library("epiR")
## Loading required package: survival
## Package epiR 0.9-82 is loaded
## Type help(epi.about) for summary information
##
library("FRESA.CAD")
## Loading required package: Rcpp
## Loading required package: stringr
## Loading required package: miscTools
## Loading required package: Hmisc
## Loading required package: lattice
## Loading required package: Formula
## Loading required package: ggplot2
##
## Attaching package: 'Hmisc'
## The following objects are masked from 'package:base':
##
## format.pval, round.POSIXt, trunc.POSIXt, units
## Loading required package: pROC
## Type 'citation("pROC")' for a citation.
##
## Attaching package: 'pROC'
## The following objects are masked from 'package:stats':
##
## cov, smooth, var
library(network)
## network: Classes for Relational Data
## Version 1.13.0 created on 2015-08-31.
## copyright (c) 2005, Carter T. Butts, University of California-Irvine
## Mark S. Handcock, University of California -- Los Angeles
## David R. Hunter, Penn State University
## Martina Morris, University of Washington
## Skye Bender-deMoll, University of Washington
## For citation information, type citation("network").
## Type help("network-package") to get started.
##
## Attaching package: 'network'
## The following object is masked from 'package:Hmisc':
##
## is.discrete
library(GGally)
library("e1071")
## Warning: package 'e1071' was built under R version 3.4.2
##
## Attaching package: 'e1071'
## The following object is masked from 'package:Hmisc':
##
## impute
madelonTrain <- read.delim("./MADELON/MADELON/madelon.txt")
madelonTrain$Label <- 1*(madelonTrain$Label>0)
madeloncontrol <- subset(madelonTrain,Label==0)
vartoadjust <- colnames(madelonTrain)
vartoadjust <- cbind(vartoadjust[-1],vartoadjust[-1])
madelon.norm <- rankInverseNormalDataFrame(vartoadjust, madelonTrain,madeloncontrol)
## Min Strata: 1 Max Strata: 1
## Variable: V1 Min: 462 Max: 501
## Variable: V2 Min: 386 Max: 584
## Variable: V3 Min: 370 Max: 632
## Variable: V4 Min: 456 Max: 519
## Variable: V5 Min: 371 Max: 647
## Variable: V6 Min: 459 Max: 505
## Variable: V7 Min: 334 Max: 611
## Variable: V8 Min: 471 Max: 481
## Variable: V9 Min: 440 Max: 536
## Variable: V10 Min: 455 Max: 502
## Variable: V11 Min: 354 Max: 593
## Variable: V12 Min: 389 Max: 585
## Variable: V13 Min: 347 Max: 593
## Variable: V14 Min: 359 Max: 609
## Variable: V15 Min: 444 Max: 523
## Variable: V16 Min: 410 Max: 551
## Variable: V17 Min: 433 Max: 523
## Variable: V18 Min: 377 Max: 592
## Variable: V19 Min: 419 Max: 566
## Variable: V20 Min: 445 Max: 513
## Variable: V21 Min: 426 Max: 526
## Variable: V22 Min: 428 Max: 571
## Variable: V23 Min: 456 Max: 499
## Variable: V24 Min: 449 Max: 510
## Variable: V25 Min: 343 Max: 653
## Variable: V26 Min: 417 Max: 586
## Variable: V27 Min: 423 Max: 568
## Variable: V28 Min: 441 Max: 528
## Variable: V29 Min: 439 Max: 516
## Variable: V30 Min: 417 Max: 573
## Variable: V31 Min: 451 Max: 505
## Variable: V32 Min: 382 Max: 609
## Variable: V33 Min: 369 Max: 614
## Variable: V34 Min: 363 Max: 637
## Variable: V35 Min: 405 Max: 555
## Variable: V36 Min: 343 Max: 619
## Variable: V37 Min: 441 Max: 515
## Variable: V38 Min: 396 Max: 550
## Variable: V39 Min: 464 Max: 496
## Variable: V40 Min: 471 Max: 480
## Variable: V41 Min: 464 Max: 487
## Variable: V42 Min: 370 Max: 643
## Variable: V43 Min: 392 Max: 568
## Variable: V44 Min: 438 Max: 548
## Variable: V45 Min: 410 Max: 590
## Variable: V46 Min: 412 Max: 557
## Variable: V47 Min: 371 Max: 601
## Variable: V48 Min: 373 Max: 619
## Variable: V49 Min: 382 Max: 614
## Variable: V50 Min: 382 Max: 571
## Variable: V51 Min: 381 Max: 655
## Variable: V52 Min: 390 Max: 635
## Variable: V53 Min: 399 Max: 555
## Variable: V54 Min: 465 Max: 498
## Variable: V55 Min: 404 Max: 587
## Variable: V56 Min: 433 Max: 560
## Variable: V57 Min: 360 Max: 615
## Variable: V58 Min: 377 Max: 617
## Variable: V59 Min: 378 Max: 653
## Variable: V60 Min: 408 Max: 543
## Variable: V61 Min: 400 Max: 558
## Variable: V62 Min: 463 Max: 502
## Variable: V63 Min: 387 Max: 606
## Variable: V64 Min: 459 Max: 505
## Variable: V65 Min: 248 Max: 768
## Variable: V66 Min: 385 Max: 640
## Variable: V67 Min: 373 Max: 607
## Variable: V68 Min: 423 Max: 563
## Variable: V69 Min: 462 Max: 498
## Variable: V70 Min: 456 Max: 501
## Variable: V71 Min: 362 Max: 668
## Variable: V72 Min: 442 Max: 536
## Variable: V73 Min: 402 Max: 549
## Variable: V74 Min: 354 Max: 629
## Variable: V75 Min: 456 Max: 508
## Variable: V76 Min: 371 Max: 651
## Variable: V77 Min: 450 Max: 508
## Variable: V78 Min: 396 Max: 581
## Variable: V79 Min: 395 Max: 640
## Variable: V80 Min: 424 Max: 546
## Variable: V81 Min: 415 Max: 578
## Variable: V82 Min: 385 Max: 674
## Variable: V83 Min: 396 Max: 613
## Variable: V84 Min: 430 Max: 523
## Variable: V85 Min: 372 Max: 647
## Variable: V86 Min: 391 Max: 583
## Variable: V87 Min: 461 Max: 494
## Variable: V88 Min: 406 Max: 567
## Variable: V89 Min: 456 Max: 498
## Variable: V90 Min: 386 Max: 631
## Variable: V91 Min: 474 Max: 478
## Variable: V92 Min: 395 Max: 609
## Variable: V93 Min: 399 Max: 551
## Variable: V94 Min: 438 Max: 557
## Variable: V95 Min: 452 Max: 501
## Variable: V96 Min: 384 Max: 595
## Variable: V97 Min: 468 Max: 491
## Variable: V98 Min: 406 Max: 554
## Variable: V99 Min: 421 Max: 537
## Variable: V100 Min: 355 Max: 603
## Variable: V101 Min: 453 Max: 507
## Variable: V102 Min: 448 Max: 509
## Variable: V103 Min: 463 Max: 506
## Variable: V104 Min: 434 Max: 533
## Variable: V105 Min: 361 Max: 645
## Variable: V106 Min: 0 Max: 896
## Variable: V107 Min: 349 Max: 566
## Variable: V108 Min: 385 Max: 592
## Variable: V109 Min: 404 Max: 599
## Variable: V110 Min: 449 Max: 518
## Variable: V111 Min: 392 Max: 610
## Variable: V112 Min: 356 Max: 611
## Variable: V113 Min: 452 Max: 506
## Variable: V114 Min: 385 Max: 585
## Variable: V115 Min: 353 Max: 617
## Variable: V116 Min: 425 Max: 545
## Variable: V117 Min: 418 Max: 564
## Variable: V118 Min: 443 Max: 521
## Variable: V119 Min: 389 Max: 592
## Variable: V120 Min: 419 Max: 564
## Variable: V121 Min: 469 Max: 483
## Variable: V122 Min: 405 Max: 574
## Variable: V123 Min: 439 Max: 516
## Variable: V124 Min: 358 Max: 615
## Variable: V125 Min: 415 Max: 549
## Variable: V126 Min: 410 Max: 612
## Variable: V127 Min: 442 Max: 530
## Variable: V128 Min: 387 Max: 569
## Variable: V129 Min: 435 Max: 510
## Variable: V130 Min: 361 Max: 613
## Variable: V131 Min: 401 Max: 618
## Variable: V132 Min: 425 Max: 552
## Variable: V133 Min: 402 Max: 556
## Variable: V134 Min: 466 Max: 491
## Variable: V135 Min: 413 Max: 560
## Variable: