Level Risiko Investasi
Camila Nurahma
2024-10-23
library(naniar)
library(VIM)## Loading required package: colorspace## Loading required package: grid## VIM is ready to use.## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues##
## Attaching package: 'VIM'## The following object is masked from 'package:datasets':
##
## sleeplibrary(missMDA)
library(lattice)
library(ggplot2)
library(datasets)
library(mice)##
## Attaching package: 'mice'## The following object is masked from 'package:stats':
##
## filter## The following objects are masked from 'package:base':
##
## cbind, rbindlibrary(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(e1071)
library(caret)
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.1
## ✔ readr 2.1.5## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks mice::filter(), stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ purrr::lift() masks caret::lift()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(rmarkdown)Memanggil Data dari Path yang Sama
data3<- read.csv("dataresiko.csv", stringsAsFactors = TRUE)
data3## Country X1 X2 X3 X4 X5 X6 X7
## 1 AD 17.5000 38674.6160 172.75400 0.68000 1.2206 1.78560 -2.0843
## 2 AE 18.2000 40105.1201 103.52280 1.76600 0.8698 2.65884 -0.7254
## 3 AE-AZ 18.7000 76037.9968 31.03626 2.63056 1.4893 1.85034 -1.9008
## 4 AE-RK NA 27882.8286 24.78532 1.29416 1.7530 2.23192 -1.1355
## 5 AM 14.0000 4251.3977 89.61882 1.44000 0.2562 4.74800 2.3318
## 6 AO NA 2033.8999 57.05566 22.35646 3.3422 -0.87800 -5.2032
## 7 AR 23.2527 9203.4287 43.25546 36.70346 0.9657 -0.23680 -3.7297
## 8 AT 18.5740 53174.2385 159.39690 1.52348 0.7259 1.88048 -0.3001
## 9 AU 15.7000 63972.3400 121.98890 1.65124 1.4790 2.44592 0.0306
## 10 AW 33.5000 24642.7034 92.84624 1.21694 0.7972 2.06486 -4.7211
## 11 AZ 25.3012 5083.2568 43.35272 6.85276 1.0510 0.39070 -1.7366
## 12 BD 4.2000 2323.5586 19.74352 5.81200 1.0568 7.39000 6.0712
## 13 BE 19.3188 49537.5785 256.72570 1.64000 0.5259 1.70044 -0.4905
## 14 BG 22.7406 11288.8489 70.29080 0.77854 -0.7095 3.61996 2.7008
## 15 BH 20.0000 22003.1172 214.20080 1.82200 4.4021 2.80902 -3.2531
## 16 BJ 10.5000 1420.6492 49.56500 0.22520 2.7684 4.87736 2.2133
## 17 BO 12.2800 3372.3576 32.27932 2.92384 1.4362 3.95132 -0.0467
## 18 BR 19.1400 7372.9153 35.67380 5.72400 0.7789 -0.46082 -1.3423
## 19 BY NA 6453.9238 69.54962 8.39000 0.0197 0.10000 0.6603
## 20 CA 16.0956 51704.8992 117.76010 1.67406 1.1918 1.79828 -0.5879
## 21 CG 22.3000 2378.0444 70.34826 2.03374 2.5889 -5.13500 -8.1338
## 22 CH 19.3000 89770.8521 275.61690 0.00116 0.8402 1.88522 0.1733
## 23 CI NA 2594.7038 35.68100 0.75212 2.5779 