..$ spec        :List of 8
##   .. .. .. .. ..$ args                 :List of 2
##   .. .. .. .. .. ..$ penalty: num 0
##   .. .. .. .. .. ..$ mixture: language ~0
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. ..$ method               :List of 3
##   .. .. .. .. .. ..$ libs: chr "glmnet"
##   .. .. .. .. .. ..$ fit :List of 5
##   .. .. .. .. .. .. ..$ interface: chr "matrix"
##   .. .. .. .. .. .. ..$ protect  : chr [1:3] "x" "y" "weights"
##   .. .. .. .. .. .. ..$ func     : Named chr [1:2] "glmnet" "glmnet"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. ..$ defaults :List of 1
##   .. .. .. .. .. .. .. ..$ family: chr "gaussian"
##   .. .. .. .. .. .. ..$ args     :List of 5
##   .. .. .. .. .. .. .. ..$ x      : language missing_arg()
##   .. .. .. .. .. .. .. ..$ y      : language missing_arg()
##   .. .. .. .. .. .. .. ..$ weights: language missing_arg()
##   .. .. .. .. .. .. .. ..$ alpha  : language ~0
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ family : chr "gaussian"
##   .. .. .. .. .. ..$ pred:List of 2
##   .. .. .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post:function (x, object)  
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 4
##   .. .. .. .. .. .. .. .. ..$ object: language object$fit
##   .. .. .. .. .. .. .. .. ..$ newx  : language as.matrix(new_data[, rownames(object$fit$beta), drop = FALSE])
##   .. .. .. .. .. .. .. .. ..$ type  : chr "response"
##   .. .. .. .. .. .. .. .. ..$ s     : language object$spec$args$penalty
##   .. .. .. .. .. .. ..$ raw    :List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object: language object$fit
##   .. .. .. .. .. .. .. .. ..$ newx  : language as.matrix(new_data)
##   .. .. .. .. ..$ engine               : chr "glmnet"
##   .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. ..$ defaults             :List of 1
##   .. .. .. .. .. ..$ family: chr "gaussian"
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "linear_reg" "model_spec"
##   .. .. .. ..$ fit         :List of 12
##   .. .. .. .. ..$ a0       : Named num [1:100] 7.14 7.59 7.63 7.67 7.72 ...
##   .. .. .. .. .. ..- attr(*, "names")= chr [1:100] "s0" "s1" "s2" "s3" ...
##   .. .. .. .. ..$ beta     :Formal class 'dgCMatrix' [package "Matrix"] with 6 slots
##   .. .. .. .. .. .. ..@ i       : int [1:1700] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. ..@ p       : int [1:101] 0 17 34 51 68 85 102 119 136 153 ...
##   .. .. .. .. .. .. ..@ Dim     : int [1:2] 17 100
##   .. .. .. .. .. .. ..@ Dimnames:List of 2
##   .. .. .. .. .. .. .. ..$ : chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. ..$ : chr [1:100] "s0" "s1" "s2" "s3" ...
##   .. .. .. .. .. .. ..@ x       : num [1:1700] -0.000000000000000000000000000000000000000060426649 -0.000000000000000000000000000000000000000000000699 -0.000000| __truncated__ ...
##   .. .. .. .. .. .. ..@ factors : list()
##   .. .. .. .. ..$ df       : int [1:100] 17 17 17 17 17 17 17 17 17 17 ...
##   .. .. .. .. ..$ dim      : int [1:2] 17 100
##   .. .. .. .. ..$ lambda   : num [1:100] 108.4 98.8 90 82 74.7 ...
##   .. .. .. .. ..$ dev.ratio: num [1:100] 0.000000000000000000000000000000000000192 0.001622689077473609201018867054244765313 0.001771123251411462710264155| __truncated__ ...
##   .. .. .. .. ..$ nulldev  : num 2377
##   .. .. .. .. ..$ npasses  : int 407
##   .. .. .. .. ..$ jerr     : int 0
##   .. .. .. .. ..$ offset   : logi FALSE
##   .. .. .. .. ..$ call     : language glmnet::glmnet(x = maybe_matrix(x), y = y, family = "gaussian", alpha = ~0)
##   .. .. .. .. ..$ nobs     : int 2979
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "elnet" "glmnet"
##   .. .. .. ..$ preproc     :List of 1
##   .. .. .. .. ..$ y_var: chr(0) 
##   .. .. .. ..$ elapsed     :List of 1
##   .. .. .. .. ..$ elapsed: num NA
##   .. .. .. ..$ censor_probs: list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "_elnet" "model_fit"
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_fit" "stage"
##   .. ..$ post   :List of 1
##   .. .. ..$ actions: Named list()
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_post" "stage"
##   .. ..$ trained: logi TRUE
##   .. ..- attr(*, "class")= chr "workflow"
##   ..$ :List of 4
##   .. ..$ pre    :List of 3
##   .. .. ..$ actions     :List of 1
##   .. .. .. ..$ recipe:List of 2
##   .. .. .. .. ..$ recipe   :List of 7
##   .. .. .. .. .. ..$ var_info    : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info   : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ steps       :List of 3
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ columns: NULL
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. ..$ template    : tibble [2,235 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ levels      : NULL
##   .. .. .. .. .. ..$ retained    : logi NA
##   .. .. .. .. .. ..$ requirements:List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ blueprint:List of 8
##   .. .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. .. ..$ ptypes            : NULL
##   .. .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. .. ..$ recipe            : NULL
##   .. .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_recipe" "action_pre" "action"
##   .. .. ..$ mold        :List of 4
##   .. .. .. ..$ predictors: tibble [2,979 × 17] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ time          : Date[1:2979], format: "2011-11-29" ...
##   .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. ..$ outcomes  : tibble [2,979 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ close: num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ blueprint :List of 8
##   .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. ..$ ptypes            :List of 2
##   .. .. .. .. .. ..$ predictors: tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time: 'Date' num(0) 
##   .. .. .. .. .. ..$ outcomes  : tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ close: num(0) 
##   .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. ..$ recipe            :List of 8
##   .. .. .. .. .. ..$ var_info      : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info     : tibble [18 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "close" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:18] "predictor" "outcome" "predictor" "predictor" ...
##   .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. ..$ steps         :List of 3
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ columns: Named chr "time"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. ..$ retained      : logi FALSE
##   .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..$ tr_info       :'data.frame':    1 obs. of  2 variables:
##   .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. ..$ orig_lvls     :List of 2
##   .. .. .. .. .. .. ..$ time :List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ close:List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. ..$ last_term_info: gropd_df [29 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. ..$ type    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr "outcome"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. ..$ source  : chr [1:29] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. .. ..$ number  : num [1:29] 3 3 1 3 3 1 1 3 3 3 ...
##   .. .. .. .. .. .. ..$ skip    : logi [1:29] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. ..- attr(*, "groups")= tibble [29 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:29] 
##   .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. ..$ : int 19
##   .. .. .. .. .. .. .. .. ..$ : int 20
##   .. .. .. .. .. .. .. .. ..$ : int 21
##   .. .. .. .. .. .. .. .. ..$ : int 22
##   .. .. .. .. .. .. .. .. ..$ : int 23
##   .. .. .. .. .. .. .. .. ..$ : int 24
##   .. .. .. .. .. .. .. .. ..$ : int 25
##   .. .. .. .. .. .. .. .. ..$ : int 26
##   .. .. .. .. .. .. .. .. ..$ : int 27
##   .. .. .. .. .. .. .. .. ..$ : int 28
##   .. .. .. .. .. .. .. .. ..$ : int 29
##   .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. ..$ extras    :List of 1
##   .. .. .. .. ..$ roles: NULL
##   .. .. ..$ case_weights: NULL
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_pre" "stage"
##   .. ..$ fit    :List of 2
##   .. .. ..$ actions:List of 1
##   .. .. .. ..$ model:List of 2
##   .. .. .. .. ..$ spec   :List of 7
##   .. .. .. .. .. ..$ args                 :List of 4
##   .. .. .. .. .. .. ..$ cost        : language ~10
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ degree      : language ~1
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ scale_factor: language ~1
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ margin      : language ~0.1
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. .. ..$ method               : NULL
##   .. .. .. .. .. ..$ engine               : chr "kernlab"
##   .. .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "svm_poly" "model_spec"
##   .. .. .. .. ..$ formula: NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_model" "action_fit" "action"
##   .. .. ..$ fit    :List of 6
##   .. .. .. ..$ lvl         : NULL
##   .. .. .. ..$ spec        :List of 8
##   .. .. .. .. ..$ args                 :List of 4
##   .. .. .. .. .. ..$ cost        : language ~10
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ degree      : language ~1
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ scale_factor: language ~1
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ margin      : language ~0.1
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. ..$ method               :List of 3
##   .. .. .. .. .. ..$ libs: chr "kernlab"
##   .. .. .. .. .. ..$ fit :List of 6
##   .. .. .. .. .. .. ..$ interface: chr "formula"
##   .. .. .. .. .. .. ..$ data     : Named chr [1:2] "x" "data"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "formula" "data"
##   .. .. .. .. .. .. ..$ protect  : chr [1:2] "x" "data"
##   .. .. .. .. .. .. ..$ func     : Named chr [1:2] "kernlab" "ksvm"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. ..$ defaults :List of 1
##   .. .. .. .. .. .. .. ..$ kernel: chr "polydot"
##   .. .. .. .. .. .. ..$ args     :List of 6
##   .. .. .. .. .. .. .. ..$ x      : language missing_arg()
##   .. .. .. .. .. .. .. ..$ data   : language missing_arg()
##   .. .. .. .. .. .. .. ..$ C      : language ~10
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ epsilon: language ~0.1
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ kernel : chr "polydot"
##   .. .. .. .. .. .. .. ..$ kpar   : language list(degree = ~1, scale = ~1)
##   .. .. .. .. .. ..$ pred:List of 2
##   .. .. .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post:function (results, object)  
##   .. .. .. .. .. .. .. ..$ func: Named chr [1:2] "kernlab" "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 3
##   .. .. .. .. .. .. .. .. ..$ object : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata: symbol new_data
##   .. .. .. .. .. .. .. .. ..$ type   : chr "response"
##   .. .. .. .. .. .. ..$ raw    :List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr [1:2] "kernlab" "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata: symbol new_data
##   .. .. .. .. ..$ engine               : chr "kernlab"
##   .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. ..$ defaults             :List of 1
##   .. .. .. .. .. ..$ kernel: chr "polydot"
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "svm_poly" "model_spec"
##   .. .. .. ..$ fit         :Formal class 'ksvm' [package "kernlab"] with 24 slots
##   .. .. .. .. .. ..@ param     :List of 2
##   .. .. .. .. .. .. ..$ epsilon: num 0.1
##   .. .. .. .. .. .. ..$ C      : num 10
##   .. .. .. .. .. ..@ scaling   :List of 3
##   .. .. .. .. .. .. ..$ scaled : logi [1:17] TRUE TRUE TRUE TRUE TRUE TRUE ...
##   .. .. .. .. .. .. ..$ x.scale:List of 2
##   .. .. .. .. .. .. .. ..$ scaled:center: Named num [1:17] 17477.6 1510064599.4 2017.35 1.51 2.51 ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. ..$ scaled:scale : Named num [1:17] 1249.68 107972612.19 3.42 0.5 1.12 ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. ..$ y.scale:List of 2
##   .. .. .. .. .. .. .. ..$ scaled:center: num 7.14
##   .. .. .. .. .. .. .. ..$ scaled:scale : num 0.893
##   .. .. .. .. .. ..@ coef      : num [1:2678] -10 -10 -10 -10 -10 -10 -10 -10 -10 -10 ...
##   .. .. .. .. .. ..@ alphaindex: int [1:2678] 1 2 3 4 5 6 7 8 9 10 ...
##   .. .. .. .. .. ..@ b         : num -0.128
##   .. .. .. .. .. ..@ obj       : num -20175
##   .. .. .. .. .. ..@ SVindex   : int [1:2678] 1 2 3 4 5 6 7 8 9 10 ...
##   .. .. .. .. .. ..@ nSV       : int 2678
##   .. .. .. .. .. ..@ prior     :List of 1
##   .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. ..@ prob.model:List of 1
##   .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. ..@ alpha     : num [1:2678] -10 -10 -10 -10 -10 -10 -10 -10 -10 -10 ...
##   .. .. .. .. .. ..@ type      : chr "eps-svr"
##   .. .. .. .. .. ..@ kernelf   :Formal class 'polykernel' [package "kernlab"] with 2 slots
##   .. .. .. .. .. .. .. ..@ .Data:function (x, y = NULL)  
##   .. .. .. .. .. .. .. ..@ kpar :List of 3
##   .. .. .. .. .. .. .. .. ..$ degree: num 1
##   .. .. .. .. .. .. .. .. ..$ scale : num 1
##   .. .. .. .. .. .. .. .. ..$ offset: num 1
##   .. .. .. .. .. ..@ kpar      : list()
##   .. .. .. .. .. ..@ xmatrix   : num [1:2678, 1:17] -1.74 -1.74 -1.74 -1.73 -1.73 ...
##   .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. ..$ : chr [1:2678] "1" "2" "3" "4" ...
##   .. .. .. .. .. .. .. ..$ : chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. ..@ ymatrix   : num [1:2979] -0.293 -0.293 -0.816 -1.104 -1.104 ...
##   .. .. .. .. .. ..@ fitted    : num [1:2979, 1] 0.911 0.909 0.901 0.899 0.928 ...
##   .. .. .. .. .. ..@ lev       : num [1:2385] -2.38 -2.3 -2.3 -2.29 -2.28 ...
##   .. .. .. .. .. ..@ nclass    : int 2385
##   .. .. .. .. .. ..@ error     : num 1.04
##   .. .. .. .. .. ..@ cross     : num -1
##   .. .. .. .. .. ..@ n.action  :function (object, ...)  
##   .. .. .. .. .. ..@ terms     :Classes 'terms', 'formula'  language ..y ~ time + time_index.num + time_year + time_half + time_quarter + time_month +      time_day + time_wday + tim| __truncated__ ...
##   .. .. .. .. .. .. .. ..- attr(*, "variables")= language list(..y, time, time_index.num, time_year, time_half, time_quarter, time_month,      time_day, time_wday, time_md| __truncated__ ...
##   .. .. .. .. .. .. .. ..- attr(*, "factors")= int [1:18, 1:17] 0 1 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. ..$ : chr [1:18] "..y" "time" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. .. .. .. ..$ : chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. ..- attr(*, "term.labels")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. ..- attr(*, "order")= int [1:17] 1 1 1 1 1 1 1 1 1 1 ...
##   .. .. .. .. .. .. .. ..- attr(*, "intercept")= num 0
##   .. .. .. .. .. .. .. ..- attr(*, "response")= int 1
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180daa6bfc8> 
##   .. .. .. .. .. .. .. ..- attr(*, "predvars")= language list(..y, time, time_index.num, time_year, time_half, time_quarter, time_month,      time_day, time_wday, time_md| __truncated__ ...
##   .. .. .. .. .. .. .. ..- attr(*, "dataClasses")= Named chr [1:18] "numeric" "other" "numeric" "numeric" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:18] "..y" "time" "time_index.num" "time_year" ...
##   .. .. .. .. .. ..@ kcall     : language .local(x = x, data = ..1, C = ..2, epsilon = ..3, kernel = "polydot", kpar = ..5)
##   .. .. .. ..$ preproc     :List of 2
##   .. .. .. .. ..$ x_var: chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. ..$ y_var: chr "close"
##   .. .. .. ..$ elapsed     :List of 1
##   .. .. .. .. ..$ elapsed: num NA
##   .. .. .. ..$ censor_probs: list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "_ksvm" "model_fit"
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_fit" "stage"
##   .. ..$ post   :List of 1
##   .. .. ..$ actions: Named list()
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_post" "stage"
##   .. ..$ trained: logi TRUE
##   .. ..- attr(*, "class")= chr "workflow"
##   ..$ :List of 4
##   .. ..$ pre    :List of 3
##   .. .. ..$ actions     :List of 1
##   .. .. .. ..$ recipe:List of 2
##   .. .. .. .. ..$ recipe   :List of 7
##   .. .. .. .. .. ..$ var_info    : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info   : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ steps       :List of 3
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ columns: NULL
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. ..$ template    : tibble [2,235 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ levels      : NULL
##   .. .. .. .. .. ..$ retained    : logi NA
##   .. .. .. .. .. ..$ requirements:List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ blueprint:List of 8
##   .. .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. .. ..$ ptypes            : NULL
##   .. .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. .. ..$ recipe            : NULL
##   .. .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_recipe" "action_pre" "action"
##   .. .. ..$ mold        :List of 4
##   .. .. .. ..$ predictors: tibble [2,979 × 17] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ time          : Date[1:2979], format: "2011-11-29" ...
##   .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. ..$ outcomes  : tibble [2,979 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ close: num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ blueprint :List of 8
##   .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. ..$ ptypes            :List of 2
##   .. .. .. .. .. ..$ predictors: tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time: 'Date' num(0) 
##   .. .. .. .. .. ..$ outcomes  : tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ close: num(0) 
##   .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. ..$ recipe            :List of 8
##   .. .. .. .. .. ..$ var_info      : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info     : tibble [18 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "close" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:18] "predictor" "outcome" "predictor" "predictor" ...
##   .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. ..$ steps         :List of 3
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ columns: Named chr "time"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. ..$ retained      : logi FALSE
##   .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..$ tr_info       :'data.frame':    1 obs. of  2 variables:
##   .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. ..$ orig_lvls     :List of 2
##   .. .. .. .. .. .. ..$ time :List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ close:List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. ..$ last_term_info: gropd_df [29 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. ..$ type    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr "outcome"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. ..$ source  : chr [1:29] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. .. ..$ number  : num [1:29] 3 3 1 3 3 1 1 3 3 3 ...
##   .. .. .. .. .. .. ..$ skip    : logi [1:29] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. ..- attr(*, "groups")= tibble [29 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:29] 
##   .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. ..$ : int 19
##   .. .. .. .. .. .. .. .. ..$ : int 20
##   .. .. .. .. .. .. .. .. ..$ : int 21
##   .. .. .. .. .. .. .. .. ..$ : int 22
##   .. .. .. .. .. .. .. .. ..$ : int 23
##   .. .. .. .. .. .. .. .. ..$ : int 24
##   .. .. .. .. .. .. .. .. ..$ : int 25
##   .. .. .. .. .. .. .. .. ..$ : int 26
##   .. .. .. .. .. .. .. .. ..$ : int 27
##   .. .. .. .. .. .. .. .. ..$ : int 28
##   .. .. .. .. .. .. .. .. ..$ : int 29
##   .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. ..$ extras    :List of 1
##   .. .. .. .. ..$ roles: NULL
##   .. .. ..$ case_weights: NULL
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_pre" "stage"
##   .. ..$ fit    :List of 2
##   .. .. ..$ actions:List of 1
##   .. .. .. ..$ model:List of 2
##   .. .. .. .. ..$ spec   :List of 7
##   .. .. .. .. .. ..$ args                 :List of 3
##   .. .. .. .. .. .. ..$ cost     : language ~1
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ rbf_sigma: language ~0.01
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ margin   : language ~0.1
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. .. ..$ method               : NULL
##   .. .. .. .. .. ..$ engine               : chr "kernlab"
##   .. .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "svm_rbf" "model_spec"
##   .. .. .. .. ..$ formula: NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_model" "action_fit" "action"
##   .. .. ..$ fit    :List of 6
##   .. .. .. ..$ lvl         : NULL
##   .. .. .. ..$ spec        :List of 8
##   .. .. .. .. ..$ args                 :List of 3
##   .. .. .. .. .. ..$ cost     : language ~1
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ rbf_sigma: language ~0.01
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ margin   : language ~0.1
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. ..$ method               :List of 3
##   .. .. .. .. .. ..$ libs: chr "kernlab"
##   .. .. .. .. .. ..$ fit :List of 6
##   .. .. .. .. .. .. ..$ interface: chr "formula"
##   .. .. .. .. .. .. ..$ data     : Named chr [1:2] "x" "data"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "formula" "data"
##   .. .. .. .. .. .. ..$ protect  : chr [1:2] "x" "data"
##   .. .. .. .. .. .. ..$ func     : Named chr [1:2] "kernlab" "ksvm"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. ..$ defaults :List of 1
##   .. .. .. .. .. .. .. ..$ kernel: chr "rbfdot"
##   .. .. .. .. .. .. ..$ args     :List of 6
##   .. .. .. .. .. .. .. ..$ x      : language missing_arg()
##   .. .. .. .. .. .. .. ..$ data   : language missing_arg()
##   .. .. .. .. .. .. .. ..$ C      : language ~1
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ epsilon: language ~0.1
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ kernel : chr "rbfdot"
##   .. .. .. .. .. .. .. ..$ kpar   : language list(sigma = ~0.01)
##   .. .. .. .. .. ..$ pred:List of 2
##   .. .. .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post:function (results, object)  
##   .. .. .. .. .. .. .. ..$ func: Named chr [1:2] "kernlab" "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 3
##   .. .. .. .. .. .. .. .. ..$ object : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata: symbol new_data
##   .. .. .. .. .. .. .. .. ..$ type   : chr "response"
##   .. .. .. .. .. .. ..$ raw    :List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr [1:2] "kernlab" "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata: symbol new_data
##   .. .. .. .. ..$ engine               : chr "kernlab"
##   .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. ..$ defaults             :List of 1
##   .. .. .. .. .. ..$ kernel: chr "rbfdot"
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "svm_rbf" "model_spec"
##   .. .. .. ..$ fit         :Formal class 'ksvm' [package "kernlab"] with 24 slots
##   .. .. .. .. .. ..@ param     :List of 2
##   .. .. .. .. .. .. ..$ epsilon: num 0.1
##   .. .. .. .. .. .. ..$ C      : num 1
##   .. .. .. .. .. ..@ scaling   :List of 3
##   .. .. .. .. .. .. ..$ scaled : logi [1:17] TRUE TRUE TRUE TRUE TRUE TRUE ...
##   .. .. .. .. .. .. ..$ x.scale:List of 2
##   .. .. .. .. .. .. .. ..$ scaled:center: Named num [1:17] 17477.6 1510064599.4 2017.35 1.51 2.51 ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. ..$ scaled:scale : Named num [1:17] 1249.68 107972612.19 3.42 0.5 1.12 ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. ..$ y.scale:List of 2
##   .. .. .. .. .. .. .. ..$ scaled:center: num 7.14
##   .. .. .. .. .. .. .. ..$ scaled:scale : num 0.893
##   .. .. .. .. .. ..@ coef      : num [1:2714] -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
##   .. .. .. .. .. ..@ alphaindex: int [1:2714] 1 2 3 4 5 6 7 8 9 10 ...
##   .. .. .. .. .. ..@ b         : num 2.82
##   .. .. .. .. .. ..@ obj       : num -1858
##   .. .. .. .. .. ..@ SVindex   : int [1:2714] 1 2 3 4 5 6 7 8 9 10 ...
##   .. .. .. .. .. ..@ nSV       : int 2714
##   .. .. .. .. .. ..@ prior     :List of 1
##   .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. ..@ prob.model:List of 1
##   .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. ..@ alpha     : num [1:2714] -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
##   .. .. .. .. .. ..@ type      : chr "eps-svr"
##   .. .. .. .. .. ..@ kernelf   :Formal class 'rbfkernel' [package "kernlab"] with 2 slots
##   .. .. .. .. .. .. .. ..@ .Data:function (x, y = NULL)  
##   .. .. .. .. .. .. .. ..@ kpar :List of 1
##   .. .. .. .. .. .. .. .. ..$ sigma: num 0.01
##   .. .. .. .. .. ..@ kpar      : list()
##   .. .. .. .. .. ..@ xmatrix   : num [1:2714, 1:17] -1.74 -1.74 -1.74 -1.73 -1.73 ...
##   .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. ..$ : chr [1:2714] "1" "2" "3" "4" ...
##   .. .. .. .. .. .. .. ..$ : chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. ..@ ymatrix   : num [1:2979] -0.293 -0.293 -0.816 -1.104 -1.104 ...
##   .. .. .. .. .. ..@ fitted    : num [1:2979, 1] 0.0594 0.046 0.1634 0.1487 0.2358 ...
##   .. .. .. .. .. ..@ lev       : num [1:2385] -2.38 -2.3 -2.3 -2.29 -2.28 ...
##   .. .. .. .. .. ..@ nclass    : int 2385
##   .. .. .. .. .. ..@ error     : num 0.747
##   .. .. .. .. .. ..@ cross     : num -1
##   .. .. .. .. .. ..@ n.action  :function (object, ...)  
##   .. .. .. .. .. ..@ terms     :Classes 'terms', 'formula'  language ..y ~ time + time_index.num + time_year + time_half + time_quarter + time_month +      time_day + time_wday + tim| __truncated__ ...
##   .. .. .. .. .. .. .. ..- attr(*, "variables")= language list(..y, time, time_index.num, time_year, time_half, time_quarter, time_month,      time_day, time_wday, time_md| __truncated__ ...
##   .. .. .. .. .. .. .. ..- attr(*, "factors")= int [1:18, 1:17] 0 1 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. ..$ : chr [1:18] "..y" "time" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. .. .. .. ..$ : chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. ..- attr(*, "term.labels")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. ..- attr(*, "order")= int [1:17] 1 1 1 1 1 1 1 1 1 1 ...
##   .. .. .. .. .. .. .. ..- attr(*, "intercept")= num 0
##   .. .. .. .. .. .. .. ..- attr(*, "response")= int 1
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180dbeb9648> 
##   .. .. .. .. .. .. .. ..- attr(*, "predvars")= language list(..y, time, time_index.num, time_year, time_half, time_quarter, time_month,      time_day, time_wday, time_md| __truncated__ ...
##   .. .. .. .. .. .. .. ..- attr(*, "dataClasses")= Named chr [1:18] "numeric" "other" "numeric" "numeric" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:18] "..y" "time" "time_index.num" "time_year" ...
##   .. .. .. .. .. ..@ kcall     : language .local(x = x, data = ..1, C = ..2, epsilon = ..3, kernel = "rbfdot", kpar = ..5)
##   .. .. .. ..$ preproc     :List of 2
##   .. .. .. .. ..$ x_var: chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. ..$ y_var: chr "close"
##   .. .. .. ..$ elapsed     :List of 1
##   .. .. .. .. ..$ elapsed: num NA
##   .. .. .. ..$ censor_probs: list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "_ksvm" "model_fit"
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_fit" "stage"