V136 Min: 382 Max: 634
## Variable: V137 Min: 369 Max: 639
## Variable: V138 Min: 425 Max: 555
## Variable: V139 Min: 461 Max: 503
## Variable: V140 Min: 436 Max: 534
## Variable: V141 Min: 427 Max: 566
## Variable: V142 Min: 393 Max: 641
## Variable: V143 Min: 443 Max: 512
## Variable: V144 Min: 458 Max: 508
## Variable: V145 Min: 421 Max: 549
## Variable: V146 Min: 398 Max: 553
## Variable: V147 Min: 468 Max: 493
## Variable: V148 Min: 369 Max: 624
## Variable: V149 Min: 466 Max: 496
## Variable: V150 Min: 376 Max: 618
## Variable: V151 Min: 325 Max: 603
## Variable: V152 Min: 447 Max: 529
## Variable: V153 Min: 437 Max: 517
## Variable: V154 Min: 182 Max: 814
## Variable: V155 Min: 473 Max: 481
## Variable: V156 Min: 398 Max: 583
## Variable: V157 Min: 406 Max: 546
## Variable: V158 Min: 408 Max: 545
## Variable: V159 Min: 419 Max: 589
## Variable: V160 Min: 400 Max: 587
## Variable: V161 Min: 379 Max: 563
## Variable: V162 Min: 443 Max: 519
## Variable: V163 Min: 444 Max: 518
## Variable: V164 Min: 458 Max: 497
## Variable: V165 Min: 335 Max: 661
## Variable: V166 Min: 414 Max: 579
## Variable: V167 Min: 471 Max: 480
## Variable: V168 Min: 466 Max: 493
## Variable: V169 Min: 473 Max: 481
## Variable: V170 Min: 389 Max: 664
## Variable: V171 Min: 350 Max: 638
## Variable: V172 Min: 397 Max: 637
## Variable: V173 Min: 380 Max: 633
## Variable: V174 Min: 474 Max: 481
## Variable: V175 Min: 431 Max: 519
## Variable: V176 Min: 393 Max: 616
## Variable: V177 Min: 446 Max: 526
## Variable: V178 Min: 457 Max: 504
## Variable: V179 Min: 347 Max: 620
## Variable: V180 Min: 397 Max: 632
## Variable: V181 Min: 381 Max: 615
## Variable: V182 Min: 393 Max: 644
## Variable: V183 Min: 397 Max: 557
## Variable: V184 Min: 387 Max: 571
## Variable: V185 Min: 438 Max: 542
## Variable: V186 Min: 412 Max: 575
## Variable: V187 Min: 362 Max: 631
## Variable: V188 Min: 387 Max: 591
## Variable: V189 Min: 387 Max: 641
## Variable: V190 Min: 457 Max: 492
## Variable: V191 Min: 372 Max: 553
## Variable: V192 Min: 417 Max: 568
## Variable: V193 Min: 428 Max: 552
## Variable: V194 Min: 364 Max: 654
## Variable: V195 Min: 350 Max: 651
## Variable: V196 Min: 453 Max: 516
## Variable: V197 Min: 461 Max: 496
## Variable: V198 Min: 455 Max: 512
## Variable: V199 Min: 472 Max: 481
## Variable: V200 Min: 393 Max: 609
## Variable: V201 Min: 417 Max: 558
## Variable: V202 Min: 427 Max: 557
## Variable: V203 Min: 430 Max: 550
## Variable: V204 Min: 332 Max: 647
## Variable: V205 Min: 376 Max: 595
## Variable: V206 Min: 471 Max: 481
## Variable: V207 Min: 383 Max: 641
## Variable: V208 Min: 466 Max: 492
## Variable: V209 Min: 427 Max: 530
## Variable: V210 Min: 427 Max: 550
## Variable: V211 Min: 444 Max: 530
## Variable: V212 Min: 374 Max: 600
## Variable: V213 Min: 402 Max: 565
## Variable: V214 Min: 358 Max: 608
## Variable: V215 Min: 443 Max: 517
## Variable: V216 Min: 370 Max: 632
## Variable: V217 Min: 406 Max: 630
## Variable: V218 Min: 452 Max: 510
## Variable: V219 Min: 400 Max: 581
## Variable: V220 Min: 456 Max: 520
## Variable: V221 Min: 381 Max: 569
## Variable: V222 Min: 350 Max: 646
## Variable: V223 Min: 399 Max: 583
## Variable: V224 Min: 367 Max: 606
## Variable: V225 Min: 370 Max: 605
## Variable: V226 Min: 417 Max: 601
## Variable: V227 Min: 426 Max: 550
## Variable: V228 Min: 470 Max: 485
## Variable: V229 Min: 473 Max: 479
## Variable: V230 Min: 412 Max: 555
## Variable: V231 Min: 436 Max: 527
## Variable: V232 Min: 420 Max: 561
## Variable: V233 Min: 439 Max: 530
## Variable: V234 Min: 429 Max: 547
## Variable: V235 Min: 432 Max: 560
## Variable: V236 Min: 438 Max: 562
## Variable: V237 Min: 448 Max: 529
## Variable: V238 Min: 468 Max: 488
## Variable: V239 Min: 410 Max: 541
## Variable: V240 Min: 458 Max: 499
## Variable: V241 Min: 408 Max: 586
## Variable: V242 Min: 363 Max: 653
## Variable: V243 Min: 402 Max: 579
## Variable: V244 Min: 434 Max: 530
## Variable: V245 Min: 372 Max: 622
## Variable: V246 Min: 418 Max: 626
## Variable: V247 Min: 358 Max: 588
## Variable: V248 Min: 468 Max: 492
## Variable: V249 Min: 457 Max: 510
## Variable: V250 Min: 401 Max: 579
## Variable: V251 Min: 383 Max: 580
## Variable: V252 Min: 399 Max: 584
## Variable: V253 Min: 466 Max: 489
## Variable: V254 Min: 418 Max: 628
## Variable: V255 Min: 454 Max: 506
## Variable: V256 Min: 399 Max: 628
## Variable: V257 Min: 350 Max: 688
## Variable: V258 Min: 330 Max: 645
## Variable: V259 Min: 455 Max: 520
## Variable: V260 Min: 450 Max: 527
## Variable: V261 Min: 419 Max: 535
## Variable: V262 Min: 461 Max: 502
## Variable: V263 Min: 432 Max: 560
## Variable: V264 Min: 360 Max: 610
## Variable: V265 Min: 451 Max: 509
## Variable: V266 Min: 425 Max: 569
## Variable: V267 Min: 332 Max: 623
## Variable: V268 Min: 431 Max: 554
## Variable: V269 Min: 398 Max: 587
## Variable: V270 Min: 434 Max: 590
## Variable: V271 Min: 442 Max: 526
## Variable: V272 Min: 369 Max: 639
## Variable: V273 Min: 322 Max: 613
## Variable: V274 Min: 380 Max: 692
## Variable: V275 Min: 423 Max: 521
## Variable: V276 Min: 442 Max: 517
## Variable: V277 Min: 474 Max: 478
## Variable: V278 Min: 395 Max: 613
## Variable: V279 Min: 422 Max: 576
## Variable: V280 Min: 387 Max: 593
## Variable: V281 Min: 473 Max: 482
## Variable: V282 Min: 317 Max: 635
## Variable: V283 Min: 420 Max: 527
## Variable: V284 Min: 472 Max: 480
## Variable: V285 Min: 374 Max: 609
## Variable: V286 Min: 363 Max: 619
## Variable: V287 Min: 376 Max: 571
## Variable: V288 Min: 342 Max: 616
## Variable: V289 Min: 468 Max: 495
## Variable: V290 Min: 437 Max: 561
## Variable: V291 Min: 396 Max: 583
## Variable: V292 Min: 401 Max: 605
## Variable: V293 Min: 431 Max: 574
## Variable: V294 Min: 455 Max: 499
## Variable: V295 Min: 325 Max: 626
## Variable: V296 Min: 396 Max: 603
## Variable: V297 Min: 400 Max: 561
## Variable: V298 Min: 372 Max: 679
## Variable: V299 Min: 406 Max: 578
## Variable: V300 Min: 421 Max: 563
## Variable: V301 Min: 359 Max: 597
## Variable: V302 Min: 433 Max: 531
## Variable: V303 Min: 463 Max: 492
## Variable: V304 Min: 422 Max: 570
## Variable: V305 Min: 389 Max: 602
## Variable: V306 Min: 378 Max: 571
## Variable: V307 Min: 436 Max: 530
## Variable: V308 Min: 450 Max: 511
## Variable: V309 Min: 415 Max: 606
## Variable: V310 Min: 347 Max: 541
## Variable: V311 Min: 402 Max: 566
## Variable: V312 Min: 414 Max: 540
## Variable: V313 Min: 402 Max: 599
## Variable: V314 Min: 390 Max: 605
## Variable: V315 Min: 445 Max: 520
## Variable: V316 Min: 385 Max: 582
## Variable: V317 Min: 450 Max: 510
## Variable: V318 Min: 457 Max: 506
## Variable: V319 Min: 346 Max: 607
## Variable: V320 Min: 383 Max: 