7.29640 3.3099
## 24 CL 14.2800 15986.3031 65.82414 2.97824 1.2484 1.97106 -0.8925
## 25 CM 9.1000 1690.8639 39.74812 1.54052 2.6442 4.35350 0.7177
## 26 CN 14.7045 12226.6610 13.63044 2.00000 0.4575 6.64354 5.2661
## 27 CO 17.2000 5859.6535 47.58910 4.70940 1.3766 2.44972 -0.8876
## 28 CR 13.2840 11954.5890 44.98044 1.34600 0.9961 3.24766 0.7026
## 29 CV 19.4200 3466.2500 115.31060 0.37920 1.1636 3.92138 -0.4036
## 30 CY 16.0000 30630.2905 1026.49500 -0.15102 0.1535 4.62534 2.8078
## 31 CZ 21.3796 27044.7929 79.21186 1.57500 0.2067 3.72134 1.3165
## 32 DE 18.5800 50891.5812 165.29300 1.20768 0.4835 1.62892 -0.1226
## 33 DK 22.6000 67565.6556 155.84030 0.54000 0.3613 2.68708 1.3106
## 34 DO 18.6500 8172.2496 42.49502 2.22228 0.9213 6.05690 2.4036
## 35 EC 13.4000 5830.4242 49.66284 1.23328 1.7062 0.50846 -2.7675
## 36 EE 25.3120 26427.0455 84.20358 2.03974 0.2136 3.94866 2.6995
## 37 EG 20.1000 3756.4221 31.92960 16.16054 2.0540 4.44796 2.2412
## 38 ES 16.9822 30488.0476 176.49180 0.71830 0.3949 2.84406 -0.4857
## 39 ET NA 891.6737 33.04222 10.37682 2.6572 9.06000 5.5428
## 40 FI 20.1000 53937.2819 257.89490 0.67100 0.2165 1.82644 0.9465
## 41 FR 19.6501 44939.9046 247.44200 0.99026 0.2532 1.63728 -0.4225
## 42 GA NA 7803.8309 39.13694 2.80396 2.7047 2.25300 -1.5934
## 43 GB 21.6000 46723.9041 406.04150 1.53050 0.6090 1.70254 -1.3484
## 44 GE 17.6000 4422.7082 104.45110 3.93800 -0.0317 4.12018 2.3147
## 45 GH 15.0000 2353.8541 59.62672 12.94200 2.2431 5.29400 2.6949
## 46 GR 16.6643 19404.1830 239.31940 0.26994 -0.2217 0.75896 -0.5866
## 47 GT 16.1000 4478.2807 34.07538 3.74200 1.9677 3.40778 0.3178
## 48 HK 20.7000 50214.6484 446.31540 2.43600 0.8510 1.99164 -0.5657
## 49 HR 25.5000 16617.8744 89.53644 0.55302 -0.7565 3.00696 1.6712
## 50 HU 18.2802 18224.0904 115.04970 1.84622 -0.2417 4.07978 2.5449
## 51 ID 23.9000 4223.4646 35.44648 3.94398 1.1454 5.03546 2.5001
## 52 IE 25.4692 91715.2029 815.34610 0.32334 1.1977 10.07624 4.5268
## 53 IL NA 50813.0432 26.75248 0.14240 1.6423 3.36048 0.7084
## 54 IN 13.6000 2218.5362 20.80796 4.24752 1.0491 6.72450 2.6258
## 55 IQ NA 4270.7893 37.55918 0.44192 2.4876 3.80000 -1.3546
## 56 IS 24.8200 66458.8741 108.86200 0.41926 2.0438 4.63556 0.3121
## 57 IT 16.0000 34641.2557 129.37690 0.65218 -0.0396 0.98170 -0.8850
## 58 JM 14.3000 4938.6880 90.75014 3.60208 0.4806 1.18000 -1.4606
## 59 JO 17.9300 4433.1037 70.49410 1.37566 1.9443 2.02956 -0.6875
## 60 JP 17.3000 40838.2838 75.76394 0.51938 -0.1929 0.91240 -0.1394
## 61 KE 18.4444 2025.2907 52.90428 6.28796 2.8000 5.62820 1.9242
## 62 KR 14.8000 35337.0758 26.36510 1.09614 0.3751 