##   .. ..$ post   :List of 1
##   .. .. ..$ actions: Named list()
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_post" "stage"
##   .. ..$ trained: logi TRUE
##   .. ..- attr(*, "class")= chr "workflow"
##   ..$ :List of 4
##   .. ..$ pre    :List of 3
##   .. .. ..$ actions     :List of 1
##   .. .. .. ..$ recipe:List of 2
##   .. .. .. .. ..$ recipe   :List of 7
##   .. .. .. .. .. ..$ var_info    : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info   : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ steps       :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ columns: NULL
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180db71d278> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_EoYnc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ template    : tibble [2,235 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ levels      : NULL
##   .. .. .. .. .. ..$ retained    : logi NA
##   .. .. .. .. .. ..$ requirements:List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ blueprint:List of 8
##   .. .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. .. ..$ ptypes            : NULL
##   .. .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. .. ..$ recipe            : NULL
##   .. .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_recipe" "action_pre" "action"
##   .. .. ..$ mold        :List of 4
##   .. .. .. ..$ predictors: tibble [2,979 × 17] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ time          : num [1:2979] 15307 15308 15309 15310 15313 ...
##   .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. ..$ outcomes  : tibble [2,979 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ close: num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ blueprint :List of 8
##   .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. ..$ ptypes            :List of 2
##   .. .. .. .. .. ..$ predictors: tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time: 'Date' num(0) 
##   .. .. .. .. .. ..$ outcomes  : tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ close: num(0) 
##   .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. ..$ recipe            :List of 8
##   .. .. .. .. .. ..$ var_info      : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info     : tibble [18 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "close" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:18] "predictor" "outcome" "predictor" "predictor" ...
##   .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. ..$ steps         :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ columns: Named chr "time"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180db71d278> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_EoYnc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ retained      : logi FALSE
##   .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..$ tr_info       :'data.frame':    1 obs. of  2 variables:
##   .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. ..$ orig_lvls     :List of 2
##   .. .. .. .. .. .. ..$ time :List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ close:List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. ..$ last_term_info: gropd_df [29 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. ..$ type    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr "outcome"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. ..$ source  : chr [1:29] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. .. ..$ number  : num [1:29] 4 4 1 4 4 1 1 4 4 4 ...
##   .. .. .. .. .. .. ..$ skip    : logi [1:29] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. ..- attr(*, "groups")= tibble [29 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:29] 
##   .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. ..$ : int 19
##   .. .. .. .. .. .. .. .. ..$ : int 20
##   .. .. .. .. .. .. .. .. ..$ : int 21
##   .. .. .. .. .. .. .. .. ..$ : int 22
##   .. .. .. .. .. .. .. .. ..$ : int 23
##   .. .. .. .. .. .. .. .. ..$ : int 24
##   .. .. .. .. .. .. .. .. ..$ : int 25
##   .. .. .. .. .. .. .. .. ..$ : int 26
##   .. .. .. .. .. .. .. .. ..$ : int 27
##   .. .. .. .. .. .. .. .. ..$ : int 28
##   .. .. .. .. .. .. .. .. ..$ : int 29
##   .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. ..$ extras    :List of 1
##   .. .. .. .. ..$ roles: NULL
##   .. .. ..$ case_weights: NULL
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_pre" "stage"
##   .. ..$ fit    :List of 2
##   .. .. ..$ actions:List of 1
##   .. .. .. ..$ model:List of 2
##   .. .. .. .. ..$ spec   :List of 7
##   .. .. .. .. .. ..$ args                 :List of 3
##   .. .. .. .. .. .. ..$ neighbors  : language ~50
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ weight_func: language ~"optimal"
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ dist_power : language ~10
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. .. ..$ method               : NULL
##   .. .. .. .. .. ..$ engine               : chr "kknn"
##   .. .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "nearest_neighbor" "model_spec"
##   .. .. .. .. ..$ formula: NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_model" "action_fit" "action"
##   .. .. ..$ fit    :List of 6
##   .. .. .. ..$ lvl         : NULL
##   .. .. .. ..$ spec        :List of 7
##   .. .. .. .. ..$ args                 :List of 3
##   .. .. .. .. .. ..$ neighbors  : language ~50
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ weight_func: language ~"optimal"
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ dist_power : language ~10
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. ..$ method               :List of 3
##   .. .. .. .. .. ..$ libs: chr "kknn"
##   .. .. .. .. .. ..$ fit :List of 5
##   .. .. .. .. .. .. ..$ interface: chr "formula"
##   .. .. .. .. .. .. ..$ protect  : chr [1:2] "formula" "data"
##   .. .. .. .. .. .. ..$ func     : Named chr [1:2] "kknn" "train.kknn"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. ..$ defaults : list()
##   .. .. .. .. .. .. ..$ args     :List of 5
##   .. .. .. .. .. .. .. ..$ formula : language missing_arg()
##   .. .. .. .. .. .. .. ..$ data    : language missing_arg()
##   .. .. .. .. .. .. .. ..$ ks      : language min_rows(50, data, 5)
##   .. .. .. .. .. .. .. ..$ kernel  : language ~"optimal"
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ distance: language ~10
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ pred:List of 2
##   .. .. .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. .. .. ..$ pre :function (x, object)  
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 3
##   .. .. .. .. .. .. .. .. ..$ object : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata: symbol new_data
##   .. .. .. .. .. .. .. .. ..$ type   : chr "raw"
##   .. .. .. .. .. .. ..$ raw    :List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata: symbol new_data
##   .. .. .. .. ..$ engine               : chr "kknn"
##   .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "nearest_neighbor" "model_spec"
##   .. .. .. ..$ fit         :List of 10
##   .. .. .. .. ..$ MISCLASS       : logi [1, 1] NA
##   .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. ..$ : chr "50"
##   .. .. .. .. .. .. ..$ : chr "optimal"
##   .. .. .. .. ..$ MEAN.ABS       : num [1, 1] 0.684
##   .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. ..$ : chr "50"
##   .. .. .. .. .. .. ..$ : chr "optimal"
##   .. .. .. .. ..$ MEAN.SQU       : num [1, 1] 0.705
##   .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. ..$ : chr "50"
##   .. .. .. .. .. .. ..$ : chr "optimal"
##   .. .. .. .. ..$ fitted.values  :List of 1
##   .. .. .. .. .. ..$ : num [1:2979] 7.31 7.18 7.67 7.65 7.25 ...
##   .. .. .. .. .. .. ..- attr(*, "kernel")= chr "optimal"
##   .. .. .. .. .. .. ..- attr(*, "k")= int 50
##   .. .. .. .. ..$ best.parameters:List of 2
##   .. .. .. .. .. ..$ kernel: chr "optimal"
##   .. .. .. .. .. ..$ k     : int 50
##   .. .. .. .. ..$ response       : chr "continuous"
##   .. .. .. .. ..$ distance       : num 10
##   .. .. .. .. ..$ call           : language kknn::train.kknn(formula = ..y ~ ., data = data, ks = min_rows(50, data,      5), distance = ~10, kernel = ~"optimal")
##   .. .. .. .. ..$ terms          :Classes 'terms', 'formula'  language ..y ~ time + time_index.num + time_year + time_half + time_quarter + time_month +      time_day + time_wday + tim| __truncated__ ...
##   .. .. .. .. .. .. ..- attr(*, "variables")= language list(..y, time, time_index.num, time_year, time_half, time_quarter, time_month,      time_day, time_wday, time_md| __truncated__ ...
##   .. .. .. .. .. .. ..- attr(*, "factors")= int [1:18, 1:17] 0 1 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. ..$ : chr [1:18] "..y" "time" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. .. .. ..$ : chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. ..- attr(*, "term.labels")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. ..- attr(*, "order")= int [1:17] 1 1 1 1 1 1 1 1 1 1 ...
##   .. .. .. .. .. .. ..- attr(*, "intercept")= int 1
##   .. .. .. .. .. .. ..- attr(*, "response")= int 1
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180cb7a5a88> 
##   .. .. .. .. .. .. ..- attr(*, "predvars")= language list(..y, time, time_index.num, time_year, time_half, time_quarter, time_month,      time_day, time_wday, time_md| __truncated__ ...
##   .. .. .. .. .. .. ..- attr(*, "dataClasses")= Named chr [1:18] "numeric" "numeric" "numeric" "numeric" ...
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:18] "..y" "time" "time_index.num" "time_year" ...
##   .. .. .. .. ..$ data           : tibble [2,979 × 18] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. ..$ time          : num [1:2979] 15307 15308 15309 15310 15313 ...
##   .. .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. .. .. ..$ ..y           : num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "train.kknn" "kknn"
##   .. .. .. ..$ preproc     :List of 2
##   .. .. .. .. ..$ x_var: chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. ..$ y_var: chr "close"
##   .. .. .. ..$ elapsed     :List of 1
##   .. .. .. .. ..$ elapsed: num NA
##   .. .. .. ..$ censor_probs: list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "_train.kknn" "model_fit"
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_fit" "stage"
##   .. ..$ post   :List of 1
##   .. .. ..$ actions: Named list()
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_post" "stage"
##   .. ..$ trained: logi TRUE
##   .. ..- attr(*, "class")= chr "workflow"
##   ..$ :List of 4
##   .. ..$ pre    :List of 3
##   .. .. ..$ actions     :List of 1
##   .. .. .. ..$ recipe:List of 2
##   .. .. .. .. ..$ recipe   :List of 7
##   .. .. .. .. .. ..$ var_info    : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info   : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ steps       :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ columns: NULL
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180dfda0c78> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_EoYnc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ template    : tibble [2,235 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ levels      : NULL
##   .. .. .. .. .. ..$ retained    : logi NA
##   .. .. .. .. .. ..$ requirements:List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ blueprint:List of 8
##   .. .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. .. ..$ ptypes            : NULL
##   .. .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. .. ..$ recipe            : NULL
##   .. .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_recipe" "action_pre" "action"
##   .. .. ..$ mold        :List of 4
##   .. .. .. ..$ predictors: tibble [2,979 × 17] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ time          : num [1:2979] 15307 15308 15309 15310 15313 ...
##   .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. ..$ outcomes  : tibble [2,979 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ close: num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ blueprint :List of 8
##   .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. ..$ ptypes            :List of 2
##   .. .. .. .. .. ..$ predictors: tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time: 'Date' num(0) 
##   .. .. .. .. .. ..$ outcomes  : tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ close: num(0) 
##   .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. ..$ recipe            :List of 8
##   .. .. .. .. .. ..$ var_info      : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info     : tibble [18 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "close" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:18] "predictor" "outcome" "predictor" "predictor" ...
##   .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. ..$ steps         :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ columns: Named chr "time"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180dfda0c78> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_EoYnc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ retained      : logi FALSE
##   .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..$ tr_info       :'data.frame':    1 obs. of  2 variables:
##   .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. ..$ orig_lvls     :List of 2
##   .. .. .. .. .. .. ..$ time :List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ close:List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. ..$ last_term_info: gropd_df [29 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. ..$ type    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr "outcome"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. ..$ source  : chr [1:29] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. .. ..$ number  : num [1:29] 4 4 1 4 4 1 1 4 4 4 ...
##   .. .. .. .. .. .. ..$ skip    : logi [1:29] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. ..- attr(*, "groups")= tibble [29 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:29] 
##   .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. ..$ : int 19
##   .. .. .. .. .. .. .. .. ..$ : int 20
##   .. .. .. .. .. .. .. .. ..$ : int 21
##   .. .. .. .. .. .. .. .. ..$ : int 22
##   .. .. .. .. .. .. .. .. ..$ : int 23
##   .. .. .. .. .. .. .. .. ..$ : int 24
##   .. .. .. .. .. .. .. .. ..$ : int 25
##   .. .. .. .. .. .. .. .. ..$ : int 26
##   .. .. .. .. .. .. .. .. ..$ : int 27
##   .. .. .. .. .. .. .. .. ..$ : int 28
##   .. .. .. .. .. .. .. .. ..$ : int 29
##   .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. ..$ extras    :List of 1
##   .. .. .. .. ..$ roles: NULL
##   .. .. ..$ case_weights: NULL
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_pre" "stage"
##   .. ..$ fit    :List of 2
##   .. .. ..$ actions:List of 1
##   .. .. .. ..$ model:List of 2
##   .. .. .. .. ..$ spec   :List of 7
##   .. .. .. .. .. ..$ args                 :List of 3
##   .. .. .. .. .. .. ..$ mtry : language ~25
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ trees: language ~1000
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ min_n: language ~25
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. .. ..$ method               : NULL
##   .. .. .. .. .. ..$ engine               : chr "randomForest"
##   .. .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "rand_forest" "model_spec"
##   .. .. .. .. ..$ formula: NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_model" "action_fit" "action"
##   .. .. ..$ fit    :List of 6
##   .. .. .. ..$ lvl         : NULL
##   .. .. .. ..$ spec        :List of 7
##   .. .. .. .. ..$ args                 :List of 3
##   .. .. .. .. .. ..$ mtry : language ~25
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ trees: language ~1000
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ min_n: language ~25
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. ..$ method               :List of 3
##   .. .. .. .. .. ..$ libs: chr "randomForest"
##   .. .. .. .. .. ..$ fit :List of 5
##   .. .. .. .. .. .. ..$ interface: chr "data.frame"
##   .. .. .. .. .. .. ..$ protect  : chr [1:2] "x" "y"
##   .. .. .. .. .. .. ..$ func     : Named chr [1:2] "randomForest" "randomForest"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. ..$ defaults : list()
##   .. .. .. .. .. .. ..$ args     :List of 5
##   .. .. .. .. .. .. .. ..$ x       : language missing_arg()
##   .. .. .. .. .. .. .. ..$ y       : language missing_arg()
##   .. .. .. .. .. .. .. ..$ mtry    : language min_cols(~25, x)
##   .. .. .. .. .. .. .. ..$ ntree   : language ~1000
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ nodesize: language min_rows(~25, x)
##   .. .. .. .. .. ..$ pred:List of 2
##   .. .. .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata: symbol new_data
##   .. .. .. .. .. .. ..$ raw    :List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata: symbol new_data
##   .. .. .. .. ..$ engine               : chr "randomForest"
##   .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "rand_forest" "model_spec"
##   .. .. .. ..$ fit         :List of 17
##   .. .. .. .. ..$ call           : language randomForest(x = maybe_data_frame(x), y = y, ntree = ~1000, mtry = min_cols(~25,      x), nodesize = min_rows(~25, x))
##   .. .. .. .. ..$ type           : chr "regression"
##   .. .. .. .. ..$ predicted      : Named num [1:2979] 6.5 6.5 6.61 6.43 6.16 ...
##   .. .. .. .. .. ..- attr(*, "names")= chr [1:2979] "1" "2" "3" "4" ...
##   .. .. .. .. ..$ mse            : num [1:1000] 0.0176 0.0171 0.0163 0.0154 0.0146 ...
##   .. .. .. .. ..$ rsq            : num [1:1000] 0.978 0.979 0.98 0.981 0.982 ...
##   .. .. .. .. ..$ oob.times      : int [1:2979] 393 344 345 369 370 368 366 375 373 342 ...
##   .. .. .. .. ..$ importance     : num [1:17, 1] 1068.5515 1052.1295 13.7522 0.0778 0.4731 ...
##   .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. ..$ : chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. ..$ : chr "IncNodePurity"
##   .. .. .. .. ..$ importanceSD   : NULL
##   .. .. .. .. ..$ localImportance: NULL
##   .. .. .. .. ..$ proximity      : NULL
##   .. .. .. .. ..$ ntree          : num 1000
##   .. .. .. .. ..$ mtry           : num 17
##   .. .. .. .. ..$ forest         :List of 11
##   .. .. .. .. .. ..$ ndbigtree    : int [1:1000] 431 453 415 421 427 435 427 421 429 449 ...
##   .. .. .. .. .. ..$ nodestatus   : int [1:485, 1:1000] -3 -3 -3 -3 -3 -3 -3 -3 -3 -3 ...
##   .. .. .. .. .. ..$ leftDaughter : int [1:485, 1:1000] 2 4 6 8 10 12 14 16 18 20 ...
##   .. .. .. .. .. ..$ rightDaughter: int [1:485, 1:1000] 3 5 7 9 11 13 15 17 19 21 ...
##   .. .. .. .. .. ..$ nodepred     : num [1:485, 1:1000] 7.13 5.8 7.33 6 5.53 ...
##   .. .. .. .. .. ..$ bestvar      : int [1:485, 1:1000] 2 1 1 11 1 11 1 1 10 6 ...
##   .. .. .. .. .. ..$ xbestsplit   : num [1:485, 1:1000] 1371340800 15630 16982 74 15848 ...
##   .. .. .. .. .. ..$ ncat         : Named int [1:17] 1 1 1 1 1 1 1 1 1 1 ...
##   .. .. .. .. .. .. ..- attr(*, "names")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. ..$ nrnodes      : int 485
##   .. .. .. .. .. ..$ ntree        : num 1000
##   .. .. .. .. .. ..$ xlevels      :List of 17
##   .. .. .. .. .. .. ..$ time          : num 0
##   .. .. .. .. .. .. ..$ time_index.num: num 0
##   .. .. .. .. .. .. ..$ time_year     : num 0
##   .. .. .. .. .. .. ..$ time_half     : num 0
##   .. .. .. .. .. .. ..$ time_quarter  : num 0
##   .. .. .. .. .. .. ..$ time_month    : num 0
##   .. .. .. .. .. .. ..$ time_day      : num 0
##   .. .. .. .. .. .. ..$ time_wday     : num 0
##   .. .. .. .. .. .. ..$ time_mday     : num 0
##   .. .. .. .. .. .. ..$ time_qday     : num 0
##   .. .. .. .. .. .. ..$ time_yday     : num 0
##   .. .. .. .. .. .. ..$ time_mweek    : num 0
##   .. .. .. .. .. .. ..$ time_week     : num 0
##   .. .. .. .. .. .. ..$ time_week2    : num 0
##   .. .. .. .. .. .. ..$ time_week3    : num 0
##   .. .. .. .. .. .. ..$ time_week4    : num 0
##   .. .. .. .. .. .. ..$ time_mday7    : num 0
##   .. .. .. .. ..$ coefs          : NULL
##   .. .. .. .. ..$ y              : num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. ..$ test           : NULL
##   .. .. .. .. ..$ inbag          : NULL
##   .. .. .. .. ..- attr(*, "class")= chr "randomForest"
##   .. .. .. ..$ preproc     :List of 1
##   .. .. .. .. ..$ y_var: chr(0) 
##   .. .. .. ..$ elapsed     :List of 1
##   .. .. .. .. ..$ elapsed: num NA
##   .. .. .. ..$ censor_probs: list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "_randomForest" "model_fit"
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_fit" "stage"
##   .. ..$ post   :List of 1
##   .. .. ..$ actions: Named list()
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_post" "stage"
##   .. ..$ trained: logi TRUE
##   .. ..- attr(*, "class")= chr "workflow"
##   ..$ :List of 4
##   .. ..$ pre    :List of 3
##   .. .. ..$ actions     :List of 1
##   .. .. .. ..$ recipe:List of 2
##   .. .. .. .. ..$ recipe   :List of 7
##   .. .. .. .. .. ..$ var_info    : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info   : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ steps       :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ columns: NULL
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180dd655270> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_EoYnc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ template    : tibble [2,235 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ levels      : NULL
##   .. .. .. .. .. ..$ retained    : logi NA
##   .. .. .. .. .. ..$ requirements:List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ blueprint:List of 8
##   .. .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. .. ..$ ptypes            : NULL
##   .. .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. .. ..$ recipe            : NULL
##   .. .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_recipe" "action_pre" "action"
##   .. .. ..$ mold        :List of 4
##   .. .. .. ..$ predictors: tibble [2,979 × 17] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ time          : num [1:2979] 15307 15308 15309 15310 15313 ...
##   .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. ..$ outcomes  : tibble [2,979 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ close: num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ blueprint :List of 8
##   .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. ..$ ptypes            :List of 2
##   .. .. .. .. .. ..$ predictors: tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time: 'Date' num(0) 
##   .. .. .. .. .. ..$ outcomes  : tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ close: num(0) 
##   .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. ..$ recipe            :List of 8
##   .. .. .. .. .. ..$ var_info      : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info     : tibble [18 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "close" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:18] "predictor" "outcome" "predictor" "predictor" ...
##   .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. ..$ steps         :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ columns: Named chr "time"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180dd655270> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_EoYnc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ retained      : logi FALSE
##   .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..$ tr_info       :'data.frame':    1 obs. of  2 variables:
##   .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. ..$ orig_lvls     :List of 2
##   .. .. .. .. .. .. ..$ time :List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ close:List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. ..$ last_term_info: gropd_df [29 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. ..$ type    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr "outcome"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. ..$ source  : chr [1:29] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. .. ..$ number  : num [1:29] 4 4 1 4 4 1 1 4 4 4 ...
##   .. .. .. .. .. .. ..$ skip    : logi [1:29] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. ..- attr(*, "groups")= tibble [29 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:29] 
##   .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. ..$ : int 19
##   .. .. .. .. .. .. .. .. ..$ : int 20
##   .. .. .. .. .. .. .. .. ..$ : int 21
##   .. .. .. .. .. .. .. .. ..$ : int 22
##   .. .. .. .. .. .. .. .. ..$ : int 23
##   .. .. .. .. .. .. .. .. ..$ : int 24
##   .. .. .. .. .. .. .. .. ..$ : int 25
##   .. .. .. .. .. .. .. .. ..$ : int 26
##   .. .. .. .. .. .. .. .. ..$ : int 27
##   .. .. .. .. .. .. .. .. ..$ : int 28
##   .. .. .. .. .. .. .. .. ..$ : int 29
##   .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. ..$ extras    :List of 1
##   .. .. .. .. ..$ roles: NULL
##   .. .. ..$ case_weights: NULL
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_pre" "stage"
##   .. ..$ fit    :List of 2
##   .. .. ..$ actions:List of 1
##   .. .. .. ..$ model:List of 2
##   .. .. .. .. ..$ spec   :List of 7
##   .. .. .. .. .. ..$ args                 :List of 8
##   .. .. .. .. .. .. ..$ mtry          : language ~25
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ trees         : language ~1000
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ min_n         : language ~2
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ tree_depth    : language ~12
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ learn_rate    : language ~0.3
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ loss_reduction: language ~0
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ sample_size   : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ stop_iter     : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. .. ..$ method               : NULL
##   .. .. .. .. .. ..$ engine               : chr "xgboost"
##   .. .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "boost_tree" "model_spec"
##   .. .. .. .. ..$ formula: NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_model" "action_fit" "action"
##   .. .. ..$ fit    :List of 6
##   .. .. .. ..$ lvl         : NULL
##   .. .. .. ..$ spec        :List of 8
##   .. .. .. .. ..$ args                 :List of 8
##   .. .. .. .. .. ..$ mtry          : language ~25
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ trees         : language ~1000
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ min_n         : language ~2
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ tree_depth    : language ~12
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ learn_rate    : language ~0.3
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ loss_reduction: language ~0