650
## Variable: V321 Min: 440 Max: 522
## Variable: V322 Min: 374 Max: 571
## Variable: V323 Min: 429 Max: 555
## Variable: V324 Min: 439 Max: 524
## Variable: V325 Min: 442 Max: 556
## Variable: V326 Min: 462 Max: 497
## Variable: V327 Min: 409 Max: 549
## Variable: V328 Min: 399 Max: 570
## Variable: V329 Min: 444 Max: 526
## Variable: V330 Min: 395 Max: 658
## Variable: V331 Min: 372 Max: 605
## Variable: V332 Min: 437 Max: 517
## Variable: V333 Min: 473 Max: 479
## Variable: V334 Min: 383 Max: 581
## Variable: V335 Min: 352 Max: 627
## Variable: V336 Min: 455 Max: 528
## Variable: V337 Min: 180 Max: 795
## Variable: V338 Min: 378 Max: 626
## Variable: V339 Min: 263 Max: 770
## Variable: V340 Min: 378 Max: 618
## Variable: V341 Min: 383 Max: 618
## Variable: V342 Min: 413 Max: 564
## Variable: V343 Min: 389 Max: 606
## Variable: V344 Min: 415 Max: 628
## Variable: V345 Min: 358 Max: 678
## Variable: V346 Min: 452 Max: 512
## Variable: V347 Min: 457 Max: 503
## Variable: V348 Min: 355 Max: 634
## Variable: V349 Min: 409 Max: 545
## Variable: V350 Min: 398 Max: 608
## Variable: V351 Min: 459 Max: 504
## Variable: V352 Min: 347 Max: 624
## Variable: V353 Min: 351 Max: 619
## Variable: V354 Min: 442 Max: 520
## Variable: V355 Min: 431 Max: 561
## Variable: V356 Min: 430 Max: 545
## Variable: V357 Min: 366 Max: 667
## Variable: V358 Min: 471 Max: 482
## Variable: V359 Min: 405 Max: 621
## Variable: V360 Min: 359 Max: 651
## Variable: V361 Min: 375 Max: 589
## Variable: V362 Min: 416 Max: 561
## Variable: V363 Min: 293 Max: 605
## Variable: V364 Min: 415 Max: 565
## Variable: V365 Min: 465 Max: 501
## Variable: V366 Min: 361 Max: 642
## Variable: V367 Min: 407 Max: 582
## Variable: V368 Min: 448 Max: 527
## Variable: V369 Min: 440 Max: 527
## Variable: V370 Min: 376 Max: 650
## Variable: V371 Min: 374 Max: 602
## Variable: V372 Min: 342 Max: 612
## Variable: V373 Min: 424 Max: 570
## Variable: V374 Min: 399 Max: 567
## Variable: V375 Min: 411 Max: 583
## Variable: V376 Min: 381 Max: 594
## Variable: V377 Min: 456 Max: 507
## Variable: V378 Min: 410 Max: 560
## Variable: V379 Min: 348 Max: 661
## Variable: V380 Min: 361 Max: 630
## Variable: V381 Min: 465 Max: 500
## Variable: V382 Min: 404 Max: 569
## Variable: V383 Min: 383 Max: 624
## Variable: V384 Min: 443 Max: 525
## Variable: V385 Min: 424 Max: 532
## Variable: V386 Min: 442 Max: 511
## Variable: V387 Min: 419 Max: 577
## Variable: V388 Min: 472 Max: 483
## Variable: V389 Min: 429 Max: 552
## Variable: V390 Min: 344 Max: 607
## Variable: V391 Min: 463 Max: 496
## Variable: V392 Min: 350 Max: 626
## Variable: V393 Min: 468 Max: 487
## Variable: V394 Min: 393 Max: 600
## Variable: V395 Min: 470 Max: 490
## Variable: V396 Min: 407 Max: 547
## Variable: V397 Min: 455 Max: 522
## Variable: V398 Min: 346 Max: 616
## Variable: V399 Min: 347 Max: 647
## Variable: V400 Min: 462 Max: 504
## Variable: V401 Min: 461 Max: 489
## Variable: V402 Min: 392 Max: 606
## Variable: V403 Min: 472 Max: 480
## Variable: V404 Min: 387 Max: 567
## Variable: V405 Min: 475 Max: 479
## Variable: V406 Min: 372 Max: 571
## Variable: V407 Min: 354 Max: 596
## Variable: V408 Min: 459 Max: 491
## Variable: V409 Min: 396 Max: 556
## Variable: V410 Min: 455 Max: 500
## Variable: V411 Min: 419 Max: 562
## Variable: V412 Min: 369 Max: 615
## Variable: V413 Min: 389 Max: 602
## Variable: V414 Min: 426 Max: 536
## Variable: V415 Min: 398 Max: 603
## Variable: V416 Min: 385 Max: 721
## Variable: V417 Min: 448 Max: 520
## Variable: V418 Min: 375 Max: 630
## Variable: V419 Min: 361 Max: 657
## Variable: V420 Min: 387 Max: 596
## Variable: V421 Min: 461 Max: 500
## Variable: V422 Min: 427 Max: 530
## Variable: V423 Min: 444 Max: 518
## Variable: V424 Min: 474 Max: 478
## Variable: V425 Min: 445 Max: 520
## Variable: V426 Min: 437 Max: 542
## Variable: V427 Min: 435 Max: 549
## Variable: V428 Min: 372 Max: 610
## Variable: V429 Min: 362 Max: 593
## Variable: V430 Min: 463 Max: 493
## Variable: V431 Min: 398 Max: 557
## Variable: V432 Min: 404 Max: 597
## Variable: V433 Min: 383 Max: 584
## Variable: V434 Min: 263 Max: 687
## Variable: V435 Min: 421 Max: 558
## Variable: V436 Min: 389 Max: 648
## Variable: V437 Min: 436 Max: 514
## Variable: V438 Min: 393 Max: 653
## Variable: V439 Min: 368 Max: 583
## Variable: V440 Min: 452 Max: 515
## Variable: V441 Min: 349 Max: 626
## Variable: V442 Min: 423 Max: 542
## Variable: V443 Min: 244 Max: 743
## Variable: V444 Min: 345 Max: 640
## Variable: V445 Min: 435 Max: 575
## Variable: V446 Min: 472 Max: 483
## Variable: V447 Min: 435 Max: 517
## Variable: V448 Min: 449 Max: 532
## Variable: V449 Min: 368 Max: 613
## Variable: V450 Min: 435 Max: 507
## Variable: V451 Min: 433 Max: 536
## Variable: V452 Min: 450 Max: 502
## Variable: V453 Min: 436 Max: 569
## Variable: V454 Min: 84 Max: 807
## Variable: V455 Min: 461 Max: 500
## Variable: V456 Min: 265 Max: 735
## Variable: V457 Min: 462 Max: 501
## Variable: V458 Min: 387 Max: 586
## Variable: V459 Min: 350 Max: 650
## Variable: V460 Min: 383 Max: 592
## Variable: V461 Min: 392 Max: 606
## Variable: V462 Min: 407 Max: 552
## Variable: V463 Min: 383 Max: 625
## Variable: V464 Min: 347 Max: 615
## Variable: V465 Min: 432 Max: 546
## Variable: V466 Min: 426 Max: 566
## Variable: V467 Min: 456 Max: 508
## Variable: V468 Min: 364 Max: 634
## Variable: V469 Min: 408 Max: 539
## Variable: V470 Min: 342 Max: 633
## Variable: V471 Min: 406 Max: 666
## Variable: V472 Min: 465 Max: 493
## Variable: V473 Min: 358 Max: 590
## Variable: V474 Min: 472 Max: 484
## Variable: V475 Min: 459 Max: 499
## Variable: V476 Min: 308 Max: 680
## Variable: V477 Min: 432 Max: 526
## Variable: V478 Min: 423 Max: 548
## Variable: V479 Min: 347 Max: 630
## Variable: V480 Min: 451 Max: 527
## Variable: V481 Min: 418 Max: 554
## Variable: V482 Min: 402 Max: 587
## Variable: V483 Min: 443 Max: 505
## Variable: V484 Min: 394 Max: 601
## Variable: V485 Min: 376 Max: 614
## Variable: V486 Min: 446 Max: 523
## Variable: V487 Min: 444 Max: 512
## Variable: V488 Min: 355 Max: 613
## Variable: V489 Min: 417 Max: 606
## Variable: V490 Min: 449 Max: 513
## Variable: V491 Min: 424 Max: 549
## Variable: V492 Min: 463 Max: 492
## Variable: V493 Min: 413 Max: 566
## Variable: V494 Min: 130 Max: 920
## Variable: V495 Min: 368 Max: 613
## Variable: V496 Min: 403 Max: 627
## Variable: V497 Min: 457 Max: 500
## Variable: V498 Min: 435 Max: 531
## Variable: V499 Min: 363 Max: 633
## Variable: V500 Min: 407 Max: 583
madelonCV <- FRESA.Model(formula = Label ~ 1,data = madelonTrain,pvalue=0.05,filter.p.value = 0.1,CVfolds = 25,repeats = 1,equivalent = TRUE , usrFitFun= svm)