2.77248 1.6542
## 63 KW NA 30276.8754 47.57912 1.88400 1.9857 0.13772 -3.7375
## 64 KZ 26.9700 10589.0517 56.21532 7.95000 1.3350 3.00000 0.9054
## 65 LK 16.5000 3822.1732 59.36342 4.21800 0.8755 3.67800 1.0805
## 66 LS 22.9520 1010.6177 61.18192 5.00340 0.7958 0.39388 -3.2384
## 67 LS 11.0000 2637.6890 85.47152 1.81194 1.5534 6.57820 3.6709
## 68 LT 21.8073 22636.1217 78.06336 1.69862 -0.8862 3.42028 3.7273
## 69 LU 23.9000 124340.3835 6908.35200 1.17428 2.0218 3.22626 0.0792
## 70 LV 24.9680 19638.1070 134.37960 1.70144 -0.7032 3.13634 2.3134
## 71 MA 15.2000 3301.6090 45.30954 1.18800 1.2641 3.09514 -0.4997
## 72 MK 16.6966 6571.8228 72.20372 0.62200 0.0389 2.77890 1.0689
## 73 MN NA 4393.3037 218.85680 4.98958 1.8006 4.25820 0.9093
## 74 MO 14.5000 52074.0604 194.62240 2.78282 1.2126 -1.66952 -9.8453
## 75 MT 23.9600 31441.2784 761.28590 1.32032 3.1949 6.53774 -0.1381
## 76 MV 47.5000 8656.5566 35.18078 0.88000 3.5095 6.30000 -3.6495
## 77 MX 17.7000 9729.2631 37.27282 4.02524 1.1350 2.01104 -1.4444
## 78 MY 18.3000 11363.6075 65.23842 1.91000 1.3474 4.87800 1.3926
## 79 MZ 26.0000 434.4606 356.19670 9.04260 2.9384 3.92880 -0.4276
## 80 <NA> 15.2000 5051.3480 60.48620 4.85712 1.8806 0.75446 -3.5756
## 81 NG 15.4000 2149.7791 24.81464 12.94034 2.6197 1.19458 -2.3145
## 82 NI 21.7500 1986.7204 83.97706 4.34306 1.0414 1.37996 -1.0152
## 83 NL 18.9026 57230.6715 512.18330 1.17730 0.5927 2.21984 0.4875
## 84 NO 23.1000 82858.2833 155.89490 2.61900 0.8375 1.46654 0.1530
## 85 NZ NA 48925.4692 103.06840 1.20152 2.0008 3.39204 0.0639
## 86 OM 19.1000 14957.4883 88.59674 0.76000 2.3197 1.99976 -2.3013
## 87 PA 16.2500 13872.7952 156.66240 0.42400 1.6872 4.58302 -1.8406
## 88 PE 15.5888 6528.2061 35.38870 2.69720 1.0511 3.17022 -0.7479
## 89 PH 14.9396 3658.9600 32.33956 2.49528 1.4217 6.56308 1.9917
## 90 PK 17.2000 1406.1297 29.25594 4.73824 1.8710 4.29018 1.5142
## 91 PL 20.1490 17732.6481 67.90290 0.80874 -0.0948 4.34840 3.1314
## 92 PT 16.7000 25282.8171 203.15930 0.83600 -0.3333 2.53122 0.9934
## 93 PY 19.1000 5054.1153 43.10920 3.52000 1.2931 2.96754 0.8830
## 94 QA 18.8000 55338.4835 108.79850 0.82252 2.3456 1.66590 -2.3610
## 95 RO 23.2000 14981.8900 52.57054 1.51808 -0.5878 4.71770 3.9390
## 96 RS 21.8000 8768.7320 86.54676 1.90000 -0.5088 3.17400 3.1268
## 97 RU 12.7000 10274.3779 33.40582 6.72076 0.1073 0.97740 0.6743
## 98 RW 23.3000 825.5581 52.98370 4.20636 2.6417 7.36908 2.2852
## 99 SA NA 21664.6362 48.19680 0.76200 2.5009 1.56022 -2.5833
## 100 SC 19.0200 13490.5158 109.22200 1.18702 1.0858 3.51306 -1.1137
## X8 X9 X10 X11 X12 X13 X14
## 1 55.00000 -26.52000 