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ sample_size   : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ stop_iter     : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. ..$ method               :List of 3
##   .. .. .. .. .. ..$ libs: chr "xgboost"
##   .. .. .. .. .. ..$ fit :List of 5
##   .. .. .. .. .. .. ..$ interface: chr "matrix"
##   .. .. .. .. .. .. ..$ protect  : chr [1:3] "x" "y" "weights"
##   .. .. .. .. .. .. ..$ func     : Named chr [1:2] "parsnip" "xgb_train"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. ..$ defaults :List of 2
##   .. .. .. .. .. .. .. ..$ nthread: num 1
##   .. .. .. .. .. .. .. ..$ verbose: num 0
##   .. .. .. .. .. .. ..$ args     :List of 11
##   .. .. .. .. .. .. .. ..$ x               : language missing_arg()
##   .. .. .. .. .. .. .. ..$ y               : language missing_arg()
##   .. .. .. .. .. .. .. ..$ weights         : language missing_arg()
##   .. .. .. .. .. .. .. ..$ colsample_bynode: language ~25
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ nrounds         : language ~1000
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ min_child_weight: language ~2
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ max_depth       : language ~12
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ eta             : language ~0.3
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ gamma           : language ~0
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ nthread         : num 1
##   .. .. .. .. .. .. .. ..$ verbose         : num 0
##   .. .. .. .. .. ..$ pred:List of 2
##   .. .. .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "xgb_predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object  : language object$fit
##   .. .. .. .. .. .. .. .. ..$ new_data: symbol new_data
##   .. .. .. .. .. .. ..$ raw    :List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "xgb_predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object  : language object$fit
##   .. .. .. .. .. .. .. .. ..$ new_data: symbol new_data
##   .. .. .. .. ..$ engine               : chr "xgboost"
##   .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. ..$ defaults             :List of 2
##   .. .. .. .. .. ..$ nthread: num 1
##   .. .. .. .. .. ..$ verbose: num 0
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "boost_tree" "model_spec"
##   .. .. .. ..$ fit         :List of 9
##   .. .. .. .. ..$ handle        :Class 'xgb.Booster.handle' <externalptr> 
##   .. .. .. .. ..$ raw           : raw [1:2045107] 7b 4c 00 00 ...
##   .. .. .. .. ..$ niter         : num 1000
##   .. .. .. .. ..$ evaluation_log:Classes 'data.table' and 'data.frame':  1000 obs. of  2 variables:
##   .. .. .. .. .. ..$ iter         : num [1:1000] 1 2 3 4 5 6 7 8 9 10 ...
##   .. .. .. .. .. ..$ training_rmse: num [1:1000] 4.71 3.31 2.33 1.64 1.16 ...
##   .. .. .. .. .. ..- attr(*, ".internal.selfref")=<externalptr> 
##   .. .. .. .. ..$ call          : language xgboost::xgb.train(params = list(eta = 0.3, max_depth = 12, gamma = 0,      colsample_bytree = 1, colsample_bynod| __truncated__ ...
##   .. .. .. .. ..$ params        :List of 10
##   .. .. .. .. .. ..$ eta                : num 0.3
##   .. .. .. .. .. ..$ max_depth          : num 12
##   .. .. .. .. .. ..$ gamma              : num 0
##   .. .. .. .. .. ..$ colsample_bytree   : num 1
##   .. .. .. .. .. ..$ colsample_bynode   : num 1
##   .. .. .. .. .. ..$ min_child_weight   : num 2
##   .. .. .. .. .. ..$ subsample          : num 1
##   .. .. .. .. .. ..$ nthread            : num 1
##   .. .. .. .. .. ..$ objective          : chr "reg:squarederror"
##   .. .. .. .. .. ..$ validate_parameters: logi TRUE
##   .. .. .. .. ..$ callbacks     :List of 1
##   .. .. .. .. .. ..$ cb.evaluation.log:function (env = parent.frame(), finalize = FALSE)  
##   .. .. .. .. .. .. ..- attr(*, "call")= language cb.evaluation.log()
##   .. .. .. .. .. .. ..- attr(*, "name")= chr "cb.evaluation.log"
##   .. .. .. .. ..$ feature_names : chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. ..$ nfeatures     : int 17
##   .. .. .. .. ..- attr(*, "class")= chr "xgb.Booster"
##   .. .. .. ..$ preproc     :List of 1
##   .. .. .. .. ..$ y_var: chr(0) 
##   .. .. .. ..$ elapsed     :List of 1
##   .. .. .. .. ..$ elapsed: num NA
##   .. .. .. ..$ censor_probs: list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "_xgb.Booster" "model_fit"
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_fit" "stage"
##   .. ..$ post   :List of 1
##   .. .. ..$ actions: Named list()
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_post" "stage"
##   .. ..$ trained: logi TRUE
##   .. ..- attr(*, "class")= chr "workflow"
##   ..$ :List of 4
##   .. ..$ pre    :List of 3
##   .. .. ..$ actions     :List of 1
##   .. .. .. ..$ recipe:List of 2
##   .. .. .. .. ..$ recipe   :List of 7
##   .. .. .. .. .. ..$ var_info    : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info   : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ steps       :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ columns: NULL
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180df213a70> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_EoYnc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ template    : tibble [2,235 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ levels      : NULL
##   .. .. .. .. .. ..$ retained    : logi NA
##   .. .. .. .. .. ..$ requirements:List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ blueprint:List of 8
##   .. .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. .. ..$ ptypes            : NULL
##   .. .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. .. ..$ recipe            : NULL
##   .. .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_recipe" "action_pre" "action"
##   .. .. ..$ mold        :List of 4
##   .. .. .. ..$ predictors: tibble [2,979 × 17] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ time          : num [1:2979] 15307 15308 15309 15310 15313 ...
##   .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. ..$ outcomes  : tibble [2,979 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ close: num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ blueprint :List of 8
##   .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. ..$ ptypes            :List of 2
##   .. .. .. .. .. ..$ predictors: tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time: 'Date' num(0) 
##   .. .. .. .. .. ..$ outcomes  : tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ close: num(0) 
##   .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. ..$ recipe            :List of 8
##   .. .. .. .. .. ..$ var_info      : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info     : tibble [18 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "close" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:18] "predictor" "outcome" "predictor" "predictor" ...
##   .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. ..$ steps         :List of 4
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ columns: Named chr "time"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 5
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ inputs :List of 1
##   .. .. .. .. .. .. .. .. ..$ time: language ~as.numeric(time)
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180df213a70> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "mutate_EoYnc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_mutate" "step"
##   .. .. .. .. .. ..$ retained      : logi FALSE
##   .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..$ tr_info       :'data.frame':    1 obs. of  2 variables:
##   .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. ..$ orig_lvls     :List of 2
##   .. .. .. .. .. .. ..$ time :List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ close:List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. ..$ last_term_info: gropd_df [29 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. ..$ type    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr "outcome"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. ..$ source  : chr [1:29] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. .. ..$ number  : num [1:29] 4 4 1 4 4 1 1 4 4 4 ...
##   .. .. .. .. .. .. ..$ skip    : logi [1:29] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. ..- attr(*, "groups")= tibble [29 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:29] 
##   .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. ..$ : int 19
##   .. .. .. .. .. .. .. .. ..$ : int 20
##   .. .. .. .. .. .. .. .. ..$ : int 21
##   .. .. .. .. .. .. .. .. ..$ : int 22
##   .. .. .. .. .. .. .. .. ..$ : int 23
##   .. .. .. .. .. .. .. .. ..$ : int 24
##   .. .. .. .. .. .. .. .. ..$ : int 25
##   .. .. .. .. .. .. .. .. ..$ : int 26
##   .. .. .. .. .. .. .. .. ..$ : int 27
##   .. .. .. .. .. .. .. .. ..$ : int 28
##   .. .. .. .. .. .. .. .. ..$ : int 29
##   .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. ..$ extras    :List of 1
##   .. .. .. .. ..$ roles: NULL
##   .. .. ..$ case_weights: NULL
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_pre" "stage"
##   .. ..$ fit    :List of 2
##   .. .. ..$ actions:List of 1
##   .. .. .. ..$ model:List of 2
##   .. .. .. .. ..$ spec   :List of 7
##   .. .. .. .. .. ..$ args                 :List of 3
##   .. .. .. .. .. .. ..$ committees: language ~100
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ neighbors : language ~20
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ max_rules : language ~1000
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. .. ..$ user_specified_mode  : logi FALSE
##   .. .. .. .. .. ..$ method               : NULL
##   .. .. .. .. .. ..$ engine               : chr "Cubist"
##   .. .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "cubist_rules" "model_spec"
##   .. .. .. .. ..$ formula: NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_model" "action_fit" "action"
##   .. .. ..$ fit    :List of 6
##   .. .. .. ..$ lvl         : NULL
##   .. .. .. ..$ spec        :List of 7
##   .. .. .. .. ..$ args                 :List of 3
##   .. .. .. .. .. ..$ committees: language ~100
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ neighbors : language ~9L
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ max_rules : language ~1000
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. ..$ user_specified_mode  : logi FALSE
##   .. .. .. .. ..$ method               :List of 3
##   .. .. .. .. .. ..$ libs: chr [1:2] "Cubist" "rules"
##   .. .. .. .. .. ..$ fit :List of 5
##   .. .. .. .. .. .. ..$ interface: chr "data.frame"
##   .. .. .. .. .. .. ..$ protect  : chr [1:3] "x" "y" "weights"
##   .. .. .. .. .. .. ..$ func     : Named chr [1:2] "rules" "cubist_fit"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "pkg" "fun"
##   .. .. .. .. .. .. ..$ defaults : list()
##   .. .. .. .. .. .. ..$ args     :List of 6
##   .. .. .. .. .. .. .. ..$ x         : language missing_arg()
##   .. .. .. .. .. .. .. ..$ y         : language missing_arg()
##   .. .. .. .. .. .. .. ..$ weights   : language missing_arg()
##   .. .. .. .. .. .. .. ..$ committees: language ~100
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ neighbors : language ~9L
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ max_rules : language ~1000
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ pred:List of 2
##   .. .. .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 3
##   .. .. .. .. .. .. .. .. ..$ object   : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata  : symbol new_data
##   .. .. .. .. .. .. .. .. ..$ neighbors: language rules::get_neighbors(object$spec$args)
##   .. .. .. .. .. .. ..$ raw    :List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 3
##   .. .. .. .. .. .. .. .. ..$ object   : language object$fit
##   .. .. .. .. .. .. .. .. ..$ newdata  : symbol new_data
##   .. .. .. .. .. .. .. .. ..$ neighbors: language rules::get_neighbors(object$spec$args)
##   .. .. .. .. ..$ engine               : chr "Cubist"
##   .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "cubist_rules" "model_spec"
##   .. .. .. ..$ fit         :List of 15
##   .. .. .. .. ..$ data        : chr "6\\.88199997,15307,1322524800,2011,2,4,11,29,3,29,60,333,5,48,0,0,0,5\n6\\.88199997,15308,1322611200,2011,2,4,1"| __truncated__
##   .. .. .. .. ..$ names       : chr "| Generated using R version 4.2.1 (2022-06-23 ucrt)\n| on Sat Nov 25 10:24:26 2023\noutcome.\n\noutcome: contin"| __truncated__
##   .. .. .. .. ..$ caseWeights : logi FALSE
##   .. .. .. .. ..$ model       : chr "id=\"Cubist 2.07 GPL Edition 2023-11-25\"\nprec=\"4\" globalmean=\"7.143603\" extrap=\"1\" insts=\"0\" ceiling="| __truncated__
##   .. .. .. .. ..$ output      : chr "\nCubist [Release 2.07 GPL Edition]  Sat Nov 25 10:24:26 2023\n---------------------------------\n\n    Target "| __truncated__
##   .. .. .. .. ..$ control     :List of 6
##   .. .. .. .. .. ..$ unbiased     : logi FALSE
##   .. .. .. .. .. ..$ rules        : num 1000
##   .. .. .. .. .. ..$ extrapolation: num 1
##   .. .. .. .. .. ..$ sample       : num 0
##   .. .. .. .. .. ..$ label        : chr "outcome"
##   .. .. .. .. .. ..$ seed         : int 4084
##   .. .. .. .. ..$ committees  : num 100
##   .. .. .. .. ..$ maxd        : num 3.8
##   .. .. .. .. ..$ dims        : int [1:2] 2979 17
##   .. .. .. .. ..$ splits      :'data.frame': 21812 obs. of  8 variables:
##   .. .. .. .. .. ..$ committee : num [1:21812] 1 1 1 1 1 1 1 1 1 1 ...
##   .. .. .. .. .. ..$ rule      : num [1:21812] 1 1 2 2 2 3 3 4 4 4 ...
##   .. .. .. .. .. ..$ variable  : chr [1:21812] "time" "time" "time" "time_yday" ...
##   .. .. .. .. .. ..$ dir       : chr [1:21812] "<=" ">" "<=" "<=" ...
##   .. .. .. .. .. ..$ value     : num [1:21812] 15393 15376 15876 103 15471 ...
##   .. .. .. .. .. ..$ category  : chr [1:21812] "" "" "" "" ...
##   .. .. .. .. .. ..$ type      : chr [1:21812] "type2" "type2" "type2" "type2" ...
##   .. .. .. .. .. ..$ percentile: num [1:21812] 0.0205 0.0161 0.1292 0.2853 0.0386 ...
##   .. .. .. .. ..$ usage       :'data.frame': 17 obs. of  3 variables:
##   .. .. .. .. .. ..$ Conditions: num [1:17] 100 36 19 9 5 5 1 1 0 0 ...
##   .. .. .. .. .. ..$ Model     : num [1:17] 96 76 50 57 59 70 11 31 16 8 ...
##   .. .. .. .. .. ..$ Variable  : chr [1:17] "time" "time_yday" "time_qday" "time_week" ...
##   .. .. .. .. ..$ call        : language cubist.default(x = x, y = y, committees = 100, control = Cubist::cubistControl(rules = 1000))
##   .. .. .. .. ..$ coefficients:'data.frame': 7655 obs. of  20 variables:
##   .. .. .. .. .. ..$ (Intercept)   : num [1:7655] -175.23 -7.57 353.34 144.95 43.15 ...
##   .. .. .. .. .. ..$ time          : num [1:7655] 0.011726 0.000841 -0.022623 -0.008907 -0.002398 ...
##   .. .. .. .. .. ..$ time_index.num: num [1:7655] NA NA NA NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ time_year     : num [1:7655] NA NA NA NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ time_half     : num [1:7655] NA NA NA NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ time_quarter  : num [1:7655] NA NA NA NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ time_month    : num [1:7655] NA -0.05 NA -0.044 NA -0.012 NA NA -0.741 NA ...
##   .. .. .. .. .. ..$ time_day      : num [1:7655] NA 0.042 0.032 0.008 NA 0.005 NA NA -0.024 NA ...
##   .. .. .. .. .. ..$ time_wday     : num [1:7655] NA -0.05 -0.035 NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ time_mday     : num [1:7655] NA NA NA NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ time_qday     : num [1:7655] NA 0.0031 0.002 NA 0.0046 0.0005 NA NA NA NA ...
##   .. .. .. .. .. ..$ time_yday     : num [1:7655] NA 0.00449 0.00043 0.00144 0.00139 ...
##   .. .. .. .. .. ..$ time_mweek    : num [1:7655] NA -0.332 -0.239 -0.029 NA -0.039 NA NA NA NA ...
##   .. .. .. .. .. ..$ time_week     : num [1:7655] NA NA NA NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ time_week2    : num [1:7655] NA NA NA NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ time_week3    : num [1:7655] NA NA NA NA NA 0.02 NA NA NA NA ...
##   .. .. .. .. .. ..$ time_week4    : num [1:7655] NA NA NA NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ time_mday7    : num [1:7655] NA NA NA NA NA NA NA NA NA NA ...
##   .. .. .. .. .. ..$ committee     : chr [1:7655] "1" "1" "1" "1" ...
##   .. .. .. .. .. ..$ rule          : chr [1:7655] "1" "2" "3" "4" ...
##   .. .. .. .. .. ..- attr(*, "reshapeWide")=List of 5
##   .. .. .. .. .. .. ..$ v.names: chr "value"
##   .. .. .. .. .. .. ..$ timevar: chr "var"
##   .. .. .. .. .. .. ..$ idvar  : chr "tmp"
##   .. .. .. .. .. .. ..$ times  : chr [1:18] "(Intercept)" "time" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ varying: chr [1, 1:18] "value.(Intercept)" "value.time" "value.time_index.num" "value.time_year" ...
##   .. .. .. .. ..$ vars        :List of 2
##   .. .. .. .. .. ..$ all : chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. ..$ used: chr [1:15] "time" "time_year" "time_half" "time_quarter" ...
##   .. .. .. .. ..$ .neighbors  : int 9
##   .. .. .. .. ..- attr(*, "class")= chr "cubist"
##   .. .. .. ..$ preproc     :List of 1
##   .. .. .. .. ..$ y_var: chr(0) 
##   .. .. .. ..$ elapsed     :List of 1
##   .. .. .. .. ..$ elapsed: num NA
##   .. .. .. ..$ censor_probs: list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "_cubist" "model_fit"
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_fit" "stage"
##   .. ..$ post   :List of 1
##   .. .. ..$ actions: Named list()
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_post" "stage"
##   .. ..$ trained: logi TRUE
##   .. ..- attr(*, "class")= chr "workflow"
##   ..$ :List of 4
##   .. ..$ pre    :List of 3
##   .. .. ..$ actions     :List of 1
##   .. .. .. ..$ recipe:List of 2
##   .. .. .. .. ..$ recipe   :List of 7
##   .. .. .. .. .. ..$ var_info    : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info   : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ steps       :List of 3
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ columns: NULL
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. ..$ template    : tibble [2,235 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ levels      : NULL
##   .. .. .. .. .. ..$ retained    : logi NA
##   .. .. .. .. .. ..$ requirements:List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ blueprint:List of 8
##   .. .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. .. ..$ ptypes            : NULL
##   .. .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. .. ..$ recipe            : NULL
##   .. .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_recipe" "action_pre" "action"
##   .. .. ..$ mold        :List of 4
##   .. .. .. ..$ predictors: tibble [2,979 × 17] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ time          : Date[1:2979], format: "2011-11-29" ...
##   .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. ..$ outcomes  : tibble [2,979 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ close: num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ blueprint :List of 8
##   .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. ..$ ptypes            :List of 2
##   .. .. .. .. .. ..$ predictors: tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time: 'Date' num(0) 
##   .. .. .. .. .. ..$ outcomes  : tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ close: num(0) 
##   .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. ..$ recipe            :List of 8
##   .. .. .. .. .. ..$ var_info      : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info     : tibble [18 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "close" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:18] "predictor" "outcome" "predictor" "predictor" ...
##   .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. ..$ steps         :List of 3
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ columns: Named chr "time"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. ..$ retained      : logi FALSE
##   .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..$ tr_info       :'data.frame':    1 obs. of  2 variables:
##   .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. ..$ orig_lvls     :List of 2
##   .. .. .. .. .. .. ..$ time :List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ close:List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. ..$ last_term_info: gropd_df [29 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. ..$ type    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr "outcome"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. ..$ source  : chr [1:29] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. .. ..$ number  : num [1:29] 3 3 1 3 3 1 1 3 3 3 ...
##   .. .. .. .. .. .. ..$ skip    : logi [1:29] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. ..- attr(*, "groups")= tibble [29 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:29] 
##   .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. ..$ : int 19
##   .. .. .. .. .. .. .. .. ..$ : int 20
##   .. .. .. .. .. .. .. .. ..$ : int 21
##   .. .. .. .. .. .. .. .. ..$ : int 22
##   .. .. .. .. .. .. .. .. ..$ : int 23
##   .. .. .. .. .. .. .. .. ..$ : int 24
##   .. .. .. .. .. .. .. .. ..$ : int 25
##   .. .. .. .. .. .. .. .. ..$ : int 26
##   .. .. .. .. .. .. .. .. ..$ : int 27
##   .. .. .. .. .. .. .. .. ..$ : int 28
##   .. .. .. .. .. .. .. .. ..$ : int 29
##   .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. ..$ extras    :List of 1
##   .. .. .. .. ..$ roles: NULL
##   .. .. ..$ case_weights: NULL
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_pre" "stage"
##   .. ..$ fit    :List of 2
##   .. .. ..$ actions:List of 1
##   .. .. .. ..$ model:List of 2
##   .. .. .. .. ..$ spec   :List of 7
##   .. .. .. .. .. ..$ args                 :List of 7
##   .. .. .. .. .. .. ..$ seasonal_period: language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ non_seasonal_ar: language ~2
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ seasonal_ar    : language ~1
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ hidden_units   : language ~10
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ num_networks   : language ~10
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ penalty        : language ~10
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ epochs         : language ~50
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. .. ..$ method               : NULL
##   .. .. .. .. .. ..$ engine               : chr "nnetar"
##   .. .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "nnetar_reg" "model_spec"
##   .. .. .. .. ..$ formula: NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_model" "action_fit" "action"
##   .. .. ..$ fit    :List of 6
##   .. .. .. ..$ lvl         : NULL
##   .. .. .. ..$ spec        :List of 7
##   .. .. .. .. ..$ args                 :List of 7
##   .. .. .. .. .. ..$ seasonal_period: language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ non_seasonal_ar: language ~2
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ seasonal_ar    : language ~1
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ hidden_units   : language ~10
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ num_networks   : language ~10
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ penalty        : language ~10
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ epochs         : language ~50
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. ..$ eng_args             : Named list()
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. ..$ method               :List of 3
##   .. .. .. .. .. ..$ libs: chr [1:2] "forecast" "modeltime"
##   .. .. .. .. .. ..$ fit :List of 5
##   .. .. .. .. .. .. ..$ interface: chr "data.frame"
##   .. .. .. .. .. .. ..$ protect  : chr [1:2] "x" "y"
##   .. .. .. .. .. .. ..$ func     : Named chr "nnetar_fit_impl"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. ..$ defaults : list()
##   .. .. .. .. .. .. ..$ args     :List of 8
##   .. .. .. .. .. .. .. ..$ x      : language missing_arg()
##   .. .. .. .. .. .. .. ..$ y      : language missing_arg()
##   .. .. .. .. .. .. .. ..$ p      : language ~2
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ P      : language ~1
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ size   : language ~10
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ repeats: language ~10
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ decay  : language ~10
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ maxit  : language ~50
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ pred:List of 1
##   .. .. .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object  : language object$fit
##   .. .. .. .. .. .. .. .. ..$ new_data: symbol new_data
##   .. .. .. .. ..$ engine               : chr "nnetar"
##   .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "nnetar_reg" "model_spec"
##   .. .. .. ..$ fit         :List of 4
##   .. .. .. .. ..$ models:List of 1
##   .. .. .. .. .. ..$ model_1:List of 17
##   .. .. .. .. .. .. ..$ x        : Time-Series [1:2979] from 1 to 597: 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. .. ..$ m        : num 5
##   .. .. .. .. .. .. ..$ p        : num 2
##   .. .. .. .. .. .. ..$ P        : num 1
##   .. .. .. .. .. .. ..$ scalex   :List of 2
##   .. .. .. .. .. .. .. ..$ center: num 7.14
##   .. .. .. .. .. .. .. ..$ scale : num 0.893
##   .. .. .. .. .. .. ..$ scalexreg:List of 2
##   .. .. .. .. .. .. .. ..$ center: Named num [1:16] 1510064599.4 2017.35 1.51 2.51 6.52 ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:16] "time_index_num" "time_year" "time_half" "time_quarter" ...
##   .. .. .. .. .. .. .. ..$ scale : Named num [1:16] 107972612.19 3.42 0.5 1.12 3.45 ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:16] "time_index_num" "time_year" "time_half" "time_quarter" ...
##   .. .. .. .. .. .. ..$ size     : num 10
##   .. .. .. .. .. .. ..$ xreg     : num [1:2979, 1:16] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ : chr [1:16] "time_index_num" "time_year" "time_half" "time_quarter" ...
##   .. .. .. .. .. .. ..$ subset   : int [1:2979] 1 2 3 4 5 6 7 8 9 10 ...
##   .. .. .. .. .. .. ..$ model    :List of 10
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 264
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] -0.255 -0.591 -0.729 -0.563 0.479 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -1.03 -1.15 -1.29 -1.32 -1.07 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.2163 -0.0952 0.0789 0.2886 0.0725 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 139
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] -0.1043 -0.4863 -0.2448 -0.086 -0.0122 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -1.02 -1.09 -1.17 -1.18 -1.11 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.2292 -0.1591 -0.0414 0.1459 0.1129 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 318
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] -0.275 0.87 1.226 0.848 -0.256 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -1.09 -1.22 -1.29 -1.28 -1.13 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.1535 -0.0233 0.0782 0.241 0.1262 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 246