## Unadjusted size: 72 Adjusted Size: 20
## ..
## Vars: 500 Size: 100 , Fraction= 0.824, Average random size = 10.56, Size:211.20
##
## Z: 1.644854 , Var Max: 20 , s1: 501 , s2: 223 , Independent Size: 422
## [1] "V476 + V242 + V49 + V324 + V425 + V283 + V412 + V206 + V297 + V497"
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6151263 : Label ~ 1 + V476 + V49
## 1 : 18 : 0.6118669 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5961139 : Label ~ 1 + V443 + V337
## 3 : 14 : 0.5900495 : Label ~ 1 + V65 + V473
##
## Num. Models: 4 To Test: 8 TopFreq: 1 Thrf: 0 Removed: 0
## CV pvalue : 0.05352224
## Update : Label ~ 1 + V425 + V476 + V49 + V206 + V324
## At Accuray: Label ~ 1 + V476 + V49
## B:SWiMS : Label ~ 1 + V476 + V49
## Loop : 1 Input Cases = 1000 Input Control = 1000
## Loop : 1 Train Cases = 960 Train Control = 960
## Loop : 1 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6138677 : Label ~ 1 + V476 + V425 + V49
## 1 : 17 : 0.6157567 : Label ~ 1 + V242 + V379
## 2 : 15 : 0.5857045 : Label ~ 1 + V324 + V454 + V129
## 3 : 12 : 0.5835986 : Label ~ 1 + V494 + V106
## 4 : 10 : 0.5915924 : Label ~ 1 + V443 + V337
## 5 : 8 : 0.5949769 : Label ~ 1 + V65 + V473
##
## Num. Models: 6 To Test: 14 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V324 + V476 + V425 + V497 + V49 + V206 + V412 + V283
## At Accuracy: Label ~ 1 + V476 + V425 + V49
## B:SWiMS : Label ~ 1 + V476 + V425 + V49
##
## Num. Models: 32 To Test: 14 TopFreq: 26 Thrf: 0 Removed: 0
## ...:::
## Num. Models: 10 To Test: 12 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 1 Blind Cases = 40 Blind Control = 40 Total = 80 Size Cases = 40 Size Control = 40
## Accumulated Models CV Accuracy = 0.525 Sensitivity = 0.5 Specificity = 0.55 Forw. Ensemble Accuracy= 0.55
## Initial Model Accumulated CV Accuracy = 0.5625 Sensitivity = 0.575 Specificity = 0.55
## Initial Model Bootstrapped Accuracy = 0.6181853 Sensitivity = 0.607183 Specificity = 0.6291876
## Current Model Bootstrapped Accuracy = 0.6138677 Sensitivity = 0.6115233 Specificity = 0.616212
## Current KNN Accuracy = 0.8 Sensitivity = 0.725 Specificity = 0.875
## Initial KNN Accuracy = 0.7125 Sensitivity = 0.7 Specificity = 0.725
## Train Correlation: 0.9652786 Blind Correlation : 0.9172527
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 31 15
## TRUE 11 23
## Loop : 2 Input Cases = 1000 Input Control = 1000
## Loop : 2 Train Cases = 960 Train Control = 960
## Loop : 2 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6110135 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6117845 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5849633 : Label ~ 1 + V324 + V454 + V106
## 3 : 13 : 0.5778937 : Label ~ 1 + V494 + V129
## 4 : 11 : 0.5935258 : Label ~ 1 + V443 + V65
## 5 : 9 : 0.5923359 : Label ~ 1 + V337 + V473
##
## Num. Models: 6 To Test: 13 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V476 + V324 + V206 + V283
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 12 TopFreq: 25 Thrf: 0 Removed: 0
## ...::
## Num. Models: 3 To Test: 4 TopFreq: 2 Thrf: 0 Removed: 0
## Loop : 2 Blind Cases = 40 Blind Control = 40 Total = 160 Size Cases = 80 Size Control = 80
## Accumulated Models CV Accuracy = 0.54375 Sensitivity = 0.5375 Specificity = 0.55 Forw. Ensemble Accuracy= 0.54375
## Initial Model Accumulated CV Accuracy = 0.59375 Sensitivity = 0.575 Specificity = 0.6125
## Initial Model Bootstrapped Accuracy = 0.6129354 Sensitivity = 0.6090072 Specificity = 0.6168635
## Current Model Bootstrapped Accuracy = 0.6110135 Sensitivity = 0.605633 Specificity = 0.616394
## Current KNN Accuracy = 0.85 Sensitivity = 0.8125 Specificity = 0.8875
## Initial KNN Accuracy = 0.75 Sensitivity = 0.7875 Specificity = 0.7125
## Train Correlation: 0.9997752 Blind Correlation : 0.9406235
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 56 30
## TRUE 25 49
## Loop : 3 Input Cases = 1000 Input Control = 1000
## Loop : 3 Train Cases = 960 Train Control = 960
## Loop : 3 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6130782 : Label ~ 1 + V476 + V49
## 1 : 18 : 0.6136439 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5914681 : Label ~ 1 + V443 + V337
## 3 : 14 : 0.5965638 : Label ~ 1 + V65 + V473
## 4 : 12 : 0.575371 : Label ~ 1 + V454 + V106
##
## Num. Models: 5 To Test: 10 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V206 + V476 + V205 + V425 + V49 + V297 + V324 + V56
## At Accuracy: Label ~ 1 + V476 + V49
## B:SWiMS : Label ~ 1 + V476 + V49
##
## Num. Models: 32 To Test: 12 TopFreq: 29 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 3 Blind Cases = 40 Blind Control = 40 Total = 240 Size Cases = 120 Size Control = 120
## Accumulated Models CV Accuracy = 0.5708333 Sensitivity = 0.5416667 Specificity = 0.6 Forw. Ensemble Accuracy= 0.5666667
## Initial Model Accumulated CV Accuracy = 0.6125 Sensitivity = 0.5666667 Specificity = 0.6583333
## Initial Model Bootstrapped Accuracy = 0.6130144 Sensitivity = 0.6042164 Specificity = 0.6218123
## Current Model Bootstrapped Accuracy = 0.6130782 Sensitivity = 0.6040664 Specificity = 0.62209
## Current KNN Accuracy = 0.8291667 Sensitivity = 0.7916667 Specificity = 0.8666667
## Initial KNN Accuracy = 0.7583333 Sensitivity = 0.775 Specificity = 0.7416667
## Train Correlation: 0.9999627 Blind Correlation : 0.9658228
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 90 39
## TRUE 37 74
## Loop : 4 Input Cases = 1000 Input Control = 1000
## Loop : 4 Train Cases = 960 Train Control = 960
## Loop : 4 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6199194 : Label ~ 1 + V425 + V476 + V205 + V49
## 1 : 16 : 0.6104286 : Label ~ 1 + V242 + V379
##
## Num. Models: 2 To Test: 6 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V425 + V476 + V205 + V206 + V49 + V497 + V324 + V421 + V283
## At Accuracy: Label ~ 1 + V425 + V476 + V205 + V49
## B:SWiMS : Label ~ 1 + V425 + V476 + V205 + V49
##
## Num. Models: 32 To Test: 12 TopFreq: 29 Thrf: 0 Removed: 0
## ...::::
## Num. Models: 3 To Test: 6 TopFreq: 2 Thrf: 0 Removed: 0
## Loop : 4 Blind Cases = 40 Blind Control = 40 Total = 320 Size Cases = 160 Size Control = 160
## Accumulated Models CV Accuracy = 0.58125 Sensitivity = 0.55625 Specificity = 0.60625 Forw. Ensemble Accuracy= 0.571875
## Initial Model Accumulated CV Accuracy = 0.6125 Sensitivity = 0.575 Specificity = 0.65
## Initial Model Bootstrapped Accuracy = 0.6131765 Sensitivity = 0.6058931 Specificity = 0.6204599
## Current Model Bootstrapped Accuracy = 0.6199194 Sensitivity = 0.6186639 Specificity = 0.6211749
## Current KNN Accuracy = 0.765625 Sensitivity = 0.725 Specificity = 0.80625
## Initial KNN Accuracy = 0.76875 Sensitivity = 0.8 Specificity = 0.7375
## Train Correlation: 0.9337489 Blind Correlation : 0.9305907
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 127 46
## TRUE 41 106
## Loop : 5 Input Cases = 1000 Input Control = 1000
## Loop : 5 Train Cases = 960 Train Control = 960
## Loop : 5 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6141934 : Label ~ 1 + V425 + V476 + V49
## 1 : 17 : 0.6100535 : Label ~ 1 + V242 + V379
## 2 : 15 : 0.5958461 : Label ~ 1 + V443 + V337
## 3 : 13 : 0.5891642 : Label ~ 1 + V65 + V473
##
## Num. Models: 4 To Test: 9 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V425 + V476 + V324 + V49 + V297 + V497 + V56 + V283 + V200
## At Accuracy: Label ~ 1 + V425 + V476 + V49
## B:SWiMS : Label ~ 1 + V425 + V476 + V49
##
## Num. Models: 32 To Test: 12 TopFreq: 28 Thrf: 0 Removed: 0
## ...:::
## Num. Models: 3 To Test: 5 TopFreq: 2 Thrf: 0 Removed: 0
## Loop : 5 Blind Cases = 40 Blind Control = 40 Total = 400 Size Cases = 200 Size Control = 200
## Accumulated Models CV Accuracy = 0.59 Sensitivity = 0.575 Specificity = 0.605 Forw. Ensemble Accuracy= 0.5825
## Initial Model Accumulated CV Accuracy = 0.625 Sensitivity = 0.6 Specificity = 0.65
## Initial Model Bootstrapped Accuracy = 0.609438 Sensitivity = 0.6030005 Specificity = 0.6158756
## Current Model Bootstrapped Accuracy = 0.6141934 Sensitivity = 0.6131721 Specificity = 0.6152148
## Current KNN Accuracy = 0.7825 Sensitivity = 0.76 Specificity = 0.805
## Initial KNN Accuracy = 0.7825 Sensitivity = 0.82 Specificity = 0.745
## Train Correlation: 0.9531343 Blind Correlation : 0.9629395
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 152 57