2.857862 8.0000 23.08410 26.94344 3.0000
## 2 102.52738 -13.59890 352.910575 8.1550 24.85976 32.47740 2.4500
## 3 102.52738 -56.24160 199.928422 8.1550 20.39940 31.03926 NA
## 4 102.52738 24.78532 10.108892 NA 21.69104 17.30888 NA
## 5 166.80851 47.27262 12.645460 6.6000 19.40300 15.11172 18.5000
## 6 34.81845 15.44938 62.485865 10.3000 31.12380 20.57210 10.5000
## 7 NA -5.01348 375.190755 10.6000 16.71368 13.81918 11.0500
## 8 116.41876 15.36980 429.980978 2.0190 24.78244 26.89982 6.0000
## 9 191.74943 57.95768 1359.132847 0.9600 24.28828 22.49670 5.4478
## 10 80.54508 28.09668 2.383969 5.0000 21.13634 24.49756 8.0000
## 11 110.63987 -174.36800 42.607177 NA 23.63816 29.44668 7.0000
## 12 78.40700 4.91586 347.147671 7.7000 32.70006 32.19390 5.0000
## 13 90.42874 -18.98450 514.176961 NA 24.55938 24.73148 6.0000
## 14 72.99709 -12.95970 69.103768 5.7984 20.46028 23.25440 5.3000
## 15 NA -51.11920 34.539229 NA 31.14198 28.74462 4.0000
## 16 81.54536 20.59038 15.355253 17.0000 23.40036 19.12786 2.3000
## 17 101.29834 -20.17800 37.238307 NA 20.84156 16.34698 8.5000
## 18 76.95112 10.01940 1444.733210 NA 15.49512 13.50872 13.9500
## 19 149.03716 42.60472 60.258857 4.8292 28.15432 18.39389 4.5000
## 20 106.86400 45.53354 1721.506090 0.5333 23.26748 20.61472 7.4503
## 21 84.09314 54.86688 9.707663 24.4000 46.82746 35.13040 NA
## 22 82.50000 -152.44500 749.017673 0.7500 24.41888 32.83370 3.1728
## 23 83.29876 7.37624 61.348608 8.8000 20.82476 19.42264 12.0000
## 24 116.51738 14.00910 252.940034 1.7229 22.48684 20.37026 10.0000
## 25 87.68676 26.04546 40.349134 20.0000 28.82414 25.75278 NA
## 26 94.22575 -26.98080 14866.703370 1.8396 43.17774 44.69396 4.9000
## 27 117.32727 9.92820 271.346897 3.1800 22.22970 18.09570 13.0000
## 28 125.26214 1.74676 61.520675 2.7000 17.93502 15.88014 15.0000
## 29 67.45486 51.37952 1.703701 9.5200 35.67148 32.54966 15.8000
## 30 68.15254 456.48640 23.804052 NA 17.90342 14.38300 7.8000
## 31 76.50765 -16.61460 243.530380 2.6562 27.97028 30.60572 3.4000
## 32 138.35724 -15.64810 3793.593164 NA 20.71144 28.03106 4.8177
## 33 359.13886 -5.59082 355.184032 1.8000 22.06322 29.24874 5.4000
## 34 80.10580 20.97700 79.001191 1.8500 23.77748 23.65308 5.7000
## 35 99.71869 8.90856 98.808010 NA 26.15664 26.23654 7.2000
## 36 104.68417 -13.26730 30.960228 0.3791 26.20832 28.47148 6.4000
## 37 53.29829 11.90716 361.845786 3.9000 15.78406 11.70278 7.0000
## 38 117.48908 83.40662 1278.325953 2.8512 19.68004 22.06638 16.1639
## 39 NA 27.57822 107.795527 11.1000 39.33340 31.44122 18.0000
## 40 175.16013 68.78926 270.625631 1.4000 23.67910 22.42012 7.8000
## 41 139.57196 