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] 0.0547 0.6304 0.3603 0.1676 -0.1326 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -0.999 -1.072 -1.18 -1.197 -1.072 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.247 -0.176 -0.033 0.162 0.072 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 124
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] -0.00225 -0.61109 -0.33115 -0.07935 -0.02567 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -1.07 -1.15 -1.23 -1.24 -1.11 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.1741 -0.0986 0.0218 0.2096 0.1099 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 436
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] -0.6 0.49 0.535 0.578 -0.438 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -1.15 -1.23 -1.28 -1.28 -1.09 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.1005 -0.015 0.0635 0.2482 0.0924 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 130
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] 0.036 0.0415 0.0346 0.0292 -0.1853 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -1.05 -1.13 -1.22 -1.23 -1.07 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.20123 -0.11577 0.00635 0.19423 0.06762 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 122
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] 0.0526 0.055 0.0563 -0.121 0.2697 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -1.01 -1.09 -1.2 -1.22 -1.11 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.2316 -0.1567 -0.0165 0.1803 0.1098 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 123
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] 0.2012 0.3794 0.3044 0.2384 -0.0288 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -1.05 -1.13 -1.22 -1.23 -1.09 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.1968 -0.1144 0.0108 0.198 0.0851 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..$ :List of 15
##   .. .. .. .. .. .. .. .. ..$ n            : num [1:3] 19 10 1
##   .. .. .. .. .. .. .. .. ..$ nunits       : int 31
##   .. .. .. .. .. .. .. .. ..$ nconn        : num [1:32] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. .. ..$ conn         : num [1:211] 0 1 2 3 4 5 6 7 8 9 ...
##   .. .. .. .. .. .. .. .. ..$ nsunits      : num 30
##   .. .. .. .. .. .. .. .. ..$ decay        : num 10
##   .. .. .. .. .. .. .. .. ..$ entropy      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ softmax      : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ censored     : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ value        : num 130
##   .. .. .. .. .. .. .. .. ..$ wts          : num [1:211] -0.1523 -0.3737 -0.2355 -0.122 -0.0201 ...
##   .. .. .. .. .. .. .. .. ..$ convergence  : int 1
##   .. .. .. .. .. .. .. .. ..$ fitted.values: num [1:2974, 1] -1.07 -1.16 -1.24 -1.26 -1.14 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ residuals    : num [1:2974, 1] -0.1731 -0.0915 0.0297 0.2209 0.1406 ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. ..$ call         : language nnet.default(x = x, y = y, size = ..1, linout = linout, decay = ..2, maxit = ..3,      trace = trace)
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnet"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr "nnetarmodels"
##   .. .. .. .. .. .. ..$ nnetargs :List of 2
##   .. .. .. .. .. .. .. ..$ decay: num 10
##   .. .. .. .. .. .. .. ..$ maxit: num 50
##   .. .. .. .. .. .. ..$ fitted   : Time-Series [1:2979] from 1 to 597: NA NA NA NA NA ...
##   .. .. .. .. .. .. ..$ residuals: Time-Series [1:2979] from 1 to 597: NA NA NA NA NA ...
##   .. .. .. .. .. .. ..$ lags     : num [1:3] 1 2 5
##   .. .. .. .. .. .. ..$ series   : chr "outcome"
##   .. .. .. .. .. .. ..$ method   : chr "NNAR(2,1,10)[5]"
##   .. .. .. .. .. .. ..$ call     : language forecast::nnetar(y = outcome, p = p, P = P, size = size, repeats = repeats,      xreg = xreg_matrix, decay = deca| __truncated__
##   .. .. .. .. .. .. ..- attr(*, "class")= chr "nnetar"
##   .. .. .. .. ..$ data  : tibble [2,979 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. ..$ time      : Date[1:2979], format: "2011-11-29" ...
##   .. .. .. .. .. ..$ .actual   : num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ .fitted   : num [1:2979] NA NA NA NA NA ...
##   .. .. .. .. .. ..$ .residuals: num [1:2979] NA NA NA NA NA ...
##   .. .. .. .. ..$ extras:List of 1
##   .. .. .. .. .. ..$ xreg_recipe:List of 9
##   .. .. .. .. .. .. ..$ var_info      : tibble [17 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. ..$ type    :List of 17
##   .. .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ role    : chr [1:17] "predictor" "predictor" "predictor" "predictor" ...
##   .. .. .. .. .. .. .. ..$ source  : chr [1:17] "original" "original" "original" "original" ...
##   .. .. .. .. .. .. ..$ term_info     : tibble [16 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:16] "time_index_num" "time_year" "time_half" "time_quarter" ...
##   .. .. .. .. .. .. .. ..$ type    :List of 16
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ role    : chr [1:16] "predictor" "predictor" "predictor" "predictor" ...
##   .. .. .. .. .. .. .. ..$ source  : chr [1:16] "derived" "original" "original" "original" ...
##   .. .. .. .. .. .. ..$ steps         :List of 3
##   .. .. .. .. .. .. .. ..$ :List of 7
##   .. .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. .. ..$ : language ~dplyr::everything()
##   .. .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180d5dca7e8> 
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. .. ..$ fn     :function (string, case = "snake", replace = c(`'` = "", `"` = "", `%` = "_percent_", 
##     `#` = "_number_"), ascii = TRUE, use_make_names = TRUE, allow_dupes = FALSE, 
##     sep_in = "\\.", transliterations = "Latin-ASCII", parsing_option = 1, 
##     numerals = "asis", ...)  
##   .. .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. .. ..$ inputs : Named chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ id     : chr "rename_at_z3YUX"
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rename_at" "step"
##   .. .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. .. ..$ : language ~names_date
##   .. .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180d8043440> 
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. .. ..$ removals: Named chr "time"
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ id      : chr "rm_v6SVN"
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. .. ..$ :List of 7
##   .. .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. .. ..$ : language ~recipes::all_predictors()
##   .. .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180d806a878> 
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. .. ..$ group   : NULL
##   .. .. .. .. .. .. .. .. ..$ removals: chr(0) 
##   .. .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ id      : chr "zv_59K4i"
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_zv" "step"
##   .. .. .. .. .. .. ..$ template      : tibble [2,979 × 16] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ time_index_num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. .. .. .. ..$ retained      : logi TRUE
##   .. .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. .. ..$ tr_info       :'data.frame': 1 obs. of  2 variables:
##   .. .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. .. ..$ orig_lvls     :List of 17
##   .. .. .. .. .. .. .. ..$ time          :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_index.num:List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_year     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_half     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_quarter  :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_month    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_day      :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_wday     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_mday     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_qday     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_yday     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_mweek    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_week     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_week2    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_week3    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_week4    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_mday7    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ last_term_info: gropd_df [18 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "time_day" "time_half" "time_index.num" ...
##   .. .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ role    :List of 18
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "original" "original" ...
##   .. .. .. .. .. .. .. ..$ number  : num [1:18] 1 3 3 0 3 3 3 3 3 3 ...
##   .. .. .. .. .. .. .. ..$ skip    : logi [1:18] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. .. ..- attr(*, "groups")= tibble [18 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "time_day" "time_half" "time_index.num" ...
##   .. .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:18] 
##   .. .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ desc  : chr "NNAR(2,1,10)[5]"
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "nnetar_fit_impl" "modeltime_bridge"
##   .. .. .. ..$ preproc     :List of 1
##   .. .. .. .. ..$ y_var: chr(0) 
##   .. .. .. ..$ elapsed     :List of 1
##   .. .. .. .. ..$ elapsed: num NA
##   .. .. .. ..$ censor_probs: list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "_nnetar_fit_impl" "model_fit"
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_fit" "stage"
##   .. ..$ post   :List of 1
##   .. .. ..$ actions: Named list()
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_post" "stage"
##   .. ..$ trained: logi TRUE
##   .. ..- attr(*, "class")= chr "workflow"
##   ..$ :List of 4
##   .. ..$ pre    :List of 3
##   .. .. ..$ actions     :List of 1
##   .. .. .. ..$ recipe:List of 2
##   .. .. .. .. ..$ recipe   :List of 7
##   .. .. .. .. .. ..$ var_info    : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info   : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ steps       :List of 3
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi FALSE
##   .. .. .. .. .. .. .. ..$ columns: NULL
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi FALSE
##   .. .. .. .. .. .. .. ..$ removals: NULL
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. ..$ template    : tibble [2,235 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ levels      : NULL
##   .. .. .. .. .. ..$ retained    : logi NA
##   .. .. .. .. .. ..$ requirements:List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ blueprint:List of 8
##   .. .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. .. ..$ ptypes            : NULL
##   .. .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. .. ..$ recipe            : NULL
##   .. .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_recipe" "action_pre" "action"
##   .. .. ..$ mold        :List of 4
##   .. .. .. ..$ predictors: tibble [2,979 × 17] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ time          : Date[1:2979], format: "2011-11-29" ...
##   .. .. .. .. ..$ time_index.num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. ..$ outcomes  : tibble [2,979 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ close: num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ blueprint :List of 8
##   .. .. .. .. ..$ intercept         : logi FALSE
##   .. .. .. .. ..$ allow_novel_levels: logi FALSE
##   .. .. .. .. ..$ composition       : chr "tibble"
##   .. .. .. .. ..$ ptypes            :List of 2
##   .. .. .. .. .. ..$ predictors: tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ time: 'Date' num(0) 
##   .. .. .. .. .. ..$ outcomes  : tibble [0 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ close: num(0) 
##   .. .. .. .. ..$ fresh             : logi TRUE
##   .. .. .. .. ..$ strings_as_factors: logi TRUE
##   .. .. .. .. ..$ recipe            :List of 8
##   .. .. .. .. .. ..$ var_info      : tibble [2 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:2] "time" "close"
##   .. .. .. .. .. .. ..$ type    :List of 2
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:2] "predictor" "outcome"
##   .. .. .. .. .. .. ..$ source  : chr [1:2] "original" "original"
##   .. .. .. .. .. ..$ term_info     : tibble [18 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "close" "time_index.num" "time_year" ...
##   .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    : chr [1:18] "predictor" "outcome" "predictor" "predictor" ...
##   .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. ..$ steps         :List of 3
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~time
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac67e8> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. ..$ columns: Named chr "time"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. ..$ id     : chr "timeseries_signature_ieZJJ"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_timeseries_signature" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~matches("(iso)|(xts)|(hour)|(minute)|(second)|(am.pm)")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6890> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:9] "time_year.iso" "time_month.xts" "time_hour" "time_minute" ...
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_5yUqM"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. ..$ : language ~c("time_month.lbl", "time_wday.lbl")
##   .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180caac6938> 
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. ..$ removals: Named chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:2] "time_month.lbl" "time_wday.lbl"
##   .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. ..$ id      : chr "rm_mt3Sc"
##   .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. ..$ retained      : logi FALSE
##   .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. ..$ tr_info       :'data.frame':    1 obs. of  2 variables:
##   .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. ..$ orig_lvls     :List of 2
##   .. .. .. .. .. .. ..$ time :List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ close:List of 2
##   .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. ..$ last_term_info: gropd_df [29 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. ..$ type    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "ordered" "nominal"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. ..$ role    :List of 29
##   .. .. .. .. .. .. .. ..$ : chr "outcome"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. ..$ source  : chr [1:29] "original" "original" "derived" "derived" ...
##   .. .. .. .. .. .. ..$ number  : num [1:29] 3 3 1 3 3 1 1 3 3 3 ...
##   .. .. .. .. .. .. ..$ skip    : logi [1:29] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. ..- attr(*, "groups")= tibble [29 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:29] "close" "time" "time_am.pm" "time_day" ...
##   .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:29] 
##   .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. ..$ : int 19
##   .. .. .. .. .. .. .. .. ..$ : int 20
##   .. .. .. .. .. .. .. .. ..$ : int 21
##   .. .. .. .. .. .. .. .. ..$ : int 22
##   .. .. .. .. .. .. .. .. ..$ : int 23
##   .. .. .. .. .. .. .. .. ..$ : int 24
##   .. .. .. .. .. .. .. .. ..$ : int 25
##   .. .. .. .. .. .. .. .. ..$ : int 26
##   .. .. .. .. .. .. .. .. ..$ : int 27
##   .. .. .. .. .. .. .. .. ..$ : int 28
##   .. .. .. .. .. .. .. .. ..$ : int 29
##   .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. ..$ extra_role_ptypes : NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "default_recipe_blueprint" "recipe_blueprint" "hardhat_blueprint"
##   .. .. .. ..$ extras    :List of 1
##   .. .. .. .. ..$ roles: NULL
##   .. .. ..$ case_weights: NULL
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_pre" "stage"
##   .. ..$ fit    :List of 2
##   .. .. ..$ actions:List of 1
##   .. .. .. ..$ model:List of 2
##   .. .. .. .. ..$ spec   :List of 7
##   .. .. .. .. .. ..$ args                 :List of 20
##   .. .. .. .. .. .. ..$ growth                  : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ changepoint_num         : language ~25
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ changepoint_range       : language ~0.8
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ seasonality_yearly      : language ~F
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. .. .. .. .. .. ..$ seasonality_weekly      : language ~F
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. .. .. .. .. .. ..$ seasonality_daily       : language ~F
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. .. .. .. .. .. ..$ season                  : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ prior_scale_changepoints: language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ prior_scale_seasonality : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ prior_scale_holidays    : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ logistic_cap            : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ logistic_floor          : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ mtry                    : language ~0.75
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ trees                   : language ~300
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ min_n                   : language ~20
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ tree_depth              : language ~3
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ learn_rate              : language ~0.35
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ loss_reduction          : language ~0.15
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ sample_size             : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. ..$ stop_iter               : language ~NULL
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ eng_args             :List of 1
##   .. .. .. .. .. .. ..$ counts: language ~F
##   .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180dd1b27f8> 
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. .. ..$ method               : NULL
##   .. .. .. .. .. ..$ engine               : chr "prophet_xgboost"
##   .. .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "prophet_boost" "model_spec"
##   .. .. .. .. ..$ formula: NULL
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "action_model" "action_fit" "action"
##   .. .. ..$ fit    :List of 6
##   .. .. .. ..$ lvl         : NULL
##   .. .. .. ..$ spec        :List of 8
##   .. .. .. .. ..$ args                 :List of 20
##   .. .. .. .. .. ..$ growth                  : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ changepoint_num         : language ~25
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ changepoint_range       : language ~0.8
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ seasonality_yearly      : language ~F
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. .. .. .. .. ..$ seasonality_weekly      : language ~F
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. .. .. .. .. ..$ seasonality_daily       : language ~F
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. .. .. .. .. ..$ season                  : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ prior_scale_changepoints: language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ prior_scale_seasonality : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ prior_scale_holidays    : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ logistic_cap            : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ logistic_floor          : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ mtry                    : language ~0.75
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ trees                   : language ~300
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ min_n                   : language ~20
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ tree_depth              : language ~3
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ learn_rate              : language ~0.35
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ loss_reduction          : language ~0.15
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ sample_size             : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. ..$ stop_iter               : language ~NULL
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. ..$ eng_args             :List of 1
##   .. .. .. .. .. ..$ counts: language ~F
##   .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180dd1b27f8> 
##   .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. ..$ mode                 : chr "regression"
##   .. .. .. .. ..$ user_specified_mode  : logi TRUE
##   .. .. .. .. ..$ method               :List of 3
##   .. .. .. .. .. ..$ libs: chr [1:3] "prophet" "xgboost" "modeltime"
##   .. .. .. .. .. ..$ fit :List of 5
##   .. .. .. .. .. .. ..$ interface: chr "data.frame"
##   .. .. .. .. .. .. ..$ protect  : chr [1:2] "x" "y"
##   .. .. .. .. .. .. ..$ func     : Named chr "prophet_xgboost_fit_impl"
##   .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. ..$ defaults :List of 4
##   .. .. .. .. .. .. .. ..$ uncertainty.samples: num 0
##   .. .. .. .. .. .. .. ..$ objective          : chr "reg:squarederror"
##   .. .. .. .. .. .. .. ..$ nthread            : num 1
##   .. .. .. .. .. .. .. ..$ verbose            : num 0
##   .. .. .. .. .. .. ..$ args     :List of 18
##   .. .. .. .. .. .. .. ..$ x                  : language missing_arg()
##   .. .. .. .. .. .. .. ..$ y                  : language missing_arg()
##   .. .. .. .. .. .. .. ..$ n.changepoints     : language ~25
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ changepoint.range  : language ~0.8
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ yearly.seasonality : language ~F
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. .. .. .. .. .. .. ..$ weekly.seasonality : language ~F
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. .. .. .. .. .. .. ..$ daily.seasonality  : language ~F
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
##   .. .. .. .. .. .. .. ..$ colsample_bynode   : language ~0.75
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ nrounds            : language ~300
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ min_child_weight   : language ~20
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ max_depth          : language ~3
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ eta                : language ~0.35
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ gamma              : language ~0.15
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##   .. .. .. .. .. .. .. ..$ counts             : language ~F
##   .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180dd1b27f8> 
##   .. .. .. .. .. .. .. ..$ uncertainty.samples: num 0
##   .. .. .. .. .. .. .. ..$ objective          : chr "reg:squarederror"
##   .. .. .. .. .. .. .. ..$ nthread            : num 1
##   .. .. .. .. .. .. .. ..$ verbose            : num 0
##   .. .. .. .. .. ..$ pred:List of 1
##   .. .. .. .. .. .. ..$ numeric:List of 4
##   .. .. .. .. .. .. .. ..$ pre : NULL
##   .. .. .. .. .. .. .. ..$ post: NULL
##   .. .. .. .. .. .. .. ..$ func: Named chr "predict"
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "fun"
##   .. .. .. .. .. .. .. ..$ args:List of 2
##   .. .. .. .. .. .. .. .. ..$ object  : language object$fit
##   .. .. .. .. .. .. .. .. ..$ new_data: symbol new_data
##   .. .. .. .. ..$ engine               : chr "prophet_xgboost"
##   .. .. .. .. ..$ user_specified_engine: logi TRUE
##   .. .. .. .. ..$ defaults             :List of 4
##   .. .. .. .. .. ..$ uncertainty.samples: num 0
##   .. .. .. .. .. ..$ objective          : chr "reg:squarederror"
##   .. .. .. .. .. ..$ nthread            : num 1
##   .. .. .. .. .. ..$ verbose            : num 0
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "prophet_boost" "model_spec"