## TRUE 54 137
## Loop : 6 Input Cases = 1000 Input Control = 1000
## Loop : 6 Train Cases = 960 Train Control = 960
## Loop : 6 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6130956 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6123562 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5932229 : Label ~ 1 + V337 + V443
## 3 : 14 : 0.5945158 : Label ~ 1 + V65 + V473
## 5 : 12 : 0.5776797 : Label ~ 1 + V494 + V106
## 7 : 10 : 0.5781069 : Label ~ 1 + V129 + V454
##
## Num. Models: 6 To Test: 12 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V476 + V206 + V425 + V324 + V497 + V297
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 11 TopFreq: 25 Thrf: 0 Removed: 0
## ...::
## Num. Models: 12 To Test: 13 TopFreq: 11 Thrf: 0 Removed: 0
## .Loop : 6 Blind Cases = 40 Blind Control = 40 Total = 480 Size Cases = 240 Size Control = 240
## Accumulated Models CV Accuracy = 0.5916667 Sensitivity = 0.5791667 Specificity = 0.6041667 Forw. Ensemble Accuracy= 0.5791667
## Initial Model Accumulated CV Accuracy = 0.6229167 Sensitivity = 0.5916667 Specificity = 0.6541667
## Initial Model Bootstrapped Accuracy = 0.6150833 Sensitivity = 0.6082224 Specificity = 0.6219443
## Current Model Bootstrapped Accuracy = 0.6130956 Sensitivity = 0.6078699 Specificity = 0.6183212
## Current KNN Accuracy = 0.775 Sensitivity = 0.7583333 Specificity = 0.7916667
## Initial KNN Accuracy = 0.7645833 Sensitivity = 0.8 Specificity = 0.7291667
## Train Correlation: 0.9998893 Blind Correlation : 0.9817862
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 180 68
## TRUE 66 166
## Loop : 7 Input Cases = 1000 Input Control = 1000
## Loop : 7 Train Cases = 960 Train Control = 960
## Loop : 7 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6115593 : Label ~ 1 + V425 + V476 + V49
## 1 : 17 : 0.6085821 : Label ~ 1 + V242 + V379
## 2 : 15 : 0.5952708 : Label ~ 1 + V337 + V443
## 3 : 13 : 0.5913433 : Label ~ 1 + V65 + V473
## 4 : 11 : 0.5758012 : Label ~ 1 + V129 + V454
##
## Num. Models: 5 To Test: 11 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V425 + V476 + V49 + V297 + V324 + V299 + V283
## At Accuracy: Label ~ 1 + V425 + V476 + V49
## B:SWiMS : Label ~ 1 + V425 + V476 + V49
##
## Num. Models: 32 To Test: 11 TopFreq: 27 Thrf: 0 Removed: 0
## ...:::
## Num. Models: 10 To Test: 12 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 7 Blind Cases = 40 Blind Control = 40 Total = 560 Size Cases = 280 Size Control = 280
## Accumulated Models CV Accuracy = 0.5982143 Sensitivity = 0.5892857 Specificity = 0.6071429 Forw. Ensemble Accuracy= 0.5839286
## Initial Model Accumulated CV Accuracy = 0.625 Sensitivity = 0.5964286 Specificity = 0.6535714
## Initial Model Bootstrapped Accuracy = 0.6133814 Sensitivity = 0.6008617 Specificity = 0.625901
## Current Model Bootstrapped Accuracy = 0.6115593 Sensitivity = 0.6092408 Specificity = 0.6138777
## Current KNN Accuracy = 0.7892857 Sensitivity = 0.775 Specificity = 0.8035714
## Initial KNN Accuracy = 0.7642857 Sensitivity = 0.8071429 Specificity = 0.7214286
## Train Correlation: 0.9653428 Blind Correlation : 0.9620722
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 206 82
## TRUE 79 193
## Loop : 8 Input Cases = 1000 Input Control = 1000
## Loop : 8 Train Cases = 960 Train Control = 960
## Loop : 8 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6185583 : Label ~ 1 + V476 + V49
## 1 : 18 : 0.6161106 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5967442 : Label ~ 1 + V443 + V337
## 4 : 14 : 0.596176 : Label ~ 1 + V473 + V454 + V106 + V339
##
## Num. Models: 4 To Test: 10 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V476 + V206 + V49 + V283 + V324 + V297
## At Accuracy: Label ~ 1 + V476 + V49
## B:SWiMS : Label ~ 1 + V476 + V49
##
## Num. Models: 32 To Test: 12 TopFreq: 25 Thrf: 0 Removed: 0
## ...::
## Num. Models: 3 To Test: 4 TopFreq: 2 Thrf: 0 Removed: 0
## Loop : 8 Blind Cases = 40 Blind Control = 40 Total = 640 Size Cases = 320 Size Control = 320
## Accumulated Models CV Accuracy = 0.5875 Sensitivity = 0.590625 Specificity = 0.584375 Forw. Ensemble Accuracy= 0.56875
## Initial Model Accumulated CV Accuracy = 0.6046875 Sensitivity = 0.590625 Specificity = 0.61875
## Initial Model Bootstrapped Accuracy = 0.616862 Sensitivity = 0.6059882 Specificity = 0.6277358
## Current Model Bootstrapped Accuracy = 0.6185583 Sensitivity = 0.608803 Specificity = 0.6283135
## Current KNN Accuracy = 0.784375 Sensitivity = 0.778125 Specificity = 0.790625
## Initial KNN Accuracy = 0.7578125 Sensitivity = 0.8 Specificity = 0.715625
## Train Correlation: 0.9999992 Blind Correlation : 0.9678387
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 227 97
## TRUE 91 225
## Loop : 9 Input Cases = 1000 Input Control = 1000
## Loop : 9 Train Cases = 960 Train Control = 960
## Loop : 9 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6095839 : Label ~ 1 + V425 + V49 + V476
## 1 : 17 : 0.6088223 : Label ~ 1 + V242 + V379
## 2 : 15 : 0.590003 : Label ~ 1 + V65 + V443
## 3 : 13 : 0.5925996 : Label ~ 1 + V337 + V473
## 4 : 11 : 0.5740424 : Label ~ 1 + V454 + V129
##
## Num. Models: 5 To Test: 11 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V425 + V49 + V476 + V283 + V205 + V297 + V324
## At Accuracy: Label ~ 1 + V425 + V49 + V476
## B:SWiMS : Label ~ 1 + V425 + V49 + V476
##
## Num. Models: 32 To Test: 13 TopFreq: 29 Thrf: 0 Removed: 0
## ...:::
## Num. Models: 9 To Test: 11 TopFreq: 8 Thrf: 0 Removed: 0
## Loop : 9 Blind Cases = 40 Blind Control = 40 Total = 720 Size Cases = 360 Size Control = 360
## Accumulated Models CV Accuracy = 0.5972222 Sensitivity = 0.6 Specificity = 0.5944444 Forw. Ensemble Accuracy= 0.5763889
## Initial Model Accumulated CV Accuracy = 0.6152778 Sensitivity = 0.6027778 Specificity = 0.6277778
## Initial Model Bootstrapped Accuracy = 0.6057805 Sensitivity = 0.5975207 Specificity = 0.6140404
## Current Model Bootstrapped Accuracy = 0.6095839 Sensitivity = 0.6079612 Specificity = 0.6112067
## Current KNN Accuracy = 0.7861111 Sensitivity = 0.7777778 Specificity = 0.7944444
## Initial KNN Accuracy = 0.7541667 Sensitivity = 0.8 Specificity = 0.7083333
## Train Correlation: 0.9571252 Blind Correlation : 0.8851852
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 258 108
## TRUE 100 254
## Loop : 10 Input Cases = 1000 Input Control = 1000
## Loop : 10 Train Cases = 960 Train Control = 960
## Loop : 10 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6132404 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6121688 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5897031 : Label ~ 1 + V443 + V337
## 3 : 14 : 0.5879488 : Label ~ 1 + V65 + V473
##
## Num. Models: 4 To Test: 8 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V476 + V425 + V324 + V206 + V120 + V283 + V56
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 15 TopFreq: 24 Thrf: 0 Removed: 0
## ...::
## Num. Models: 3 To Test: 4 TopFreq: 2 Thrf: 0 Removed: 0
## Loop : 10 Blind Cases = 40 Blind Control = 40 Total = 800 Size Cases = 400 Size Control = 400
## Accumulated Models CV Accuracy = 0.6025 Sensitivity = 0.6025 Specificity = 0.6025 Forw. Ensemble Accuracy= 0.57875
## Initial Model Accumulated CV Accuracy = 0.6175 Sensitivity = 0.6025 Specificity = 0.6325
## Initial Model Bootstrapped Accuracy = 0.615304 Sensitivity = 0.6094284 Specificity = 0.6211795
## Current Model Bootstrapped Accuracy = 0.6132404 Sensitivity = 0.6026786 Specificity = 0.6238023
## Current KNN Accuracy = 0.7875 Sensitivity = 0.7875 Specificity = 0.7875
## Initial KNN Accuracy = 0.75875 Sensitivity = 0.8075 Specificity = 0.71
## Train Correlation: 0.9999784 Blind Correlation : 0.9837084
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 284 116
## TRUE 116 284
## Loop : 11 Input Cases = 1000 Input Control = 1000
## Loop : 11 Train Cases = 960 Train Control = 960
## Loop : 11 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6136784 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6117427 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5941024 : Label ~ 1 + V443 + V337
## 3 : 14 : 0.5926336 : Label ~ 1 + V65 + V473
##
## Num. Models: 4 To Test: 8 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V476 + V206 + V378 + V324 + V497 + V120
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 11 TopFreq: 25 Thrf: 0 Removed: 0
## ...::
## Num. Models: 3 To Test: 4 TopFreq: 2 Thrf: 0 Removed: 0
## Loop : 11 Blind Cases = 40 Blind Control = 40 Total = 880 Size Cases = 440 Size Control = 440
## Accumulated Models CV Accuracy = 0.6034091 Sensitivity = 0.6045455 Specificity = 0.6022727 Forw. Ensemble Accuracy= 0.5795455
## Initial Model Accumulated CV Accuracy = 0.6159091 Sensitivity = 0.6045455 Specificity = 0.6272727
## Initial Model Bootstrapped Accuracy = 0.6111233 Sensitivity = 0.603623 Specificity = 0.6186235
## Current Model Bootstrapped Accuracy = 0.6136784 Sensitivity = 0.6038923 Specificity = 0.6234645
## Current KNN Accuracy = 0.7829545 Sensitivity = 0.7840909 Specificity = 0.7818182
## Initial KNN Accuracy = 0.7568182 Sensitivity = 0.8022727 Specificity = 0.7113636
## Train Correlation: 0.9999418 Blind Correlation : 0.9401078
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 310 129
## TRUE 129 312
## Loop : 12 Input Cases = 1000 Input Control = 1000
## Loop : 12 Train Cases = 960 Train Control = 960
## Loop : 12 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6100257 : Label ~ 1 + V49 + V425 + V476
## 1 : 17 : 0.6105823 : Label ~ 1 + V242 + V379
## 3 : 15 : 0.5754209 : Label ~ 1 + V454 + V129
## 4 : 13 : 0.5744833 : Label ~ 1 + V494 + V106
## 5 : 11 : 0.5934376 : Label ~ 1 + V443 + V337
## 6 : 9 : 0.5944272 : Label ~ 1 + V65 + V473
##
## Num. Models: 6 To Test: 13 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V425 + V476 + V205 + V421 + V324 + V497
## At Accuracy: Label ~ 1 + V49 + V425 + V476
## B:SWiMS : Label ~ 1 + V49 + V425 + V476
##
## Num. Models: 32 To Test: 12 TopFreq: 29 Thrf: 0 Removed: 0
## ...:::
## Num. Models: 10 To Test: 12 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 12 Blind Cases = 40 Blind Control = 40 Total = 960 Size Cases = 480 Size Control = 480
## Accumulated Models CV Accuracy = 0.6083333 Sensitivity = 0.60625 Specificity = 0.6104167 Forw. Ensemble Accuracy= 0.5875
## Initial Model Accumulated CV Accuracy = 0.621875 Sensitivity = 0.6083333 Specificity = 0.6354167
## Initial Model Bootstrapped Accuracy = 0.6102917 Sensitivity = 0.6042852 Specificity = 0.6162982
## Current Model Bootstrapped Accuracy = 0.6100257 Sensitivity = 0.6059552 Specificity = 0.6140961
## Current KNN Accuracy = 0.7875 Sensitivity = 0.78125 Specificity = 0.79375
## Initial KNN Accuracy = 0.753125 Sensitivity = 0.7916667 Specificity = 0.7145833
## Train Correlation: 0.9628324 Blind Correlation : 0.9064463
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 343 143
## TRUE 139 335
## Loop : 13 Input Cases = 1000 Input Control = 1000
## Loop : 13 Train Cases = 960 Train Control = 960
## Loop : 13 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6064593 : Label ~ 1 + V49 + V242
## 1 : 18 : 0.6121364 : Label ~ 1 + V476 + V379
## 2 : 16 : 0.5903705 : Label ~ 1 + V443 + V337
## 3 : 14 : 0.58315 : Label ~ 1 + V65 + V473
## 5 : 12 : 0.5737412 : Label ~ 1 + V129 + V454
##
## Num. Models: 5 To Test: 10 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V324 + V385 + V242 + V497 + V205 + V283 + V297 + V412
## At Accuracy: Label ~ 1 + V49 + V242
## B:SWiMS : Label ~ 1 + V49 + V242
##
## Num. Models: 32 To Test: 12 TopFreq: 25 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 13 Blind Cases = 40 Blind Control = 40 Total = 1040 Size Cases = 520 Size Control = 520
## Accumulated Models CV Accuracy = 0.6105769 Sensitivity = 0.6115385 Specificity = 0.6096154 Forw. Ensemble Accuracy= 0.5894231
## Initial Model Accumulated CV Accuracy = 0.6221154 Sensitivity = 0.6115385 Specificity = 0.6326923
## Initial Model Bootstrapped Accuracy = 0.6068234 Sensitivity = 0.5979203 Specificity = 0.6157265
## Current Model Bootstrapped Accuracy = 0.6064593 Sensitivity = 0.5993712 Specificity = 0.6135474
## Current KNN Accuracy = 0.7903846 Sensitivity = 0.7884615 Specificity = 0.7903846
## Initial KNN Accuracy = 0.7548077 Sensitivity = 0.7980769 Specificity = 0.7115385
## Train Correlation: 0.9936798 Blind Correlation : 0.9640647
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 367 155
## TRUE 152 366
## Loop : 14 Input Cases = 1000 Input Control = 1000
## Loop : 14 Train Cases = 960 Train Control = 960
## Loop : 14 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6154092 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6148617 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5907483 : Label ~ 1 + V443 + V65
## 3 : 14 : 0.5964803 : Label ~ 1 + V337 + V473
##
## Num. Models: 4 To Test: 8 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V476 + V432 + V324
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 14 TopFreq: 23 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 14 Blind Cases = 40 Blind Control = 40 Total = 1120 Size Cases = 560 Size Control = 560
## Accumulated Models CV Accuracy = 0.6071429 Sensitivity = 0.6107143 Specificity = 0.6035714 Forw. Ensemble Accuracy= 0.5839286
## Initial Model Accumulated CV Accuracy = 0.6142857 Sensitivity = 0.6071429 Specificity = 0.6214286
## Initial Model Bootstrapped Accuracy = 0.6142996 Sensitivity = 0.6035148 Specificity = 0.6250844
## Current Model Bootstrapped Accuracy = 0.6154092 Sensitivity = 0.6089945 Specificity = 0.621824
## Current KNN Accuracy = 0.7839286 Sensitivity = 0.7821429 Specificity = 0.7839286
## Initial KNN Accuracy = 0.7508929 Sensitivity = 0.7910714 Specificity = 0.7107143
## Train Correlation: 0.9991969 Blind Correlation : 0.9683779
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 395 167
## TRUE 161 397
## Loop : 15 Input Cases = 1000 Input Control = 1000
## Loop : 15 Train Cases = 960 Train Control = 960
## Loop : 15 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6108441 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6155699 : Label ~ 1 + V242 + V379 + V425
## 2 : 15 : 0.5925936 : Label ~ 1 + V443 + V337
## 3 : 13 : 0.5931166 : Label ~ 1 + V65 + V473
##
## Num. Models: 4 To Test: 9 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V425 + V476 + V206 + V205 + V283 + V324 + V330
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 13 TopFreq: 25 Thrf: 0 Removed: 0
## ...::
## Num. Models: 12 To Test: 13 TopFreq: 11 Thrf: 0 Removed: 0
## .Loop : 15 Blind Cases = 40 Blind Control = 40 Total = 1200 Size Cases = 600 Size Control = 600
## Accumulated Models CV Accuracy = 0.6083333 Sensitivity = 0.6116667 Specificity = 0.605 Forw. Ensemble Accuracy= 0.5866667
## Initial Model Accumulated CV Accuracy = 0.6183333 Sensitivity = 0.61 Specificity = 0.6266667
## Initial Model Bootstrapped Accuracy = 0.6089101 Sensitivity = 0.6016853 Specificity = 0.6161348
## Current Model Bootstrapped Accuracy = 0.6108441 Sensitivity = 0.6045188 Specificity = 0.6171694
## Current KNN Accuracy = 0.785 Sensitivity = 0.7833333 Specificity = 0.785
## Initial KNN Accuracy = 0.7541667 Sensitivity = 0.7916667 Specificity = 0.7166667
## Train Correlation: 0.9999843 Blind Correlation : 0.9521097
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 423 179
## TRUE 173 425
## Loop : 16 Input Cases = 1000 Input Control = 1000
## Loop : 16 Train Cases = 960 Train Control = 960
## Loop : 16 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6092111 : Label ~ 1 + V476 + V49
## 1 : 18 : 0.6092545 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5914745 : Label ~ 1 + V337 + V443
##
## Num. Models: 3 To Test: 6 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V324 + V476 + V49 + V425 + V497 + V482
## At Accuracy: Label ~ 1 + V476 + V49
## B:SWiMS : Label ~ 1 + V476 + V49
##
## Num. Models: 32 To Test: 13 TopFreq: 26 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 16 Blind Cases = 40 Blind Control = 40 Total = 1280 Size Cases = 640 Size Control = 640
## Accumulated Models CV Accuracy = 0.6117187 Sensitivity = 0.621875 Specificity = 0.6015625 Forw. Ensemble Accuracy= 0.59375
## Initial Model Accumulated CV Accuracy = 0.621875 Sensitivity = 0.6203125 Specificity = 0.6234375
## Initial Model Bootstrapped Accuracy = 0.6089825 Sensitivity = 0.5980235 Specificity = 0.6199415
## Current Model Bootstrapped Accuracy = 0.6092111 Sensitivity = 0.5952692 Specificity = 0.6231529
## Current KNN Accuracy = 0.784375 Sensitivity = 0.784375 Specificity = 0.7828125
## Initial KNN Accuracy = 0.7554688 Sensitivity = 0.7953125 Specificity = 0.715625
## Train Correlation: 0.9999516 Blind Correlation : 0.9983826
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 445 195