##   .. .. .. ..$ fit         :List of 4
##   .. .. .. .. ..$ models:List of 2
##   .. .. .. .. .. ..$ model_1:List of 32
##   .. .. .. .. .. .. ..$ growth                 : chr "linear"
##   .. .. .. .. .. .. ..$ changepoints           : POSIXct[1:25], format: "2012-04-16" ...
##   .. .. .. .. .. .. ..$ n.changepoints         : num 25
##   .. .. .. .. .. .. ..$ changepoint.range      : num 0.8
##   .. .. .. .. .. .. ..$ yearly.seasonality     : logi FALSE
##   .. .. .. .. .. .. ..$ weekly.seasonality     : logi FALSE
##   .. .. .. .. .. .. ..$ daily.seasonality      : logi FALSE
##   .. .. .. .. .. .. ..$ holidays               : NULL
##   .. .. .. .. .. .. ..$ seasonality.mode       : chr "additive"
##   .. .. .. .. .. .. ..$ seasonality.prior.scale: num 10
##   .. .. .. .. .. .. ..$ changepoint.prior.scale: num 0.05
##   .. .. .. .. .. .. ..$ holidays.prior.scale   : num 10
##   .. .. .. .. .. .. ..$ mcmc.samples           : num 0
##   .. .. .. .. .. .. ..$ interval.width         : num 0.8
##   .. .. .. .. .. .. ..$ uncertainty.samples    : num 0
##   .. .. .. .. .. .. ..$ specified.changepoints : logi FALSE
##   .. .. .. .. .. .. ..$ start                  : POSIXct[1:1], format: "2011-11-29"
##   .. .. .. .. .. .. ..$ y.scale                : num 9.77
##   .. .. .. .. .. .. ..$ logistic.floor         : logi FALSE
##   .. .. .. .. .. .. ..$ t.scale                : num 375494400
##   .. .. .. .. .. .. ..$ changepoints.t         : num [1:25] 0.032 0.0642 0.0966 0.1295 0.1618 ...
##   .. .. .. .. .. .. ..$ seasonalities          : list()
##   .. .. .. .. .. .. ..$ extra_regressors       : list()
##   .. .. .. .. .. .. ..$ country_holidays       : NULL
##   .. .. .. .. .. .. ..$ stan.fit               :List of 4
##   .. .. .. .. .. .. .. ..$ par        :List of 6
##   .. .. .. .. .. .. .. .. ..$ k        : num -0.772
##   .. .. .. .. .. .. .. .. ..$ m        : num 0.629
##   .. .. .. .. .. .. .. .. ..$ delta    : num [1:25(1d)] -0.000753139 -0.164279523 5.573438267 0.000000117 -4.736478012 ...
##   .. .. .. .. .. .. .. .. ..$ sigma_obs: num 0.0392
##   .. .. .. .. .. .. .. .. ..$ beta     : num [1(1d)] 0
##   .. .. .. .. .. .. .. .. ..$ trend    : num [1:2979(1d)] 0.629 0.629 0.628 0.628 0.628 ...
##   .. .. .. .. .. .. .. ..$ value      : num 7625
##   .. .. .. .. .. .. .. ..$ return_code: int 0
##   .. .. .. .. .. .. .. ..$ theta_tilde: num [1, 1:3008] -0.771812 0.6287 -0.000753 -0.16428 5.573438 ...
##   .. .. .. .. .. .. .. .. ..- attr(*, "dimnames")=List of 2
##   .. .. .. .. .. .. .. .. .. ..$ : NULL
##   .. .. .. .. .. .. .. .. .. ..$ : chr [1:3008] "k" "m" "delta[1]" "delta[2]" ...
##   .. .. .. .. .. .. ..$ params                 :List of 6
##   .. .. .. .. .. .. .. ..$ k        : num -0.772
##   .. .. .. .. .. .. .. ..$ m        : num 0.629
##   .. .. .. .. .. .. .. ..$ delta    : num [1, 1:25] -0.000753139 -0.164279523 5.573438267 0.000000117 -4.736478012 ...
##   .. .. .. .. .. .. .. ..$ sigma_obs: num 0.0392
##   .. .. .. .. .. .. .. ..$ beta     : num [1, 1] 0
##   .. .. .. .. .. .. .. ..$ trend    : num [1:2979(1d)] 0.629 0.629 0.628 0.628 0.628 ...
##   .. .. .. .. .. .. ..$ history                : tibble [2,979 × 5] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ y       : num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. .. .. ..$ ds      : POSIXct[1:2979], format: "2011-11-29" ...
##   .. .. .. .. .. .. .. ..$ floor   : num [1:2979] 0 0 0 0 0 0 0 0 0 0 ...
##   .. .. .. .. .. .. .. ..$ t       : num [1:2979] 0 0.00023 0.00046 0.00069 0.00138 ...
##   .. .. .. .. .. .. .. ..$ y_scaled: num [1:2979] 0.704 0.704 0.657 0.63 0.63 ...
##   .. .. .. .. .. .. ..$ history.dates          : POSIXct[1:2979], format: "2011-11-29" ...
##   .. .. .. .. .. .. ..$ train.holiday.names    : NULL
##   .. .. .. .. .. .. ..$ train.component.cols   :'data.frame':    1 obs. of  3 variables:
##   .. .. .. .. .. .. .. ..$ zeros               : int 1
##   .. .. .. .. .. .. .. ..$ additive_terms      : num 0
##   .. .. .. .. .. .. .. ..$ multiplicative_terms: num 0
##   .. .. .. .. .. .. ..$ component.modes        :List of 2
##   .. .. .. .. .. .. .. ..$ additive      : chr [1:3] "additive_terms" "extra_regressors_additive" "holidays"
##   .. .. .. .. .. .. .. ..$ multiplicative: chr [1:2] "multiplicative_terms" "extra_regressors_multiplicative"
##   .. .. .. .. .. .. ..$ fit.kwargs             : list()
##   .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "prophet" "list"
##   .. .. .. .. .. ..$ model_2:List of 9
##   .. .. .. .. .. .. ..$ handle        :Class 'xgb.Booster.handle' <externalptr> 
##   .. .. .. .. .. .. ..$ raw           : raw [1:317746] 7b 4c 00 00 ...
##   .. .. .. .. .. .. ..$ niter         : num 300
##   .. .. .. .. .. .. ..$ evaluation_log:Classes 'data.table' and 'data.frame':    300 obs. of  2 variables:
##   .. .. .. .. .. .. .. ..$ iter         : num [1:300] 1 2 3 4 5 6 7 8 9 10 ...
##   .. .. .. .. .. .. .. ..$ training_rmse: num [1:300] 0.481 0.396 0.353 0.319 0.3 ...
##   .. .. .. .. .. .. .. ..- attr(*, ".internal.selfref")=<externalptr> 
##   .. .. .. .. .. .. ..$ call          : language xgboost::xgb.train(params = list(eta = 0.35, max_depth = 3, gamma = 0.15,      colsample_bytree = 1, colsample_by| __truncated__ ...
##   .. .. .. .. .. .. ..$ params        :List of 10
##   .. .. .. .. .. .. .. ..$ eta                : num 0.35
##   .. .. .. .. .. .. .. ..$ max_depth          : num 3
##   .. .. .. .. .. .. .. ..$ gamma              : num 0.15
##   .. .. .. .. .. .. .. ..$ colsample_bytree   : num 1
##   .. .. .. .. .. .. .. ..$ colsample_bynode   : num 0.75
##   .. .. .. .. .. .. .. ..$ min_child_weight   : num 20
##   .. .. .. .. .. .. .. ..$ subsample          : num 1
##   .. .. .. .. .. .. .. ..$ objective          : chr "reg:squarederror"
##   .. .. .. .. .. .. .. ..$ nthread            : num 1
##   .. .. .. .. .. .. .. ..$ validate_parameters: logi TRUE
##   .. .. .. .. .. .. ..$ callbacks     :List of 1
##   .. .. .. .. .. .. .. ..$ cb.evaluation.log:function (env = parent.frame(), finalize = FALSE)  
##   .. .. .. .. .. .. .. .. ..- attr(*, "call")= language cb.evaluation.log()
##   .. .. .. .. .. .. .. .. ..- attr(*, "name")= chr "cb.evaluation.log"
##   .. .. .. .. .. .. ..$ feature_names : chr [1:16] "time_index_num" "time_year" "time_half" "time_quarter" ...
##   .. .. .. .. .. .. ..$ nfeatures     : int 16
##   .. .. .. .. .. .. ..- attr(*, "class")= chr "xgb.Booster"
##   .. .. .. .. ..$ data  : tibble [2,979 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. ..$ time      : Date[1:2979], format: "2011-11-29" ...
##   .. .. .. .. .. ..$ .actual   : num [1:2979] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. .. .. ..$ .fitted   : num [1:2979] 6.45 6.45 6.38 6.28 6.24 ...
##   .. .. .. .. .. ..$ .residuals: num [1:2979] 0.4338 0.4355 0.0316 -0.126 -0.082 ...
##   .. .. .. .. ..$ extras:List of 2
##   .. .. .. .. .. ..$ xreg_recipe    :List of 9
##   .. .. .. .. .. .. ..$ var_info      : tibble [17 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. ..$ type    :List of 17
##   .. .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ role    : chr [1:17] "predictor" "predictor" "predictor" "predictor" ...
##   .. .. .. .. .. .. .. ..$ source  : chr [1:17] "original" "original" "original" "original" ...
##   .. .. .. .. .. .. ..$ term_info     : tibble [16 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:16] "time_index_num" "time_year" "time_half" "time_quarter" ...
##   .. .. .. .. .. .. .. ..$ type    :List of 16
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ role    : chr [1:16] "predictor" "predictor" "predictor" "predictor" ...
##   .. .. .. .. .. .. .. ..$ source  : chr [1:16] "derived" "original" "original" "original" ...
##   .. .. .. .. .. .. ..$ steps         :List of 3
##   .. .. .. .. .. .. .. ..$ :List of 7
##   .. .. .. .. .. .. .. .. ..$ terms  :List of 1
##   .. .. .. .. .. .. .. .. .. ..$ : language ~dplyr::everything()
##   .. .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180cb6ed420> 
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. .. ..$ fn     :function (string, case = "snake", replace = c(`'` = "", `"` = "", `%` = "_percent_", 
##     `#` = "_number_"), ascii = TRUE, use_make_names = TRUE, allow_dupes = FALSE, 
##     sep_in = "\\.", transliterations = "Latin-ASCII", parsing_option = 1, 
##     numerals = "asis", ...)  
##   .. .. .. .. .. .. .. .. ..$ role   : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ trained: logi TRUE
##   .. .. .. .. .. .. .. .. ..$ inputs : Named chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr [1:17] "time" "time_index.num" "time_year" "time_half" ...
##   .. .. .. .. .. .. .. .. ..$ skip   : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ id     : chr "rename_at_QnRgT"
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rename_at" "step"
##   .. .. .. .. .. .. .. ..$ :List of 6
##   .. .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. .. ..$ : language ~names_date
##   .. .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180c4afdb70> 
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. .. ..$ removals: Named chr "time"
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr "time"
##   .. .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ id      : chr "rm_IpB8h"
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_rm" "step"
##   .. .. .. .. .. .. .. ..$ :List of 7
##   .. .. .. .. .. .. .. .. ..$ terms   :List of 1
##   .. .. .. .. .. .. .. .. .. ..$ : language ~recipes::all_predictors()
##   .. .. .. .. .. .. .. .. .. .. ..- attr(*, ".Environment")=<environment: 0x00000180c49aea38> 
##   .. .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "quosures" "list"
##   .. .. .. .. .. .. .. .. ..$ role    : logi NA
##   .. .. .. .. .. .. .. .. ..$ trained : logi TRUE
##   .. .. .. .. .. .. .. .. ..$ group   : NULL
##   .. .. .. .. .. .. .. .. ..$ removals: chr(0) 
##   .. .. .. .. .. .. .. .. ..$ skip    : logi FALSE
##   .. .. .. .. .. .. .. .. ..$ id      : chr "zv_BYWXf"
##   .. .. .. .. .. .. .. .. ..- attr(*, "class")= chr [1:2] "step_zv" "step"
##   .. .. .. .. .. .. ..$ template      : tibble [2,979 × 16] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ time_index_num: num [1:2979] 1322524800 1322611200 1322697600 1322784000 1323043200 ...
##   .. .. .. .. .. .. .. ..$ time_year     : int [1:2979] 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
##   .. .. .. .. .. .. .. ..$ time_half     : int [1:2979] 2 2 2 2 2 2 2 2 2 2 ...
##   .. .. .. .. .. .. .. ..$ time_quarter  : int [1:2979] 4 4 4 4 4 4 4 4 4 4 ...
##   .. .. .. .. .. .. .. ..$ time_month    : int [1:2979] 11 11 12 12 12 12 12 12 12 12 ...
##   .. .. .. .. .. .. .. ..$ time_day      : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. .. .. .. ..$ time_wday     : int [1:2979] 3 4 5 6 2 3 4 5 6 2 ...
##   .. .. .. .. .. .. .. ..$ time_mday     : int [1:2979] 29 30 1 2 5 6 7 8 9 12 ...
##   .. .. .. .. .. .. .. ..$ time_qday     : int [1:2979] 60 61 62 63 66 67 68 69 70 73 ...
##   .. .. .. .. .. .. .. ..$ time_yday     : int [1:2979] 333 334 335 336 339 340 341 342 343 346 ...
##   .. .. .. .. .. .. .. ..$ time_mweek    : int [1:2979] 5 5 1 1 2 2 2 2 2 3 ...
##   .. .. .. .. .. .. .. ..$ time_week     : int [1:2979] 48 48 48 48 49 49 49 49 49 50 ...
##   .. .. .. .. .. .. .. ..$ time_week2    : int [1:2979] 0 0 0 0 1 1 1 1 1 0 ...
##   .. .. .. .. .. .. .. ..$ time_week3    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. .. .. .. ..$ time_week4    : int [1:2979] 0 0 0 0 1 1 1 1 1 2 ...
##   .. .. .. .. .. .. .. ..$ time_mday7    : int [1:2979] 5 5 1 1 1 1 2 2 2 2 ...
##   .. .. .. .. .. .. ..$ retained      : logi TRUE
##   .. .. .. .. .. .. ..$ requirements  :List of 1
##   .. .. .. .. .. .. .. ..$ bake: Named logi(0) 
##   .. .. .. .. .. .. .. .. ..- attr(*, "names")= chr(0) 
##   .. .. .. .. .. .. ..$ tr_info       :'data.frame': 1 obs. of  2 variables:
##   .. .. .. .. .. .. .. ..$ nrows    : int 2979
##   .. .. .. .. .. .. .. ..$ ncomplete: int 2979
##   .. .. .. .. .. .. ..$ orig_lvls     :List of 17
##   .. .. .. .. .. .. .. ..$ time          :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_index.num:List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_year     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_half     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_quarter  :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_month    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_day      :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_wday     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_mday     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_qday     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_yday     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_mweek    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_week     :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_week2    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_week3    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_week4    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. .. ..$ time_mday7    :List of 2
##   .. .. .. .. .. .. .. .. ..$ values : logi NA
##   .. .. .. .. .. .. .. .. ..$ ordered: logi NA
##   .. .. .. .. .. .. ..$ last_term_info: gropd_df [18 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "time_day" "time_half" "time_index.num" ...
##   .. .. .. .. .. .. .. ..$ type    :List of 18
##   .. .. .. .. .. .. .. .. ..$ : chr "date"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "double" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. .. ..$ : chr [1:2] "integer" "numeric"
##   .. .. .. .. .. .. .. ..$ role    :List of 18
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. .. ..$ : chr "predictor"
##   .. .. .. .. .. .. .. ..$ source  : chr [1:18] "original" "original" "original" "original" ...
##   .. .. .. .. .. .. .. ..$ number  : num [1:18] 1 3 3 0 3 3 3 3 3 3 ...
##   .. .. .. .. .. .. .. ..$ skip    : logi [1:18] FALSE FALSE FALSE FALSE FALSE FALSE ...
##   .. .. .. .. .. .. .. ..- attr(*, "groups")= tibble [18 × 2] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. .. .. .. .. ..$ variable: chr [1:18] "time" "time_day" "time_half" "time_index.num" ...
##   .. .. .. .. .. .. .. .. ..$ .rows   : list<int> [1:18] 
##   .. .. .. .. .. .. .. .. .. ..$ : int 1
##   .. .. .. .. .. .. .. .. .. ..$ : int 2
##   .. .. .. .. .. .. .. .. .. ..$ : int 3
##   .. .. .. .. .. .. .. .. .. ..$ : int 4
##   .. .. .. .. .. .. .. .. .. ..$ : int 5
##   .. .. .. .. .. .. .. .. .. ..$ : int 6
##   .. .. .. .. .. .. .. .. .. ..$ : int 7
##   .. .. .. .. .. .. .. .. .. ..$ : int 8
##   .. .. .. .. .. .. .. .. .. ..$ : int 9
##   .. .. .. .. .. .. .. .. .. ..$ : int 10
##   .. .. .. .. .. .. .. .. .. ..$ : int 11
##   .. .. .. .. .. .. .. .. .. ..$ : int 12
##   .. .. .. .. .. .. .. .. .. ..$ : int 13
##   .. .. .. .. .. .. .. .. .. ..$ : int 14
##   .. .. .. .. .. .. .. .. .. ..$ : int 15
##   .. .. .. .. .. .. .. .. .. ..$ : int 16
##   .. .. .. .. .. .. .. .. .. ..$ : int 17
##   .. .. .. .. .. .. .. .. .. ..$ : int 18
##   .. .. .. .. .. .. .. .. .. ..@ ptype: int(0) 
##   .. .. .. .. .. .. .. .. ..- attr(*, ".drop")= logi TRUE
##   .. .. .. .. .. .. ..- attr(*, "class")= chr "recipe"
##   .. .. .. .. .. ..$ logistic_params:List of 3
##   .. .. .. .. .. .. ..$ growth        : chr "linear"
##   .. .. .. .. .. .. ..$ logistic_cap  : NULL
##   .. .. .. .. .. .. ..$ logistic_floor: NULL
##   .. .. .. .. ..$ desc  : chr "PROPHET w/ XGBoost Errors"
##   .. .. .. .. ..- attr(*, "class")= chr [1:2] "prophet_xgboost_fit_impl" "modeltime_bridge"
##   .. .. .. ..$ preproc     :List of 1
##   .. .. .. .. ..$ y_var: chr(0) 
##   .. .. .. ..$ elapsed     :List of 1
##   .. .. .. .. ..$ elapsed: num NA
##   .. .. .. ..$ censor_probs: list()
##   .. .. .. ..- attr(*, "class")= chr [1:2] "_prophet_xgboost_fit_impl" "model_fit"
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_fit" "stage"
##   .. ..$ post   :List of 1
##   .. .. ..$ actions: Named list()
##   .. .. ..- attr(*, "class")= chr [1:2] "stage_post" "stage"
##   .. ..$ trained: logi TRUE
##   .. ..- attr(*, "class")= chr "workflow"
##  $ .model_desc      : chr [1:10] "PROPHET" "GLMNET" "KERNLAB" "KERNLAB" ...
##  $ .type            : chr [1:10] "Test" "Test" "Test" "Test" ...
##  $ .calibration_data:List of 10
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 6.88 6.87 6.85 6.84 6.82 ...
##   .. ..$ .residuals : num [1:744] -0.187 -0.213 -0.23 -0.233 -0.195 ...
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 7.82 7.81 7.84 7.83 7.83 ...
##   .. ..$ .residuals : num [1:744] -1.13 -1.15 -1.22 -1.23 -1.2 ...
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 7.44 7.46 7.41 7.42 7.44 ...
##   .. ..$ .residuals : num [1:744] -0.753 -0.797 -0.791 -0.815 -0.807 ...
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 6.77 6.79 6.84 6.84 6.81 ...
##   .. ..$ .residuals : num [1:744] -0.0801 -0.1318 -0.2208 -0.2274 -0.1849 ...
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 7.47 7.48 7.44 7.41 7.39 ...
##   .. ..$ .residuals : num [1:744] -0.782 -0.825 -0.823 -0.799 -0.759 ...
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 6.82 6.82 6.82 6.82 6.82 ...
##   .. ..$ .residuals : num [1:744] -0.129 -0.16 -0.2 -0.212 -0.192 ...
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 6.8 6.77 6.79 6.79 6.79 ...
##   .. ..$ .residuals : num [1:744] -0.107 -0.115 -0.168 -0.179 -0.161 ...
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 6.85 6.83 6.82 6.8 6.73 ...
##   .. ..$ .residuals : num [1:744] -0.161 -0.171 -0.197 -0.195 -0.103 ...
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 6.79 6.79 6.78 6.76 6.73 ...
##   .. ..$ .residuals : num [1:744] -0.102 -0.129 -0.155 -0.15 -0.105 ...
##   ..$ : tibble [744 × 4] (S3: tbl_df/tbl/data.frame)
##   .. ..$ time       : Date[1:744], format: "2020-10-19" "2020-10-20" ...
##   .. ..$ .actual    : num [1:744] 6.69 6.66 6.62 6.61 6.63 ...
##   .. ..$ .prediction: num [1:744] 6.81 6.81 6.81 6.81 6.8 ...
##   .. ..$ .residuals : num [1:744] -0.122 -0.151 -0.188 -0.199 -0.176 ...
##  $ .resample_results:List of 10
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.516
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.545
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 1.88
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.303
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.595
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.16 7.18 7.2 7.26 7.29 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.29 7.29 7.29 7.32 7.38 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.38 7.32 7.24 7.02 6.96 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.99 6.97 6.96 6.96 6.96 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.04 7.06 7.05 7.06 7.07 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.334
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.13
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.457
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.482
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.255
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.19 7.18 7.17 7.2 7.2 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.42 7.41 7.41 7.4 7.41 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.44 7.44 7.43 7.49 7.48 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.98 6.97 6.96 6.94 7.01 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.27 7.26 7.24 7.22 7.17 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.249
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.377
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.282
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.294
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.3
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.11 7.11 7.11 7.1 7.1 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.22 7.2 7.19 7.17 7.18 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.73 7.72 7.71 7.81 7.8 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.85 6.83 6.82 6.8 6.86 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.27 7.25 7.23 7.21 7.22 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.32
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.195
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.678
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.365
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.348
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.2 7.19 7.18 7.19 7.2 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.47 7.46 7.47 7.47 7.5 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.27 7.27 7.25 7.32 7.33 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.92 6.91 6.9 6.9 6.94 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.44 7.41 7.39 7.38 7.44 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.569
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.421
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.966
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.396
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.593
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.48 7.45 7.38 7.43 7.42 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.69 7.69 7.73 7.77 7.76 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.87 6.85 6.8 6.9 6.94 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.1 7.08 7.06 7.07 7.12 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.68 7.63 7.59 7.61 7.68 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.276
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.654
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.481
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.36
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.407
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "25 columns were requested but there were 17 predictors in the data. 17 will be used."
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "25 columns were requested but there were 17 predictors in the data. 17 will be used."
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "25 columns were requested but there were 17 predictors in the data. 17 will be used."
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "25 columns were requested but there were 17 predictors in the data. 17 will be used."
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "25 columns were requested but there were 17 predictors in the data. 17 will be used."
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.12 7.12 7.12 7.13 7.13 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.34 7.34 7.34 7.34 7.34 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.67 7.67 7.67 7.67 7.67 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.97 6.97 6.97 6.97 6.97 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.41 7.41 7.41 7.41 7.41 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.249
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.381
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.727
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.314
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.171
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.08 7.08 7.08 7.08 7.07 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.13 7.21 7.2 7.22 7.23 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.34 7.35 7.35 7.36 7.36 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.94 6.94 6.94 6.94 6.94 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.03 7.02 7.02 6.94 7.01 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.158
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.846
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.318
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.188
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.415
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "The number of neighbors should be >= 0 and <= 9. Truncating the value."
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "The number of neighbors should be >= 0 and <= 9. Truncating the value."
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "The number of neighbors should be >= 0 and <= 9. Truncating the value."
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "The number of neighbors should be >= 0 and <= 9. Truncating the value."
##   .. .. ..$ : tibble [1 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr "preprocessor 1/1, model 1/1"
##   .. .. .. ..$ type    : chr "warning"
##   .. .. .. ..$ note    : chr "The number of neighbors should be >= 0 and <= 9. Truncating the value."
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.1 7.1 7.1 7.12 7.11 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.13 7.13 7.12 7.1 7.05 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.45 7.45 7.46 7.48 7.54 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.93 6.92 6.9 6.89 6.9 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.13 7.12 7.09 7.08 7.06 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.248
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.211
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.757
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.65
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.457
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.08 7.07 7.07 7.07 7.06 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.35 7.4 7.43 7.45 7.45 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.39 7.38 7.38 7.36 7.34 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.98 7 7.02 7.05 7.07 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.23 7.26 7.31 7.31 7.31 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA
##   ..$ : rsmp[+] (S3: resample_results/tune_results/tbl_df/tbl/data.frame)
##   .. ..$ splits      :List of 5
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ out_id: int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice1"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ out_id: int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice2"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ out_id: int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice3"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ out_id: int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice4"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. .. ..$ :List of 4
##   .. .. .. ..$ data  :'data.frame':  2235 obs. of  2 variables:
##   .. .. .. .. ..$ time : Date[1:2235], format: "2011-11-29" ...
##   .. .. .. .. ..$ close: num [1:2235] 6.88 6.88 6.41 6.16 6.16 ...
##   .. .. .. ..$ in_id : int [1:252] 912 913 914 915 916 917 918 919 920 921 ...
##   .. .. .. ..$ out_id: int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ id    : tibble [1 × 1] (S3: tbl_df/tbl/data.frame)
##   .. .. .. .. ..$ id: chr "Slice5"
##   .. .. .. ..- attr(*, "class")= chr [1:2] "ts_cv_split" "rsplit"
##   .. ..$ id          : chr [1:5] "Slice1" "Slice2" "Slice3" "Slice4" ...
##   .. ..$ .metrics    :List of 5
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.588
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.223
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.23
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.178
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. .. ..$ : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .metric   : chr "rmse"
##   .. .. .. ..$ .estimator: chr "standard"
##   .. .. .. ..$ .estimate : num 0.527
##   .. .. .. ..$ .config   : chr "Preprocessor1_Model1"
##   .. ..$ .notes      :List of 5
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. .. ..$ : tibble [0 × 3] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ location: chr(0) 
##   .. .. .. ..$ type    : chr(0) 
##   .. .. .. ..$ note    : chr(0) 
##   .. ..$ .predictions:List of 5
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.99 6.98 6.97 6.93 6.92 ...
##   .. .. .. ..$ .row   : int [1:64] 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 ...
##   .. .. .. ..$ close  : num [1:64] 7.07 7.04 7.06 7.07 7.05 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.4 7.4 7.39 7.39 7.37 ...
##   .. .. .. ..$ .row   : int [1:64] 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 ...
##   .. .. .. ..$ close  : num [1:64] 7.1 7.12 7.14 7.14 7.18 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.67 7.68 7.69 7.72 7.73 ...
##   .. .. .. ..$ .row   : int [1:64] 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 ...
##   .. .. .. ..$ close  : num [1:64] 7.52 7.51 7.55 7.55 7.59 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 6.91 6.91 6.9 6.9 6.91 ...
##   .. .. .. ..$ .row   : int [1:64] 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 ...
##   .. .. .. ..$ close  : num [1:64] 6.93 6.96 7 6.98 7 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. .. ..$ : tibble [64 × 4] (S3: tbl_df/tbl/data.frame)
##   .. .. .. ..$ .pred  : num [1:64] 7.05 7.04 7.03 7.02 7.01 ...
##   .. .. .. ..$ .row   : int [1:64] 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 ...
##   .. .. .. ..$ close  : num [1:64] 6.96 6.87 6.97 6.86 6.88 ...
##   .. .. .. ..$ .config: chr [1:64] "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" "Preprocessor1_Model1" ...
##   .. ..- attr(*, "parameters")= paramtrs [0 × 6] (S3: parameters/tbl_df/tbl/data.frame)
##   .. .. ..$ name        : chr(0) 
##   .. .. ..$ id          : chr(0) 
##   .. .. ..$ source      : chr(0) 
##   .. .. ..$ component   : chr(0) 
##   .. .. ..$ component_id: chr(0) 
##   .. .. ..$ object      : list()
##   .. ..- attr(*, "metrics")=function (data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)  
##   .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric_set" "metric_set" "function"
##   .. .. ..- attr(*, "metrics")=List of 1
##   .. .. .. ..$ rmse:function (data, ...)  
##   .. .. .. .. ..- attr(*, "direction")= chr "minimize"
##   .. .. .. .. ..- attr(*, "class")= chr [1:3] "numeric_metric" "metric" "function"
##   .. ..- attr(*, "outcomes")= chr "close"
##   .. ..- attr(*, "rset_info")=List of 2
##   .. .. ..$ att  :List of 8
##   .. .. .. ..$ class      : chr "time_series_cv"
##   .. .. .. ..$ initial    : num 252
##   .. .. .. ..$ assess     : num 64
##   .. .. .. ..$ cumulative : logi FALSE
##   .. .. .. ..$ skip       : num 252
##   .. .. .. ..$ lag        : num 0
##   .. .. .. ..$ slice_limit: num 5
##   .. .. .. ..$ fingerprint: chr "ed270d80c0e4efa2eb273ba7489ab90f"
##   .. .. ..$ label: chr NA