## TRUE 182 458
## Loop : 17 Input Cases = 1000 Input Control = 1000
## Loop : 17 Train Cases = 960 Train Control = 960
## Loop : 17 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.608756 : Label ~ 1 + V49 + V242
## 1 : 18 : 0.6082211 : Label ~ 1 + V476 + V379
## 2 : 16 : 0.592325 : Label ~ 1 + V443 + V337
## 3 : 14 : 0.5889612 : Label ~ 1 + V65 + V473
## 4 : 12 : 0.5767398 : Label ~ 1 + V129 + V454
## 5 : 10 : 0.5845806 : Label ~ 1 + V494 + V106 + V324
## 6 : 7 : 0.5747904 : Label ~ 1 + V339
##
## Num. Models: 7 To Test: 14 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V425 + V49 + V324 + V242 + V432 + V206 + V297 + V385 + V56
## At Accuracy: Label ~ 1 + V49 + V242
## B:SWiMS : Label ~ 1 + V49 + V242
##
## Num. Models: 32 To Test: 11 TopFreq: 28 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 17 Blind Cases = 40 Blind Control = 40 Total = 1360 Size Cases = 680 Size Control = 680
## Accumulated Models CV Accuracy = 0.6125 Sensitivity = 0.6176471 Specificity = 0.6073529 Forw. Ensemble Accuracy= 0.5955882
## Initial Model Accumulated CV Accuracy = 0.6227941 Sensitivity = 0.6147059 Specificity = 0.6308824
## Initial Model Bootstrapped Accuracy = 0.6102483 Sensitivity = 0.6058416 Specificity = 0.614655
## Current Model Bootstrapped Accuracy = 0.608756 Sensitivity = 0.6034672 Specificity = 0.6140447
## Current KNN Accuracy = 0.7904412 Sensitivity = 0.7882353 Specificity = 0.7911765
## Initial KNN Accuracy = 0.7566176 Sensitivity = 0.7941176 Specificity = 0.7191176
## Train Correlation: 0.9936663 Blind Correlation : 0.8776606
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 475 208
## TRUE 198 479
## Loop : 18 Input Cases = 1000 Input Control = 1000
## Loop : 18 Train Cases = 960 Train Control = 960
## Loop : 18 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6105048 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6111051 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5782059 : Label ~ 1 + V454 + V129
## 3 : 14 : 0.5805143 : Label ~ 1 + V494 + V106
## 4 : 12 : 0.5922961 : Label ~ 1 + V443 + V337
## 5 : 10 : 0.5976449 : Label ~ 1 + V65 + V473
##
## Num. Models: 6 To Test: 12 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V205 + V476 + V206 + V378 + V283 + V324 + V137
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 12 TopFreq: 27 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 18 Blind Cases = 40 Blind Control = 40 Total = 1440 Size Cases = 720 Size Control = 720
## Accumulated Models CV Accuracy = 0.6097222 Sensitivity = 0.6138889 Specificity = 0.6055556 Forw. Ensemble Accuracy= 0.5916667
## Initial Model Accumulated CV Accuracy = 0.6215278 Sensitivity = 0.6138889 Specificity = 0.6291667
## Initial Model Bootstrapped Accuracy = 0.6142971 Sensitivity = 0.6041084 Specificity = 0.6244858
## Current Model Bootstrapped Accuracy = 0.6105048 Sensitivity = 0.6028031 Specificity = 0.6182066
## Current KNN Accuracy = 0.79375 Sensitivity = 0.7888889 Specificity = 0.7972222
## Initial KNN Accuracy = 0.7548611 Sensitivity = 0.7888889 Specificity = 0.7208333
## Train Correlation: 0.999707 Blind Correlation : 0.9491092
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 503 224
## TRUE 211 502
## Loop : 19 Input Cases = 1000 Input Control = 1000
## Loop : 19 Train Cases = 960 Train Control = 960
## Loop : 19 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6161077 : Label ~ 1 + V425 + V476 + V49
## 1 : 17 : 0.6151337 : Label ~ 1 + V242 + V379
## 2 : 15 : 0.5983732 : Label ~ 1 + V337 + V443
## 3 : 13 : 0.5974692 : Label ~ 1 + V65 + V473
##
## Num. Models: 4 To Test: 9 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V425 + V476 + V324 + V49 + V385 + V287 + V431 + V283
## At Accuracy: Label ~ 1 + V425 + V476 + V49
## B:SWiMS : Label ~ 1 + V425 + V476 + V49
##
## Num. Models: 32 To Test: 11 TopFreq: 27 Thrf: 0 Removed: 0
## ...:::
## Num. Models: 3 To Test: 5 TopFreq: 2 Thrf: 0 Removed: 0
## Loop : 19 Blind Cases = 40 Blind Control = 40 Total = 1520 Size Cases = 760 Size Control = 760
## Accumulated Models CV Accuracy = 0.6039474 Sensitivity = 0.6144737 Specificity = 0.5934211 Forw. Ensemble Accuracy= 0.5868421
## Initial Model Accumulated CV Accuracy = 0.6151316 Sensitivity = 0.6118421 Specificity = 0.6184211
## Initial Model Bootstrapped Accuracy = 0.6153275 Sensitivity = 0.6075786 Specificity = 0.6230765
## Current Model Bootstrapped Accuracy = 0.6161077 Sensitivity = 0.6132397 Specificity = 0.6189757
## Current KNN Accuracy = 0.7888158 Sensitivity = 0.7855263 Specificity = 0.7907895
## Initial KNN Accuracy = 0.7513158 Sensitivity = 0.7855263 Specificity = 0.7171053
## Train Correlation: 0.9652834 Blind Correlation : 0.9431959
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 527 238
## TRUE 217 538
## Loop : 20 Input Cases = 1000 Input Control = 1000
## Loop : 20 Train Cases = 960 Train Control = 960
## Loop : 20 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6089954 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6116476 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5957663 : Label ~ 1 + V337 + V443
## 3 : 14 : 0.5954004 : Label ~ 1 + V65 + V473
## 5 : 12 : 0.5774549 : Label ~ 1 + V494 + V106
##
## Num. Models: 5 To Test: 10 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V324 + V49 + V476 + V425 + V432 + V385 + V297
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 12 TopFreq: 24 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 20 Blind Cases = 40 Blind Control = 40 Total = 1600 Size Cases = 800 Size Control = 800
## Accumulated Models CV Accuracy = 0.605625 Sensitivity = 0.6075 Specificity = 0.60375 Forw. Ensemble Accuracy= 0.58625
## Initial Model Accumulated CV Accuracy = 0.618125 Sensitivity = 0.61125 Specificity = 0.625
## Initial Model Bootstrapped Accuracy = 0.6150967 Sensitivity = 0.6084923 Specificity = 0.6217012
## Current Model Bootstrapped Accuracy = 0.6089954 Sensitivity = 0.5988117 Specificity = 0.6191792
## Current KNN Accuracy = 0.790625 Sensitivity = 0.78375 Specificity = 0.79625
## Initial KNN Accuracy = 0.749375 Sensitivity = 0.7775 Specificity = 0.72125
## Train Correlation: 0.9997226 Blind Correlation : 0.9703
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 562 249
## TRUE 235 554
## Loop : 21 Input Cases = 1000 Input Control = 1000
## Loop : 21 Train Cases = 960 Train Control = 960
## Loop : 21 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6115272 : Label ~ 1 + V476 + V49
## 1 : 18 : 0.6156934 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5791918 : Label ~ 1 + V454 + V129
## 3 : 14 : 0.595594 : Label ~ 1 + V337 + V443
## 4 : 12 : 0.5969059 : Label ~ 1 + V65 + V473
## 5 : 10 : 0.5801503 : Label ~ 1 + V494 + V106
##
## Num. Models: 6 To Test: 12 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V205 + V476 + V49 + V432 + V425 + V324 + V385 + V299 + V56
## At Accuracy: Label ~ 1 + V476 + V49
## B:SWiMS : Label ~ 1 + V476 + V49
##
## Num. Models: 32 To Test: 11 TopFreq: 26 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 21 Blind Cases = 40 Blind Control = 40 Total = 1680 Size Cases = 840 Size Control = 840
## Accumulated Models CV Accuracy = 0.6029762 Sensitivity = 0.6083333 Specificity = 0.597619 Forw. Ensemble Accuracy= 0.5821429
## Initial Model Accumulated CV Accuracy = 0.6136905 Sensitivity = 0.6107143 Specificity = 0.6166667
## Initial Model Bootstrapped Accuracy = 0.6165478 Sensitivity = 0.6068901 Specificity = 0.6262055
## Current Model Bootstrapped Accuracy = 0.6115272 Sensitivity = 0.5989701 Specificity = 0.6240844
## Current KNN Accuracy = 0.7886905 Sensitivity = 0.7821429 Specificity = 0.7940476
## Initial KNN Accuracy = 0.7464286 Sensitivity = 0.7738095 Specificity = 0.7190476
## Train Correlation: 0.9997393 Blind Correlation : 0.9594233
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 586 265