Cubist Stacking

set.seed(123)
ensemble_fit_cubist_tscv <- submodels_resample %>%
    ensemble_model_spec(
        model_spec = cubist_rules(mode = "regression",
            committees = tune(), 
            neighbors  = tune(),
            max_rules  = tune()
        ) %>%
            set_engine("Cubist"),
        # kfold = 10,
        grid  = 10, 
        control = control_grid(
            verbose = TRUE, 
            allow_par = TRUE
        )
    )
## ── Tuning Model Specification ───────────────────────────────────
## ℹ Performing 5-Fold Cross Validation.
## i Fold1: preprocessor 1/1
## ✓ Fold1: preprocessor 1/1
## i Fold1: preprocessor 1/1, model 1/10
## ✓ Fold1: preprocessor 1/1, model 1/10
## i Fold1: preprocessor 1/1, model 1/10 (predictions)
## i Fold1: preprocessor 1/1, model 2/10
## ✓ Fold1: preprocessor 1/1, model 2/10
## i Fold1: preprocessor 1/1, model 2/10 (predictions)
## i Fold1: preprocessor 1/1, model 3/10
## ✓ Fold1: preprocessor 1/1, model 3/10
## i Fold1: preprocessor 1/1, model 3/10 (predictions)
## i Fold1: preprocessor 1/1, model 4/10
## ✓ Fold1: preprocessor 1/1, model 4/10
## i Fold1: preprocessor 1/1, model 4/10 (predictions)
## i Fold1: preprocessor 1/1, model 5/10
## ✓ Fold1: preprocessor 1/1, model 5/10
## i Fold1: preprocessor 1/1, model 5/10 (predictions)
## i Fold1: preprocessor 1/1, model 6/10
## ✓ Fold1: preprocessor 1/1, model 6/10
## i Fold1: preprocessor 1/1, model 6/10 (predictions)
## i Fold1: preprocessor 1/1, model 7/10
## ✓ Fold1: preprocessor 1/1, model 7/10
## i Fold1: preprocessor 1/1, model 7/10 (predictions)
## i Fold1: preprocessor 1/1, model 8/10
## ✓ Fold1: preprocessor 1/1, model 8/10
## i Fold1: preprocessor 1/1, model 8/10 (predictions)
## i Fold1: preprocessor 1/1, model 9/10
## ✓ Fold1: preprocessor 1/1, model 9/10
## i Fold1: preprocessor 1/1, model 9/10 (predictions)
## i Fold1: preprocessor 1/1, model 10/10
## ✓ Fold1: preprocessor 1/1, model 10/10
## i Fold1: preprocessor 1/1, model 10/10 (predictions)
## i Fold2: preprocessor 1/1
## ✓ Fold2: preprocessor 1/1
## i Fold2: preprocessor 1/1, model 1/10
## ✓ Fold2: preprocessor 1/1, model 1/10
## i Fold2: preprocessor 1/1, model 1/10 (predictions)
## i Fold2: preprocessor 1/1, model 2/10
## ✓ Fold2: preprocessor 1/1, model 2/10
## i Fold2: preprocessor 1/1, model 2/10 (predictions)
## i Fold2: preprocessor 1/1, model 3/10
## ✓ Fold2: preprocessor 1/1, model 3/10
## i Fold2: preprocessor 1/1, model 3/10 (predictions)
## i Fold2: preprocessor 1/1, model 4/10
## ✓ Fold2: preprocessor 1/1, model 4/10
## i Fold2: preprocessor 1/1, model 4/10 (predictions)
## i Fold2: preprocessor 1/1, model 5/10
## ✓ Fold2: preprocessor 1/1, model 5/10
## i Fold2: preprocessor 1/1, model 5/10 (predictions)
## i Fold2: preprocessor 1/1, model 6/10
## ✓ Fold2: preprocessor 1/1, model 6/10
## i Fold2: preprocessor 1/1, model 6/10 (predictions)
## i Fold2: preprocessor 1/1, model 7/10
## ✓ Fold2: preprocessor 1/1, model 7/10
## i Fold2: preprocessor 1/1, model 7/10 (predictions)
## i Fold2: preprocessor 1/1, model 8/10
## ✓ Fold2: preprocessor 1/1, model 8/10
## i Fold2: preprocessor 1/1, model 8/10 (predictions)
## i Fold2: preprocessor 1/1, model 9/10
## ✓ Fold2: preprocessor 1/1, model 9/10
## i Fold2: preprocessor 1/1, model 9/10 (predictions)
## i Fold2: preprocessor 1/1, model 10/10
## ✓ Fold2: preprocessor 1/1, model 10/10
## i Fold2: preprocessor 1/1, model 10/10 (predictions)
## i Fold3: preprocessor 1/1
## ✓ Fold3: preprocessor 1/1
## i Fold3: preprocessor 1/1, model 1/10
## ✓ Fold3: preprocessor 1/1, model 1/10
## i Fold3: preprocessor 1/1, model 1/10 (predictions)
## i Fold3: preprocessor 1/1, model 2/10
## ✓ Fold3: preprocessor 1/1, model 2/10
## i Fold3: preprocessor 1/1, model 2/10 (predictions)
## i Fold3: preprocessor 1/1, model 3/10
## ✓ Fold3: preprocessor 1/1, model 3/10
## i Fold3: preprocessor 1/1, model 3/10 (predictions)
## i Fold3: preprocessor 1/1, model 4/10
## ✓ Fold3: preprocessor 1/1, model 4/10
## i Fold3: preprocessor 1/1, model 4/10 (predictions)
## i Fold3: preprocessor 1/1, model 5/10
## ✓ Fold3: preprocessor 1/1, model 5/10
## i Fold3: preprocessor 1/1, model 5/10 (predictions)
## i Fold3: preprocessor 1/1, model 6/10
## ✓ Fold3: preprocessor 1/1, model 6/10
## i Fold3: preprocessor 1/1, model 6/10 (predictions)
## i Fold3: preprocessor 1/1, model 7/10
## ✓ Fold3: preprocessor 1/1, model 7/10
## i Fold3: preprocessor 1/1, model 7/10 (predictions)
## i Fold3: preprocessor 1/1, model 8/10
## ✓ Fold3: preprocessor 1/1, model 8/10
## i Fold3: preprocessor 1/1, model 8/10 (predictions)
## i Fold3: preprocessor 1/1, model 9/10
## ✓ Fold3: preprocessor 1/1, model 9/10
## i Fold3: preprocessor 1/1, model 9/10 (predictions)
## i Fold3: preprocessor 1/1, model 10/10
## ✓ Fold3: preprocessor 1/1, model 10/10
## i Fold3: preprocessor 1/1, model 10/10 (predictions)
## i Fold4: preprocessor 1/1
## ✓ Fold4: preprocessor 1/1
## i Fold4: preprocessor 1/1, model 1/10
## ✓ Fold4: preprocessor 1/1, model 1/10
## i Fold4: preprocessor 1/1, model 1/10 (predictions)
## i Fold4: preprocessor 1/1, model 2/10
## ✓ Fold4: preprocessor 1/1, model 2/10
## i Fold4: preprocessor 1/1, model 2/10 (predictions)
## i Fold4: preprocessor 1/1, model 3/10
## ✓ Fold4: preprocessor 1/1, model 3/10
## i Fold4: preprocessor 1/1, model 3/10 (predictions)
## i Fold4: preprocessor 1/1, model 4/10
## ✓ Fold4: preprocessor 1/1, model 4/10
## i Fold4: preprocessor 1/1, model 4/10 (predictions)
## i Fold4: preprocessor 1/1, model 5/10
## ✓ Fold4: preprocessor 1/1, model 5/10
## i Fold4: preprocessor 1/1, model 5/10 (predictions)
## i Fold4: preprocessor 1/1, model 6/10
## ✓ Fold4: preprocessor 1/1, model 6/10
## i Fold4: preprocessor 1/1, model 6/10 (predictions)
## i Fold4: preprocessor 1/1, model 7/10
## ✓ Fold4: preprocessor 1/1, model 7/10
## i Fold4: preprocessor 1/1, model 7/10 (predictions)
## i Fold4: preprocessor 1/1, model 8/10
## ✓ Fold4: preprocessor 1/1, model 8/10
## i Fold4: preprocessor 1/1, model 8/10 (predictions)
## i Fold4: preprocessor 1/1, model 9/10
## ✓ Fold4: preprocessor 1/1, model 9/10
## i Fold4: preprocessor 1/1, model 9/10 (predictions)
## i Fold4: preprocessor 1/1, model 10/10
## ✓ Fold4: preprocessor 1/1, model 10/10
## i Fold4: preprocessor 1/1, model 10/10 (predictions)
## i Fold5: preprocessor 1/1
## ✓ Fold5: preprocessor 1/1
## i Fold5: preprocessor 1/1, model 1/10
## ✓ Fold5: preprocessor 1/1, model 1/10
## i Fold5: preprocessor 1/1, model 1/10 (predictions)
## i Fold5: preprocessor 1/1, model 2/10
## ✓ Fold5: preprocessor 1/1, model 2/10
## i Fold5: preprocessor 1/1, model 2/10 (predictions)
## i Fold5: preprocessor 1/1, model 3/10
## ✓ Fold5: preprocessor 1/1, model 3/10
## i Fold5: preprocessor 1/1, model 3/10 (predictions)
## i Fold5: preprocessor 1/1, model 4/10
## ✓ Fold5: preprocessor 1/1, model 4/10
## i Fold5: preprocessor 1/1, model 4/10 (predictions)
## i Fold5: preprocessor 1/1, model 5/10
## ✓ Fold5: preprocessor 1/1, model 5/10
## i Fold5: preprocessor 1/1, model 5/10 (predictions)
## i Fold5: preprocessor 1/1, model 6/10
## ✓ Fold5: preprocessor 1/1, model 6/10
## i Fold5: preprocessor 1/1, model 6/10 (predictions)
## i Fold5: preprocessor 1/1, model 7/10
## ✓ Fold5: preprocessor 1/1, model 7/10
## i Fold5: preprocessor 1/1, model 7/10 (predictions)
## i Fold5: preprocessor 1/1, model 8/10
## ✓ Fold5: preprocessor 1/1, model 8/10
## i Fold5: preprocessor 1/1, model 8/10 (predictions)
## i Fold5: preprocessor 1/1, model 9/10
## ✓ Fold5: preprocessor 1/1, model 9/10
## i Fold5: preprocessor 1/1, model 9/10 (predictions)
## i Fold5: preprocessor 1/1, model 10/10
## ✓ Fold5: preprocessor 1/1, model 10/10
## i Fold5: preprocessor 1/1, model 10/10 (predictions)
## ✔ Finished tuning Model Specification.
## ℹ Model Parameters:
## # A tibble: 1 × 9
##   committees neighbors max_rules .metric .estimator   mean     n std_err .config
##        <int>     <int>     <int> <chr>   <chr>       <dbl> <int>   <dbl> <chr>  
## 1         70         2       378 rmse    standard   0.0688     5 0.00526 Prepro…
## ℹ Prediction Error Comparison:
## # A tibble: 11 × 3
##    .model_id   rmse .model_desc              
##    <chr>      <dbl> <chr>                    
##  1 1         0.952  PROPHET                  
##  2 10        0.389  PROPHET W/ XGBOOST ERRORS
##  3 2         0.356  GLMNET                   
##  4 3         0.303  KERNLAB                  
##  5 4         0.413  KERNLAB                  
##  6 5         0.623  KKNN                     
##  7 6         0.454  RANDOMFOREST             
##  8 7         0.415  XGBOOST                  
##  9 8         0.458  CUBIST                   
## 10 9         0.512  NNAR(2,1,10)[5]          
## 11 ensemble  0.0283 ENSEMBLE (MODEL SPEC)    
## 
## ── Final Model ──────────────────────────────────────────────────
## ℹ Model Workflow:
## ══ Workflow [trained] ══════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: cubist_rules()
## 
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 0 Recipe Steps
## 
## ── Model ───────────────────────────────────────────────────────────────────────
## 
## Call:
## cubist.default(x = x, y = y, committees = 70L, control
##  = Cubist::cubistControl(rules = 378L))
## 
## Number of samples: 320 
## Number of predictors: 10 
## 
## Number of committees: 70 
## Number of rules per committee: 10, 6, 7, 5, 7, 7, 6, 5, 4, 5, 8, 7, 4, 9, 4, 8, 3, 12, 8, 6 ... 
## 
## 
## 29.67 sec elapsed
modeltime_table(
    ensemble_fit_cubist_tscv
) %>%
    modeltime_accuracy(testing(splits))
## # A tibble: 1 × 9
##   .model_id .model_desc                .type   mae  mape  mase smape  rmse   rsq
##       <int> <chr>                      <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1         1 ENSEMBLE (CUBIST STACK): … Test  0.139  2.08  4.38  2.10 0.169 0.861

XGBOOST Stack

set.seed(123)
ensemble_fit_xgboost_tscv <- submodels_resample %>%
    ensemble_model_spec(boost_tree(mode = "regression", 
                               # mtry = tune(), 
                               trees = tune(), 
                               min_n = tune(), 
                               tree_depth = tune(), 
                               learn_rate = tune(), 
                               loss_reduction = tune()) %>% 
  set_engine("xgboost"),
        grid  = 10, 
        control = control_grid(
            verbose = TRUE, 
            allow_par = TRUE
        )
    )
## ── Tuning Model Specification ───────────────────────────────────
## ℹ Performing 5-Fold Cross Validation.
## i Fold1: preprocessor 1/1
## ✓ Fold1: preprocessor 1/1
## i Fold1: preprocessor 1/1, model 1/10
## ✓ Fold1: preprocessor 1/1, model 1/10
## i Fold1: preprocessor 1/1, model 1/10 (predictions)
## i Fold1: preprocessor 1/1, model 2/10
## ✓ Fold1: preprocessor 1/1, model 2/10
## i Fold1: preprocessor 1/1, model 2/10 (predictions)
## i Fold1: preprocessor 1/1, model 3/10
## ✓ Fold1: preprocessor 1/1, model 3/10
## i Fold1: preprocessor 1/1, model 3/10 (predictions)
## i Fold1: preprocessor 1/1, model 4/10
## ✓ Fold1: preprocessor 1/1, model 4/10
## i Fold1: preprocessor 1/1, model 4/10 (predictions)
## i Fold1: preprocessor 1/1, model 5/10
## ✓ Fold1: preprocessor 1/1, model 5/10
## i Fold1: preprocessor 1/1, model 5/10 (predictions)
## i Fold1: preprocessor 1/1, model 6/10
## ✓ Fold1: preprocessor 1/1, model 6/10
## i Fold1: preprocessor 1/1, model 6/10 (predictions)
## i Fold1: preprocessor 1/1, model 7/10
## ✓ Fold1: preprocessor 1/1, model 7/10
## i Fold1: preprocessor 1/1, model 7/10 (predictions)
## i Fold1: preprocessor 1/1, model 8/10
## ✓ Fold1: preprocessor 1/1, model 8/10
## i Fold1: preprocessor 1/1, model 8/10 (predictions)
## i Fold1: preprocessor 1/1, model 9/10
## ✓ Fold1: preprocessor 1/1, model 9/10
## i Fold1: preprocessor 1/1, model 9/10 (predictions)
## i Fold1: preprocessor 1/1, model 10/10
## ✓ Fold1: preprocessor 1/1, model 10/10
## i Fold1: preprocessor 1/1, model 10/10 (predictions)
## i Fold2: preprocessor 1/1
## ✓ Fold2: preprocessor 1/1
## i Fold2: preprocessor 1/1, model 1/10
## ✓ Fold2: preprocessor 1/1, model 1/10
## i Fold2: preprocessor 1/1, model 1/10 (predictions)
## i Fold2: preprocessor 1/1, model 2/10
## ✓ Fold2: preprocessor 1/1, model 2/10
## i Fold2: preprocessor 1/1, model 2/10 (predictions)
## i Fold2: preprocessor 1/1, model 3/10
## ✓ Fold2: preprocessor 1/1, model 3/10
## i Fold2: preprocessor 1/1, model 3/10 (predictions)
## i Fold2: preprocessor 1/1, model 4/10
## ✓ Fold2: preprocessor 1/1, model 4/10
## i Fold2: preprocessor 1/1, model 4/10 (predictions)
## i Fold2: preprocessor 1/1, model 5/10
## ✓ Fold2: preprocessor 1/1, model 5/10
## i Fold2: preprocessor 1/1, model 5/10 (predictions)
## i Fold2: preprocessor 1/1, model 6/10
## ✓ Fold2: preprocessor 1/1, model 6/10
## i Fold2: preprocessor 1/1, model 6/10 (predictions)
## i Fold2: preprocessor 1/1, model 7/10
## ✓ Fold2: preprocessor 1/1, model 7/10
## i Fold2: preprocessor 1/1, model 7/10 (predictions)
## i Fold2: preprocessor 1/1, model 8/10
## ✓ Fold2: preprocessor 1/1, model 8/10
## i Fold2: preprocessor 1/1, model 8/10 (predictions)
## i Fold2: preprocessor 1/1, model 9/10
## ✓ Fold2: preprocessor 1/1, model 9/10
## i Fold2: preprocessor 1/1, model 9/10 (predictions)
## i Fold2: preprocessor 1/1, model 10/10
## ✓ Fold2: preprocessor 1/1, model 10/10
## i Fold2: preprocessor 1/1, model 10/10 (predictions)
## i Fold3: preprocessor 1/1
## ✓ Fold3: preprocessor 1/1
## i Fold3: preprocessor 1/1, model 1/10
## ✓ Fold3: preprocessor 1/1, model 1/10
## i Fold3: preprocessor 1/1, model 1/10 (predictions)
## i Fold3: preprocessor 1/1, model 2/10
## ✓ Fold3: preprocessor 1/1, model 2/10
## i Fold3: preprocessor 1/1, model 2/10 (predictions)
## i Fold3: preprocessor 1/1, model 3/10
## ✓ Fold3: preprocessor 1/1, model 3/10
## i Fold3: preprocessor 1/1, model 3/10 (predictions)
## i Fold3: preprocessor 1/1, model 4/10
## ✓ Fold3: preprocessor 1/1, model 4/10
## i Fold3: preprocessor 1/1, model 4/10 (predictions)
## i Fold3: preprocessor 1/1, model 5/10
## ✓ Fold3: preprocessor 1/1, model 5/10
## i Fold3: preprocessor 1/1, model 5/10 (predictions)
## i Fold3: preprocessor 1/1, model 6/10
## ✓ Fold3: preprocessor 1/1, model 6/10
## i Fold3: preprocessor 1/1, model 6/10 (predictions)
## i Fold3: preprocessor 1/1, model 7/10
## ✓ Fold3: preprocessor 1/1, model 7/10
## i Fold3: preprocessor 1/1, model 7/10 (predictions)
## i Fold3: preprocessor 1/1, model 8/10
## ✓ Fold3: preprocessor 1/1, model 8/10
## i Fold3: preprocessor 1/1, model 8/10 (predictions)
## i Fold3: preprocessor 1/1, model 9/10
## ✓ Fold3: preprocessor 1/1, model 9/10
## i Fold3: preprocessor 1/1, model 9/10 (predictions)
## i Fold3: preprocessor 1/1, model 10/10
## ✓ Fold3: preprocessor 1/1, model 10/10
## i Fold3: preprocessor 1/1, model 10/10 (predictions)
## i Fold4: preprocessor 1/1
## ✓ Fold4: preprocessor 1/1
## i Fold4: preprocessor 1/1, model 1/10
## ✓ Fold4: preprocessor 1/1, model 1/10
## i Fold4: preprocessor 1/1, model 1/10 (predictions)
## i Fold4: preprocessor 1/1, model 2/10
## ✓ Fold4: preprocessor 1/1, model 2/10
## i Fold4: preprocessor 1/1, model 2/10 (predictions)
## i Fold4: preprocessor 1/1, model 3/10
## ✓ Fold4: preprocessor 1/1, model 3/10
## i Fold4: preprocessor 1/1, model 3/10 (predictions)
## i Fold4: preprocessor 1/1, model 4/10
## ✓ Fold4: preprocessor 1/1, model 4/10
## i Fold4: preprocessor 1/1, model 4/10 (predictions)
## i Fold4: preprocessor 1/1, model 5/10
## ✓ Fold4: preprocessor 1/1, model 5/10
## i Fold4: preprocessor 1/1, model 5/10 (predictions)
## i Fold4: preprocessor 1/1, model 6/10
## ✓ Fold4: preprocessor 1/1, model 6/10
## i Fold4: preprocessor 1/1, model 6/10 (predictions)
## i Fold4: preprocessor 1/1, model 7/10
## ✓ Fold4: preprocessor 1/1, model 7/10
## i Fold4: preprocessor 1/1, model 7/10 (predictions)
## i Fold4: preprocessor 1/1, model 8/10
## ✓ Fold4: preprocessor 1/1, model 8/10
## i Fold4: preprocessor 1/1, model 8/10 (predictions)
## i Fold4: preprocessor 1/1, model 9/10
## ✓ Fold4: preprocessor 1/1, model 9/10
## i Fold4: preprocessor 1/1, model 9/10 (predictions)
## i Fold4: preprocessor 1/1, model 10/10
## ✓ Fold4: preprocessor 1/1, model 10/10
## i Fold4: preprocessor 1/1, model 10/10 (predictions)
## i Fold5: preprocessor 1/1
## ✓ Fold5: preprocessor 1/1
## i Fold5: preprocessor 1/1, model 1/10
## ✓ Fold5: preprocessor 1/1, model 1/10
## i Fold5: preprocessor 1/1, model 1/10 (predictions)
## i Fold5: preprocessor 1/1, model 2/10
## ✓ Fold5: preprocessor 1/1, model 2/10
## i Fold5: preprocessor 1/1, model 2/10 (predictions)
## i Fold5: preprocessor 1/1, model 3/10
## ✓ Fold5: preprocessor 1/1, model 3/10
## i Fold5: preprocessor 1/1, model 3/10 (predictions)
## i Fold5: preprocessor 1/1, model 4/10
## ✓ Fold5: preprocessor 1/1, model 4/10
## i Fold5: preprocessor 1/1, model 4/10 (predictions)
## i Fold5: preprocessor 1/1, model 5/10
## ✓ Fold5: preprocessor 1/1, model 5/10
## i Fold5: preprocessor 1/1, model 5/10 (predictions)
## i Fold5: preprocessor 1/1, model 6/10
## ✓ Fold5: preprocessor 1/1, model 6/10
## i Fold5: preprocessor 1/1, model 6/10 (predictions)
## i Fold5: preprocessor 1/1, model 7/10
## ✓ Fold5: preprocessor 1/1, model 7/10
## i Fold5: preprocessor 1/1, model 7/10 (predictions)
## i Fold5: preprocessor 1/1, model 8/10
## ✓ Fold5: preprocessor 1/1, model 8/10
## i Fold5: preprocessor 1/1, model 8/10 (predictions)
## i Fold5: preprocessor 1/1, model 9/10
## ✓ Fold5: preprocessor 1/1, model 9/10
## i Fold5: preprocessor 1/1, model 9/10 (predictions)
## i Fold5: preprocessor 1/1, model 10/10
## ✓ Fold5: preprocessor 1/1, model 10/10
## i Fold5: preprocessor 1/1, model 10/10 (predictions)
## ✔ Finished tuning Model Specification.
## ℹ Model Parameters:
## # A tibble: 1 × 11
##   trees min_n tree_depth learn_rate loss_reduction .metric .estimator   mean
##   <int> <int>      <int>      <dbl>          <dbl> <chr>   <chr>       <dbl>
## 1  1291    12         11      0.230       0.000130 rmse    standard   0.0771
## # ℹ 3 more variables: n <int>, std_err <dbl>, .config <chr>
## ℹ Prediction Error Comparison:
## # A tibble: 11 × 3
##    .model_id    rmse .model_desc              
##    <chr>       <dbl> <chr>                    
##  1 1         0.952   PROPHET                  
##  2 10        0.389   PROPHET W/ XGBOOST ERRORS
##  3 2         0.356   GLMNET                   
##  4 3         0.303   KERNLAB                  
##  5 4         0.413   KERNLAB                  
##  6 5         0.623   KKNN                     
##  7 6         0.454   RANDOMFOREST             
##  8 7         0.415   XGBOOST                  
##  9 8         0.458   CUBIST                   
## 10 9         0.512   NNAR(2,1,10)[5]          
## 11 ensemble  0.00869 ENSEMBLE (MODEL SPEC)    
## 
## ── Final Model ──────────────────────────────────────────────────
## ℹ Model Workflow:
## ══ Workflow [trained] ══════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: boost_tree()
## 
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 0 Recipe Steps
## 
## ── Model ───────────────────────────────────────────────────────────────────────
## ##### xgb.Booster
## raw: 1.8 Mb 
## call:
##   xgboost::xgb.train(params = list(eta = 0.229923571462474, max_depth = 11L, 
##     gamma = 0.000130024971167041, colsample_bytree = 1, colsample_bynode = 1, 
##     min_child_weight = 12L, subsample = 1), data = x$data, nrounds = 1291L, 
##     watchlist = x$watchlist, verbose = 0, nthread = 1, objective = "reg:squarederror")
## params (as set within xgb.train):
##   eta = "0.229923571462474", max_depth = "11", gamma = "0.000130024971167041", colsample_bytree = "1", colsample_bynode = "1", min_child_weight = "12", subsample = "1", nthread = "1", objective = "reg:squarederror", validate_parameters = "TRUE"
## xgb.attributes:
##   niter
## callbacks:
##   cb.evaluation.log()
## # of features: 10 
## niter: 1291
## nfeatures : 10 
## evaluation_log:
##     iter training_rmse
##        1   5.168808703
##        2   3.991416259
## ---                   
##     1290   0.008686332
##     1291   0.008686332
## 
## 45.23 sec elapsed
modeltime_table(
    ensemble_fit_xgboost_tscv
) %>%
    modeltime_accuracy(testing(splits))
## # A tibble: 1 × 9
##   .model_id .model_desc                .type   mae  mape  mase smape  rmse   rsq
##       <int> <chr>                      <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1         1 ENSEMBLE (XGBOOST STACK):… Test  0.230  3.57  7.27  3.49 0.278 0.604

GLMNET Stack

set.seed(123)
ensemble_fit_glmnet_tscv <- submodels_resample %>%
    ensemble_model_spec(
        model_spec = linear_reg(
            penalty = tune(),
            mixture = tune()
        ) %>% 
            set_engine("glmnet"),
        # kfolds  = 10,
        grid    = 10,
        control = control_grid(
            verbose   = TRUE, 
            allow_par = TRUE
        )
    )
## ── Tuning Model Specification ───────────────────────────────────
## ℹ Performing 5-Fold Cross Validation.
## i Fold1: preprocessor 1/1
## ✓ Fold1: preprocessor 1/1
## i Fold1: preprocessor 1/1, model 1/10
## ✓ Fold1: preprocessor 1/1, model 1/10
## i Fold1: preprocessor 1/1, model 1/10 (predictions)
## i Fold1: preprocessor 1/1, model 2/10
## ✓ Fold1: preprocessor 1/1, model 2/10
## i Fold1: preprocessor 1/1, model 2/10 (predictions)
## i Fold1: preprocessor 1/1, model 3/10
## ✓ Fold1: preprocessor 1/1, model 3/10
## i Fold1: preprocessor 1/1, model 3/10 (predictions)
## i Fold1: preprocessor 1/1, model 4/10
## ✓ Fold1: preprocessor 1/1, model 4/10
## i Fold1: preprocessor 1/1, model 4/10 (predictions)
## i Fold1: preprocessor 1/1, model 5/10
## ✓ Fold1: preprocessor 1/1, model 5/10
## i Fold1: preprocessor 1/1, model 5/10 (predictions)
## i Fold1: preprocessor 1/1, model 6/10
## ✓ Fold1: preprocessor 1/1, model 6/10
## i Fold1: preprocessor 1/1, model 6/10 (predictions)
## i Fold1: preprocessor 1/1, model 7/10
## ✓ Fold1: preprocessor 1/1, model 7/10
## i Fold1: preprocessor 1/1, model 7/10 (predictions)
## i Fold1: preprocessor 1/1, model 8/10
## ✓ Fold1: preprocessor 1/1, model 8/10
## i Fold1: preprocessor 1/1, model 8/10 (predictions)
## i Fold1: preprocessor 1/1, model 9/10
## ✓ Fold1: preprocessor 1/1, model 9/10
## i Fold1: preprocessor 1/1, model 9/10 (predictions)
## i Fold1: preprocessor 1/1, model 10/10
## ✓ Fold1: preprocessor 1/1, model 10/10
## i Fold1: preprocessor 1/1, model 10/10 (predictions)
## i Fold2: preprocessor 1/1
## ✓ Fold2: preprocessor 1/1
## i Fold2: preprocessor 1/1, model 1/10
## ✓ Fold2: preprocessor 1/1, model 1/10
## i Fold2: preprocessor 1/1, model 1/10 (predictions)
## i Fold2: preprocessor 1/1, model 2/10
## ✓ Fold2: preprocessor 1/1, model 2/10
## i Fold2: preprocessor 1/1, model 2/10 (predictions)
## i Fold2: preprocessor 1/1, model 3/10
## ✓ Fold2: preprocessor 1/1, model 3/10
## i Fold2: preprocessor 1/1, model 3/10 (predictions)
## i Fold2: preprocessor 1/1, model 4/10
## ✓ Fold2: preprocessor 1/1, model 4/10
## i Fold2: preprocessor 1/1, model 4/10 (predictions)
## i Fold2: preprocessor 1/1, model 5/10
## ✓ Fold2: preprocessor 1/1, model 5/10
## i Fold2: preprocessor 1/1, model 5/10 (predictions)
## i Fold2: preprocessor 1/1, model 6/10
## ✓ Fold2: preprocessor 1/1, model 6/10
## i Fold2: preprocessor 1/1, model 6/10 (predictions)
## i Fold2: preprocessor 1/1, model 7/10
## ✓ Fold2: preprocessor 1/1, model 7/10
## i Fold2: preprocessor 1/1, model 7/10 (predictions)
## i Fold2: preprocessor 1/1, model 8/10
## ✓ Fold2: preprocessor 1/1, model 8/10
## i Fold2: preprocessor 1/1, model 8/10 (predictions)
## i Fold2: preprocessor 1/1, model 9/10
## ✓ Fold2: preprocessor 1/1, model 9/10
## i Fold2: preprocessor 1/1, model 9/10 (predictions)
## i Fold2: preprocessor 1/1, model 10/10
## ✓ Fold2: preprocessor 1/1, model 10/10
## i Fold2: preprocessor 1/1, model 10/10 (predictions)
## i Fold3: preprocessor 1/1
## ✓ Fold3: preprocessor 1/1
## i Fold3: preprocessor 1/1, model 1/10
## ✓ Fold3: preprocessor 1/1, model 1/10
## i Fold3: preprocessor 1/1, model 1/10 (predictions)
## i Fold3: preprocessor 1/1, model 2/10
## ✓ Fold3: preprocessor 1/1, model 2/10
## i Fold3: preprocessor 1/1, model 2/10 (predictions)
## i Fold3: preprocessor 1/1, model 3/10
## ✓ Fold3: preprocessor 1/1, model 3/10
## i Fold3: preprocessor 1/1, model 3/10 (predictions)
## i Fold3: preprocessor 1/1, model 4/10
## ✓ Fold3: preprocessor 1/1, model 4/10
## i Fold3: preprocessor 1/1, model 4/10 (predictions)
## i Fold3: preprocessor 1/1, model 5/10
## ✓ Fold3: preprocessor 1/1, model 5/10
## i Fold3: preprocessor 1/1, model 5/10 (predictions)
## i Fold3: preprocessor 1/1, model 6/10
## ✓ Fold3: preprocessor 1/1, model 6/10
## i Fold3: preprocessor 1/1, model 6/10 (predictions)
## i Fold3: preprocessor 1/1, model 7/10
## ✓ Fold3: preprocessor 1/1, model 7/10
## i Fold3: preprocessor 1/1, model 7/10 (predictions)
## i Fold3: preprocessor 1/1, model 8/10
## ✓ Fold3: preprocessor 1/1, model 8/10
## i Fold3: preprocessor 1/1, model 8/10 (predictions)
## i Fold3: preprocessor 1/1, model 9/10
## ✓ Fold3: preprocessor 1/1, model 9/10
## i Fold3: preprocessor 1/1, model 9/10 (predictions)
## i Fold3: preprocessor 1/1, model 10/10
## ✓ Fold3: preprocessor 1/1, model 10/10
## i Fold3: preprocessor 1/1, model 10/10 (predictions)
## i Fold4: preprocessor 1/1
## ✓ Fold4: preprocessor 1/1
## i Fold4: preprocessor 1/1, model 1/10
## ✓ Fold4: preprocessor 1/1, model 1/10
## i Fold4: preprocessor 1/1, model 1/10 (predictions)
## i Fold4: preprocessor 1/1, model 2/10
## ✓ Fold4: preprocessor 1/1, model 2/10
## i Fold4: preprocessor 1/1, model 2/10 (predictions)
## i Fold4: preprocessor 1/1, model 3/10
## ✓ Fold4: preprocessor 1/1, model 3/10
## i Fold4: preprocessor 1/1, model 3/10 (predictions)
## i Fold4: preprocessor 1/1, model 4/10
## ✓ Fold4: preprocessor 1/1, model 4/10
## i Fold4: preprocessor 1/1, model 4/10 (predictions)
## i Fold4: preprocessor 1/1, model 5/10
## ✓ Fold4: preprocessor 1/1, model 5/10
## i Fold4: preprocessor 1/1, model 5/10 (predictions)
## i Fold4: preprocessor 1/1, model 6/10
## ✓ Fold4: preprocessor 1/1, model 6/10
## i Fold4: preprocessor 1/1, model 6/10 (predictions)
## i Fold4: preprocessor 1/1, model 7/10
## ✓ Fold4: preprocessor 1/1, model 7/10
## i Fold4: preprocessor 1/1, model 7/10 (predictions)
## i Fold4: preprocessor 1/1, model 8/10
## ✓ Fold4: preprocessor 1/1, model 8/10
## i Fold4: preprocessor 1/1, model 8/10 (predictions)
## i Fold4: preprocessor 1/1, model 9/10
## ✓ Fold4: preprocessor 1/1, model 9/10
## i Fold4: preprocessor 1/1, model 9/10 (predictions)
## i Fold4: preprocessor 1/1, model 10/10
## ✓ Fold4: preprocessor 1/1, model 10/10
## i Fold4: preprocessor 1/1, model 10/10 (predictions)
## i Fold5: preprocessor 1/1
## ✓ Fold5: preprocessor 1/1
## i Fold5: preprocessor 1/1, model 1/10
## ✓ Fold5: preprocessor 1/1, model 1/10
## i Fold5: preprocessor 1/1, model 1/10 (predictions)
## i Fold5: preprocessor 1/1, model 2/10
## ✓ Fold5: preprocessor 1/1, model 2/10
## i Fold5: preprocessor 1/1, model 2/10 (predictions)
## i Fold5: preprocessor 1/1, model 3/10
## ✓ Fold5: preprocessor 1/1, model 3/10
## i Fold5: preprocessor 1/1, model 3/10 (predictions)
## i Fold5: preprocessor 1/1, model 4/10
## ✓ Fold5: preprocessor 1/1, model 4/10
## i Fold5: preprocessor 1/1, model 4/10 (predictions)
## i Fold5: preprocessor 1/1, model 5/10
## ✓ Fold5: preprocessor 1/1, model 5/10
## i Fold5: preprocessor 1/1, model 5/10 (predictions)
## i Fold5: preprocessor 1/1, model 6/10
## ✓ Fold5: preprocessor 1/1, model 6/10
## i Fold5: preprocessor 1/1, model 6/10 (predictions)
## i Fold5: preprocessor 1/1, model 7/10
## ✓ Fold5: preprocessor 1/1, model 7/10
## i Fold5: preprocessor 1/1, model 7/10 (predictions)
## i Fold5: preprocessor 1/1, model 8/10
## ✓ Fold5: preprocessor 1/1, model 8/10
## i Fold5: preprocessor 1/1, model 8/10 (predictions)
## i Fold5: preprocessor 1/1, model 9/10
## ✓ Fold5: preprocessor 1/1, model 9/10
## i Fold5: preprocessor 1/1, model 9/10 (predictions)
## i Fold5: preprocessor 1/1, model 10/10
## ✓ Fold5: preprocessor 1/1, model 10/10
## i Fold5: preprocessor 1/1, model 10/10 (predictions)
## ✔ Finished tuning Model Specification.
## ℹ Model Parameters:
## # A tibble: 1 × 8
##    penalty mixture .metric .estimator  mean     n std_err .config              
##      <dbl>   <dbl> <chr>   <chr>      <dbl> <int>   <dbl> <chr>                
## 1 2.19e-10   0.835 rmse    standard   0.151     5 0.00564 Preprocessor1_Model09
## ℹ Prediction Error Comparison:
## # A tibble: 11 × 3
##    .model_id  rmse .model_desc              
##    <chr>     <dbl> <chr>                    
##  1 1         0.952 PROPHET                  
##  2 10        0.389 PROPHET W/ XGBOOST ERRORS
##  3 2         0.356 GLMNET                   
##  4 3         0.303 KERNLAB                  
##  5 4         0.413 KERNLAB                  
##  6 5         0.623 KKNN                     
##  7 6         0.454 RANDOMFOREST             
##  8 7         0.415 XGBOOST                  
##  9 8         0.458 CUBIST                   
## 10 9         0.512 NNAR(2,1,10)[5]          
## 11 ensemble  0.149 ENSEMBLE (MODEL SPEC)    
## 
## ── Final Model ──────────────────────────────────────────────────
## ℹ Model Workflow:
## ══ Workflow [trained] ══════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: linear_reg()
## 
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 0 Recipe Steps
## 
## ── Model ───────────────────────────────────────────────────────────────────────
## 
## Call:  glmnet::glmnet(x = maybe_matrix(x), y = y, family = "gaussian",      alpha = ~0.83521875477978) 
## 
##    Df  %Dev  Lambda
## 1   0  0.00 0.51330
## 2   1 10.58 0.46770
## 3   2 20.41 0.42620
## 4   3 29.61 0.38830
## 5   3 37.38 0.35380
## 6   3 43.90 0.32240
## 7   3 49.38 0.29370
## 8   3 53.97 0.26760
## 9   4 57.94 0.24390
## 10  4 61.66 0.22220
## 11  5 64.85 0.20250
## 12  5 67.93 0.18450
## 13  5 70.53 0.16810
## 14  5 72.73 0.15320
## 15  5 74.60 0.13950
## 16  5 76.17 0.12720
## 17  5 77.51 0.11590
## 18  5 78.64 0.10560
## 19  4 79.53 0.09619
## 20  4 80.26 0.08764
## 21  5 81.24 0.07985
## 22  5 82.26 0.07276
## 23  5 83.12 0.06630
## 24  6 83.87 0.06041
## 25  6 84.51 0.05504
## 26  6 85.06 0.05015
## 27  6 85.53 0.04570
## 28  6 85.92 0.04164
## 29  6 86.26 0.03794
## 30  6 86.55 0.03457
## 31  6 86.80 0.03150
## 32  6 87.00 0.02870
## 33  6 87.18 0.02615
## 34  6 87.33 0.02383
## 35  6 87.45 0.02171
## 36  6 87.55 0.01978
## 37  6 87.64 0.01802
## 38  7 87.76 0.01642
## 39  7 87.92 0.01496
## 40  8 88.09 0.01363
## 41  8 88.61 0.01242
## 42  8 89.06 0.01132
## 43  8 89.44 0.01031
## 44  8 89.76 0.00940
## 45  8 90.03 0.00856
## 46  8 90.26 0.00780
## 
## ...
## and 35 more lines.
## 
## 4.98 sec elapsed
modeltime_table(
    ensemble_fit_glmnet_tscv
) %>%
    modeltime_accuracy(testing(splits))
## # A tibble: 1 × 9
##   .model_id .model_desc                .type   mae  mape  mase smape  rmse   rsq
##       <int> <chr>                      <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1         1 ENSEMBLE (GLMNET STACK): … Test  0.267  4.10  8.43  4.22 0.314 0.899