## TRUE 245 584
## Loop : 22 Input Cases = 1000 Input Control = 1000
## Loop : 22 Train Cases = 960 Train Control = 960
## Loop : 22 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6131963 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6133731 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5946304 : Label ~ 1 + V443 + V337
## 3 : 14 : 0.5951587 : Label ~ 1 + V65 + V473
## 5 : 12 : 0.5768861 : Label ~ 1 + V454 + V129
##
## Num. Models: 5 To Test: 10 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V476 + V206 + V205 + V412 + V330 + V324
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 12 TopFreq: 23 Thrf: 0 Removed: 0
## ...::
## Num. Models: 3 To Test: 4 TopFreq: 2 Thrf: 0 Removed: 0
## Loop : 22 Blind Cases = 40 Blind Control = 40 Total = 1760 Size Cases = 880 Size Control = 880
## Accumulated Models CV Accuracy = 0.6017045 Sensitivity = 0.6034091 Specificity = 0.6 Forw. Ensemble Accuracy= 0.5829545
## Initial Model Accumulated CV Accuracy = 0.6125 Sensitivity = 0.6068182 Specificity = 0.6181818
## Initial Model Bootstrapped Accuracy = 0.6117569 Sensitivity = 0.6035522 Specificity = 0.6199616
## Current Model Bootstrapped Accuracy = 0.6131963 Sensitivity = 0.6075844 Specificity = 0.6188082
## Current KNN Accuracy = 0.7903409 Sensitivity = 0.7852273 Specificity = 0.7943182
## Initial KNN Accuracy = 0.7454545 Sensitivity = 0.7704545 Specificity = 0.7204545
## Train Correlation: 0.9999968 Blind Correlation : 0.9620956
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 616 273
## TRUE 261 610
## Loop : 23 Input Cases = 1000 Input Control = 1000
## Loop : 23 Train Cases = 960 Train Control = 960
## Loop : 23 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6136433 : Label ~ 1 + V49 + V476
## 1 : 18 : 0.6137721 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.593343 : Label ~ 1 + V337 + V443
## 3 : 14 : 0.5936384 : Label ~ 1 + V65 + V473
## 5 : 12 : 0.5800789 : Label ~ 1 + V454 + V106
##
## Num. Models: 5 To Test: 10 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V49 + V476 + V206 + V120 + V425 + V11 + V324 + V297 + V56
## At Accuracy: Label ~ 1 + V49 + V476
## B:SWiMS : Label ~ 1 + V49 + V476
##
## Num. Models: 32 To Test: 12 TopFreq: 23 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 23 Blind Cases = 40 Blind Control = 40 Total = 1840 Size Cases = 920 Size Control = 920
## Accumulated Models CV Accuracy = 0.6027174 Sensitivity = 0.6021739 Specificity = 0.6032609 Forw. Ensemble Accuracy= 0.5831522
## Initial Model Accumulated CV Accuracy = 0.6130435 Sensitivity = 0.6065217 Specificity = 0.6195652
## Initial Model Bootstrapped Accuracy = 0.612239 Sensitivity = 0.603402 Specificity = 0.6210759
## Current Model Bootstrapped Accuracy = 0.6136433 Sensitivity = 0.6032125 Specificity = 0.6240741
## Current KNN Accuracy = 0.788587 Sensitivity = 0.7782609 Specificity = 0.7978261
## Initial KNN Accuracy = 0.7434783 Sensitivity = 0.7630435 Specificity = 0.723913
## Train Correlation: 0.9999446 Blind Correlation : 0.9536099
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 653 286
## TRUE 268 633
## Loop : 24 Input Cases = 1000 Input Control = 1000
## Loop : 24 Train Cases = 960 Train Control = 960
## Loop : 24 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6136259 : Label ~ 1 + V476 + V49
## 1 : 18 : 0.6135603 : Label ~ 1 + V242 + V379
## 2 : 16 : 0.5944843 : Label ~ 1 + V337 + V443
## 3 : 14 : 0.5924912 : Label ~ 1 + V65 + V473
## 4 : 12 : 0.5808706 : Label ~ 1 + V324 + V129 + V454
## 6 : 9 : 0.575727 : Label ~ 1 + V494 + V106
##
## Num. Models: 6 To Test: 13 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V324 + V476 + V49 + V425 + V431 + V120 + V212 + V283 + V412
## At Accuracy: Label ~ 1 + V476 + V49
## B:SWiMS : Label ~ 1 + V476 + V49
##
## Num. Models: 32 To Test: 12 TopFreq: 27 Thrf: 0 Removed: 0
## ...::
## Num. Models: 10 To Test: 11 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 24 Blind Cases = 40 Blind Control = 40 Total = 1920 Size Cases = 960 Size Control = 960
## Accumulated Models CV Accuracy = 0.6026042 Sensitivity = 0.6020833 Specificity = 0.603125 Forw. Ensemble Accuracy= 0.5807292
## Initial Model Accumulated CV Accuracy = 0.6114583 Sensitivity = 0.6052083 Specificity = 0.6177083
## Initial Model Bootstrapped Accuracy = 0.6124185 Sensitivity = 0.6024749 Specificity = 0.6223622
## Current Model Bootstrapped Accuracy = 0.6136259 Sensitivity = 0.6044368 Specificity = 0.6228149
## Current KNN Accuracy = 0.790625 Sensitivity = 0.7791667 Specificity = 0.8010417
## Initial KNN Accuracy = 0.7416667 Sensitivity = 0.7625 Specificity = 0.7208333
## Train Correlation: 1 Blind Correlation : 0.9122363
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 679 303
## TRUE 282 656
## Loop : 25 Input Cases = 1000 Input Control = 1000
## Loop : 25 Train Cases = 960 Train Control = 960
## Loop : 25 Blind Cases = 40 Blind Control = 40
## K : 43 KNN T Cases = 960 KNN T Control = 960
## 222 : Number of variables to test: 20
## 0 : 20 : 0.6146862 : Label ~ 1 + V425 + V49 + V476
## 1 : 17 : 0.6129814 : Label ~ 1 + V242 + V379
##
## Num. Models: 2 To Test: 5 TopFreq: 1 Thrf: 0 Removed: 0
## Update : Label ~ 1 + V425 + V431 + V49 + V324 + V476 + V205 + V206 + V495
## At Accuracy: Label ~ 1 + V425 + V49 + V476
## B:SWiMS : Label ~ 1 + V425 + V49 + V476
##
## Num. Models: 32 To Test: 14 TopFreq: 23 Thrf: 0 Removed: 0
## ...:::
## Num. Models: 10 To Test: 12 TopFreq: 9 Thrf: 0 Removed: 0
## .Loop : 25 Blind Cases = 40 Blind Control = 40 Total = 2000 Size Cases = 1000 Size Control = 1000
## Accumulated Models CV Accuracy = 0.605 Sensitivity = 0.604 Specificity = 0.606 Forw. Ensemble Accuracy= 0.583
## Initial Model Accumulated CV Accuracy = 0.614 Sensitivity = 0.606 Specificity = 0.622
## Initial Model Bootstrapped Accuracy = 0.609959 Sensitivity = 0.6023756 Specificity = 0.6175423
## Current Model Bootstrapped Accuracy = 0.6146862 Sensitivity = 0.6099549 Specificity = 0.6194175
## Current KNN Accuracy = 0.7845 Sensitivity = 0.773 Specificity = 0.795
## Initial KNN Accuracy = 0.746 Sensitivity = 0.765 Specificity = 0.727
## Train Correlation: 0.963157 Blind Correlation : 0.980497
## KNN to Model Confusion Matrix:
##
## FALSE TRUE
## FALSE 716 307
## TRUE 286 691
##
## Num. Models: 128 To Test: 20 TopFreq: 22 Thrf: 0 Removed: 0
## ............::
## Num. Models: 3 To Test: 4 TopFreq: 2 Thrf: 0 Removed: 0
pm <- plotModels.ROC(madelonCV$cvObject$LASSO.testPredictions,theCVfolds=25,main="CV LASSO",cex=0.90)
pm <- plotModels.ROC(madelonCV$cvObject$KNN.testPrediction,theCVfolds=25,main="KNN",cex=0.90)
pm <- plotModels.ROC(madelonCV$cvObject$Models.testPrediction,theCVfolds=25,predictor="Prediction",main="BB:SWiMS",cex=0.90)
pm <- plotModels.ROC(madelonCV$cvObject$Models.testPrediction,theCVfolds=25,predictor="Median",main="Forward Median",cex=0.90)
pm <- plotModels.ROC(madelonCV$cvObject$Models.testPrediction,theCVfolds=25,predictor="Bagged",main="Forward Bagged",cex=0.90)
pm <- plotModels.ROC(madelonCV$cvObject$Models.testPrediction,theCVfolds=25,predictor="Forward",main="Forward Model",cex=0.90)
pm <- plotModels.ROC(madelonCV$cvObject$Models.testPrediction,theCVfolds=25,predictor="first.B.SWiMS",main="first.B.SWiMS",cex=0.90)
pm <- plotModels.ROC(madelonCV$cvObject$Models.testPrediction,theCVfolds=25,predictor="eB.SWiMS",main="eB.SWiMS",cex=0.90)
pm <- plotModels.ROC(madelonCV$cvObject$Models.testPrediction,theCVfolds=25,predictor="Ensemble.B.SWiMS",main="Ensemble.B.SWiMS",cex=0.90)
madelonCV$cvObject$Models.testPrediction$usrFitFunction <- madelonCV$cvObject$Models.testPrediction$usrFitFunction-0.5
pm <- plotModels.ROC(madelonCV$cvObject$Models.testPrediction,theCVfolds=25,
predictor="usrFitFunction",main="Support Vector Machine",cex=0.90)
madelonCV$cvObject$Models.testPrediction$usrFitFunction_Sel <- madelonCV$cvObject$Models.testPrediction$usrFitFunction_Sel-0.5
pm <- plotModels.ROC(madelonCV$cvObject$Models.testPrediction,theCVfolds=25,
predictor="usrFitFunction_Sel",main="Support Vector Machine with FS",cex=0.90)