RANDOM FOREST Stack

set.seed(123)
ensemble_fit_ranger_tscv <- submodels_resample %>%
    ensemble_model_spec(
        model_spec = rand_forest(
            mode = "regression",
            trees = tune(),
            min_n = tune()
        )  %>%
            set_engine("ranger"),
        # kfolds  = 10,
        grid    = 10,
        control = control_grid(verbose = TRUE, allow_par = TRUE)
    )
## ── Tuning Model Specification ───────────────────────────────────
## ℹ Performing 5-Fold Cross Validation.
## i Fold1: preprocessor 1/1
## ✓ Fold1: preprocessor 1/1
## i Fold1: preprocessor 1/1, model 1/10
## ✓ Fold1: preprocessor 1/1, model 1/10
## i Fold1: preprocessor 1/1, model 1/10 (predictions)
## i Fold1: preprocessor 1/1, model 2/10
## ✓ Fold1: preprocessor 1/1, model 2/10
## i Fold1: preprocessor 1/1, model 2/10 (predictions)
## i Fold1: preprocessor 1/1, model 3/10
## ✓ Fold1: preprocessor 1/1, model 3/10
## i Fold1: preprocessor 1/1, model 3/10 (predictions)
## i Fold1: preprocessor 1/1, model 4/10
## ✓ Fold1: preprocessor 1/1, model 4/10
## i Fold1: preprocessor 1/1, model 4/10 (predictions)
## i Fold1: preprocessor 1/1, model 5/10
## ✓ Fold1: preprocessor 1/1, model 5/10
## i Fold1: preprocessor 1/1, model 5/10 (predictions)
## i Fold1: preprocessor 1/1, model 6/10
## ✓ Fold1: preprocessor 1/1, model 6/10
## i Fold1: preprocessor 1/1, model 6/10 (predictions)
## i Fold1: preprocessor 1/1, model 7/10
## ✓ Fold1: preprocessor 1/1, model 7/10
## i Fold1: preprocessor 1/1, model 7/10 (predictions)
## i Fold1: preprocessor 1/1, model 8/10
## ✓ Fold1: preprocessor 1/1, model 8/10
## i Fold1: preprocessor 1/1, model 8/10 (predictions)
## i Fold1: preprocessor 1/1, model 9/10
## ✓ Fold1: preprocessor 1/1, model 9/10
## i Fold1: preprocessor 1/1, model 9/10 (predictions)
## i Fold1: preprocessor 1/1, model 10/10
## ✓ Fold1: preprocessor 1/1, model 10/10
## i Fold1: preprocessor 1/1, model 10/10 (predictions)
## i Fold2: preprocessor 1/1
## ✓ Fold2: preprocessor 1/1
## i Fold2: preprocessor 1/1, model 1/10
## ✓ Fold2: preprocessor 1/1, model 1/10
## i Fold2: preprocessor 1/1, model 1/10 (predictions)
## i Fold2: preprocessor 1/1, model 2/10
## ✓ Fold2: preprocessor 1/1, model 2/10
## i Fold2: preprocessor 1/1, model 2/10 (predictions)
## i Fold2: preprocessor 1/1, model 3/10
## ✓ Fold2: preprocessor 1/1, model 3/10
## i Fold2: preprocessor 1/1, model 3/10 (predictions)
## i Fold2: preprocessor 1/1, model 4/10
## ✓ Fold2: preprocessor 1/1, model 4/10
## i Fold2: preprocessor 1/1, model 4/10 (predictions)
## i Fold2: preprocessor 1/1, model 5/10
## ✓ Fold2: preprocessor 1/1, model 5/10
## i Fold2: preprocessor 1/1, model 5/10 (predictions)
## i Fold2: preprocessor 1/1, model 6/10
## ✓ Fold2: preprocessor 1/1, model 6/10
## i Fold2: preprocessor 1/1, model 6/10 (predictions)
## i Fold2: preprocessor 1/1, model 7/10
## ✓ Fold2: preprocessor 1/1, model 7/10
## i Fold2: preprocessor 1/1, model 7/10 (predictions)
## i Fold2: preprocessor 1/1, model 8/10
## ✓ Fold2: preprocessor 1/1, model 8/10
## i Fold2: preprocessor 1/1, model 8/10 (predictions)
## i Fold2: preprocessor 1/1, model 9/10
## ✓ Fold2: preprocessor 1/1, model 9/10
## i Fold2: preprocessor 1/1, model 9/10 (predictions)
## i Fold2: preprocessor 1/1, model 10/10
## ✓ Fold2: preprocessor 1/1, model 10/10
## i Fold2: preprocessor 1/1, model 10/10 (predictions)
## i Fold3: preprocessor 1/1
## ✓ Fold3: preprocessor 1/1
## i Fold3: preprocessor 1/1, model 1/10
## ✓ Fold3: preprocessor 1/1, model 1/10
## i Fold3: preprocessor 1/1, model 1/10 (predictions)
## i Fold3: preprocessor 1/1, model 2/10
## ✓ Fold3: preprocessor 1/1, model 2/10
## i Fold3: preprocessor 1/1, model 2/10 (predictions)
## i Fold3: preprocessor 1/1, model 3/10
## ✓ Fold3: preprocessor 1/1, model 3/10
## i Fold3: preprocessor 1/1, model 3/10 (predictions)
## i Fold3: preprocessor 1/1, model 4/10
## ✓ Fold3: preprocessor 1/1, model 4/10
## i Fold3: preprocessor 1/1, model 4/10 (predictions)
## i Fold3: preprocessor 1/1, model 5/10
## ✓ Fold3: preprocessor 1/1, model 5/10
## i Fold3: preprocessor 1/1, model 5/10 (predictions)
## i Fold3: preprocessor 1/1, model 6/10
## ✓ Fold3: preprocessor 1/1, model 6/10
## i Fold3: preprocessor 1/1, model 6/10 (predictions)
## i Fold3: preprocessor 1/1, model 7/10
## ✓ Fold3: preprocessor 1/1, model 7/10
## i Fold3: preprocessor 1/1, model 7/10 (predictions)
## i Fold3: preprocessor 1/1, model 8/10
## ✓ Fold3: preprocessor 1/1, model 8/10
## i Fold3: preprocessor 1/1, model 8/10 (predictions)
## i Fold3: preprocessor 1/1, model 9/10
## ✓ Fold3: preprocessor 1/1, model 9/10
## i Fold3: preprocessor 1/1, model 9/10 (predictions)
## i Fold3: preprocessor 1/1, model 10/10
## ✓ Fold3: preprocessor 1/1, model 10/10
## i Fold3: preprocessor 1/1, model 10/10 (predictions)
## i Fold4: preprocessor 1/1
## ✓ Fold4: preprocessor 1/1
## i Fold4: preprocessor 1/1, model 1/10
## ✓ Fold4: preprocessor 1/1, model 1/10
## i Fold4: preprocessor 1/1, model 1/10 (predictions)
## i Fold4: preprocessor 1/1, model 2/10
## ✓ Fold4: preprocessor 1/1, model 2/10
## i Fold4: preprocessor 1/1, model 2/10 (predictions)
## i Fold4: preprocessor 1/1, model 3/10
## ✓ Fold4: preprocessor 1/1, model 3/10
## i Fold4: preprocessor 1/1, model 3/10 (predictions)
## i Fold4: preprocessor 1/1, model 4/10
## ✓ Fold4: preprocessor 1/1, model 4/10
## i Fold4: preprocessor 1/1, model 4/10 (predictions)
## i Fold4: preprocessor 1/1, model 5/10
## ✓ Fold4: preprocessor 1/1, model 5/10
## i Fold4: preprocessor 1/1, model 5/10 (predictions)
## i Fold4: preprocessor 1/1, model 6/10
## ✓ Fold4: preprocessor 1/1, model 6/10
## i Fold4: preprocessor 1/1, model 6/10 (predictions)
## i Fold4: preprocessor 1/1, model 7/10
## ✓ Fold4: preprocessor 1/1, model 7/10
## i Fold4: preprocessor 1/1, model 7/10 (predictions)
## i Fold4: preprocessor 1/1, model 8/10
## ✓ Fold4: preprocessor 1/1, model 8/10
## i Fold4: preprocessor 1/1, model 8/10 (predictions)
## i Fold4: preprocessor 1/1, model 9/10
## ✓ Fold4: preprocessor 1/1, model 9/10
## i Fold4: preprocessor 1/1, model 9/10 (predictions)
## i Fold4: preprocessor 1/1, model 10/10
## ✓ Fold4: preprocessor 1/1, model 10/10
## i Fold4: preprocessor 1/1, model 10/10 (predictions)
## i Fold5: preprocessor 1/1
## ✓ Fold5: preprocessor 1/1
## i Fold5: preprocessor 1/1, model 1/10
## ✓ Fold5: preprocessor 1/1, model 1/10
## i Fold5: preprocessor 1/1, model 1/10 (predictions)
## i Fold5: preprocessor 1/1, model 2/10
## ✓ Fold5: preprocessor 1/1, model 2/10
## i Fold5: preprocessor 1/1, model 2/10 (predictions)
## i Fold5: preprocessor 1/1, model 3/10
## ✓ Fold5: preprocessor 1/1, model 3/10
## i Fold5: preprocessor 1/1, model 3/10 (predictions)
## i Fold5: preprocessor 1/1, model 4/10
## ✓ Fold5: preprocessor 1/1, model 4/10
## i Fold5: preprocessor 1/1, model 4/10 (predictions)
## i Fold5: preprocessor 1/1, model 5/10
## ✓ Fold5: preprocessor 1/1, model 5/10
## i Fold5: preprocessor 1/1, model 5/10 (predictions)
## i Fold5: preprocessor 1/1, model 6/10
## ✓ Fold5: preprocessor 1/1, model 6/10
## i Fold5: preprocessor 1/1, model 6/10 (predictions)
## i Fold5: preprocessor 1/1, model 7/10
## ✓ Fold5: preprocessor 1/1, model 7/10
## i Fold5: preprocessor 1/1, model 7/10 (predictions)
## i Fold5: preprocessor 1/1, model 8/10
## ✓ Fold5: preprocessor 1/1, model 8/10
## i Fold5: preprocessor 1/1, model 8/10 (predictions)
## i Fold5: preprocessor 1/1, model 9/10
## ✓ Fold5: preprocessor 1/1, model 9/10
## i Fold5: preprocessor 1/1, model 9/10 (predictions)
## i Fold5: preprocessor 1/1, model 10/10
## ✓ Fold5: preprocessor 1/1, model 10/10
## i Fold5: preprocessor 1/1, model 10/10 (predictions)
## ✔ Finished tuning Model Specification.
## ℹ Model Parameters:
## # A tibble: 1 × 8
##   trees min_n .metric .estimator   mean     n std_err .config              
##   <int> <int> <chr>   <chr>       <dbl> <int>   <dbl> <chr>                
## 1  1986     2 rmse    standard   0.0754     5 0.00630 Preprocessor1_Model09
## ℹ Prediction Error Comparison:
## # A tibble: 11 × 3
##    .model_id   rmse .model_desc              
##    <chr>      <dbl> <chr>                    
##  1 1         0.952  PROPHET                  
##  2 10        0.389  PROPHET W/ XGBOOST ERRORS
##  3 2         0.356  GLMNET                   
##  4 3         0.303  KERNLAB                  
##  5 4         0.413  KERNLAB                  
##  6 5         0.623  KKNN                     
##  7 6         0.454  RANDOMFOREST             
##  8 7         0.415  XGBOOST                  
##  9 8         0.458  CUBIST                   
## 10 9         0.512  NNAR(2,1,10)[5]          
## 11 ensemble  0.0282 ENSEMBLE (MODEL SPEC)    
## 
## ── Final Model ──────────────────────────────────────────────────
## ℹ Model Workflow:
## ══ Workflow [trained] ══════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: rand_forest()
## 
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 0 Recipe Steps
## 
## ── Model ───────────────────────────────────────────────────────────────────────
## Ranger result
## 
## Call:
##  ranger::ranger(x = maybe_data_frame(x), y = y, num.trees = ~1986L,      min.node.size = min_rows(~2L, x), num.threads = 1, verbose = FALSE,      seed = sample.int(10^5, 1)) 
## 
## Type:                             Regression 
## Number of trees:                  1986 
## Sample size:                      320 
## Number of independent variables:  10 
## Mtry:                             3 
## Target node size:                 2 
## Variable importance mode:         none 
## Splitrule:                        variance 
## OOB prediction error (MSE):       0.005551274 
## R squared (OOB):                  0.9785192 
## 
## 15.23 sec elapsed
modeltime_table(
    ensemble_fit_ranger_tscv
) %>%
    modeltime_accuracy(testing(splits))
## # A tibble: 1 × 9
##   .model_id .model_desc                .type   mae  mape  mase smape  rmse   rsq
##       <int> <chr>                      <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1         1 ENSEMBLE (RANGER STACK): … Test  0.228  3.50  7.21  3.45 0.266 0.717

Multiple Stack

model_stack_level_2_accuracy_tbl <- modeltime_table(
    ensemble_fit_glmnet_tscv,
  ensemble_fit_xgboost_tscv,
  ensemble_fit_cubist_tscv,
  ensemble_fit_ranger_tscv
) %>%
    modeltime_accuracy(testing(splits))

model_stack_level_2_accuracy_tbl %>% write_rds("model_stack_level_2_accuracy_tbl")

model_stack_level_2_accuracy_tbl %>% table_modeltime_accuracy()
model_stack_level_3_tbl <- modeltime_table(
  ensemble_fit_glmnet_tscv,
  ensemble_fit_xgboost_tscv
) %>%
    ensemble_weighted(loadings = c(1,2)) %>%
    modeltime_table()

model_stack_level_3_tbl %>% write_rds("model_stack_level_3_tbl")

model_stack_level_3_tbl %>%
    modeltime_accuracy(testing(splits)) # RMSE 1074
## # A tibble: 1 × 9
##   .model_id .model_desc                .type   mae  mape  mase smape  rmse   rsq
##       <int> <chr>                      <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1         1 ENSEMBLE (WEIGHTED): 2 MO… Test  0.124  1.88  3.92  1.88 0.147 0.878

Calibration

calibration_ensemble_tbl <- model_stack_level_3_tbl %>% 
    modeltime_calibrate(testing(splits))

calibration_ensemble_tbl
## # Modeltime Table
## # A tibble: 1 × 5
##   .model_id .model         .model_desc                   .type .calibration_data
##       <int> <list>         <chr>                         <chr> <list>           
## 1         1 <ensemble [2]> ENSEMBLE (WEIGHTED): 2 MODELS Test  <tibble>
calibration_ensemble_tbl %>% write_rds("calibration_ensemble_tbl")

calibration_ensemble_tbl %>% 
  modeltime_accuracy()
## # A tibble: 1 × 9
##   .model_id .model_desc                .type   mae  mape  mase smape  rmse   rsq
##       <int> <chr>                      <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1         1 ENSEMBLE (WEIGHTED): 2 MO… Test  0.124  1.88  3.92  1.88 0.147 0.878

Test Forecast

forecast_test_tbl <- calibration_ensemble_tbl %>%
    modeltime_forecast(
        new_data    = testing(splits),
        actual_data = yield
    )

forecast_test_tbl %>%
    plot_modeltime_forecast()

Refit Forecast

set.seed(123)
refit_ensemble_superlearner_tbl_no_resample <- calibration_ensemble_tbl %>% 
  modeltime_refit(data = yield)
## frequency = 5 observations per 1 week
## frequency = 5 observations per 1 week
## Warning: There was 1 warning in `dplyr::mutate()`.
## ℹ In argument: `.model = purrr::map2(...)`.
## Caused by warning:
## ! There were 4 warnings in `dplyr::mutate()`.
## The first warning was:
## ℹ In argument: `.model = purrr::map2(...)`.
## Caused by warning in `mdl_time_refit.mdl_time_ensemble_model_spec()`:
## ! 'resamples' not provided during refitting. Submodels will be refit, but the meta-learner will *not* be refit. You can provide 'resamples' via `modeltime_refit(object, data, resamples, control)`. Proceeding by refitting the submodels only.
## ℹ Run ]8;;ide:run:dplyr::last_dplyr_warnings()dplyr::last_dplyr_warnings()]8;; to see the 3 remaining warnings.
set.seed(123)
refit_ensemble_superlearner_tbl_resample <- calibration_ensemble_tbl %>% 
  modeltime_refit(data = yield, 
                  resample = resamples_tscv_no_acum %>% drop_na())
## frequency = 5 observations per 1 week
## frequency = 5 observations per 1 week
## Warning: There was 1 warning in `dplyr::mutate()`.
## ℹ In argument: `.model = purrr::map2(...)`.
## Caused by warning:
## ! There were 4 warnings in `dplyr::mutate()`.
## The first warning was:
## ℹ In argument: `.model = purrr::map2(...)`.
## Caused by warning in `mdl_time_refit.mdl_time_ensemble_model_spec()`:
## ! 'resamples' not provided during refitting. Submodels will be refit, but the meta-learner will *not* be refit. You can provide 'resamples' via `modeltime_refit(object, data, resamples, control)`. Proceeding by refitting the submodels only.
## ℹ Run ]8;;ide:run:dplyr::last_dplyr_warnings()dplyr::last_dplyr_warnings()]8;; to see the 3 remaining warnings.
forecast_superlearner_tbl_no_resample <- refit_ensemble_superlearner_tbl_no_resample %>%
    modeltime_forecast(h = "1 year", actual_data = yield)

forecast_superlearner_tbl_no_resample %>%
    plot_modeltime_forecast()
forecast_superlearner_tbl_resample <- refit_ensemble_superlearner_tbl_resample %>%
    modeltime_forecast(h = "1 year", actual_data = yield)
    
forecast_superlearner_tbl_resample %>%
    plot_modeltime_forecast()