36.80590 2609.943503 2.8415 23.40664 22.34918 9.3242
## 42 72.26748 29.34950 15.062255 11.2000 32.40134 32.38396 19.0000
## 43 91.33396 31.42504 2707.744043 1.2157 17.99490 14.01296 5.5665
## 44 145.18138 62.38444 15.891616 2.3000 27.43172 19.16908 20.0000
## 45 50.13182 47.67084 67.471195 15.0000 26.24074 23.15904 NA
## 46 89.84441 134.16510 188.985393 26.9780 12.66678 10.94992 18.3000
## 47 72.98978 2.81678 77.604632 1.8301 14.07878 15.21612 4.0000
## 48 68.82672 -283.26700 349.444713 0.9024 21.19750 24.59920 6.5000
## 49 82.18115 32.12062 56.170837 7.1776 21.94236 25.00206 7.5000
## 50 79.03623 11.68846 155.013041 0.9250 24.36458 27.06952 4.4000
## 51 96.57359 9.73972 1062.299663 3.0600 33.99662 32.80276 6.5000
## 52 84.42461 -345.29200 417.683180 3.5406 34.89774 43.30982 6.5000
## 53 85.93030 -47.40690 403.526464 1.4760 21.12638 24.84940 4.5000
## 54 73.69553 0.68776 2660.261329 9.5000 31.20112 30.23156 7.5000
## 55 NA 1.49128 165.493039 NA 19.14184 22.59400 13.5000
## 56 160.95762 28.71610 21.714538 2.9022 20.96484 26.28896 7.8000
## 57 111.19617 50.94154 1880.708359 NA 17.86622 20.23166 10.8839
## 58 88.86704 38.11946 13.812422 2.8000 22.55048 21.29292 8.5000
## 59 93.88143 10.63962 43.697563 5.4000 18.98000 11.38420 22.0000
## 60 70.95343 -44.36040 5043.573440 1.0734 25.31864 27.87758 2.7383
## 61 87.40996 39.30272 100.470001 14.1390 17.13230 11.00750 11.4537
## 62 123.99717 -26.86070 1631.134780 1.0000 30.95906 36.10606 4.0000
## 63 NA -271.87800 105.949023 NA 26.68898 32.14778 NA
## 64 83.52300 -38.63250 171.239891 7.9000 26.82074 26.28400 5.1000
## 65 89.13270 46.95208 80.676726 5.3000 29.69044 27.95642 5.0000
## 66 59.50145 12.39604 1.844513 4.1991 28.89906 16.64574 24.6500
## 67 NA 72.94226 19.129116 3.2000 33.45200 30.12460 NA
## 68 68.23179 16.85362 55.761983 0.9915 19.48272 20.31900 9.0000
## 69 42.65388 -1955.72000 73.055370 1.0280 18.38978 34.25134 6.8000
## 70 77.92536 22.27304 33.430044 3.5221 22.67616 23.11992 8.1000
## 71 102.28671 15.76728 112.869983 8.3515 32.29572 29.09784 11.5000
## 72 94.67722 23.32864 12.263700 3.2613 32.41148 31.85910 16.3000
## 73 77.34337 180.83030 13.269000 11.6788 32.50458 24.22642 7.3000
## 74 81.91411 -213.14400 24.333081 0.3357 19.61144 55.08932 2.4000
## 75 67.94252 -212.97000 14.474956 3.6629 22.98726 29.32880 4.3000
## 76 78.58290 -0.57864 3.767023 8.3000 20.09944 25.59820 6.5000
## 77 99.03247 8.52064 1073.915464 2.4292 22.74344 21.51140 4.0000
## 78 113.38897 -16.25250 336.664465 1.6600 24.38356 27.92792 4.0000
## 79 49.29687 282.81000 14.374968 11.8000 42.66772 15.14566 NA
## 80 91.29415 19.01378 10.710329 6.4000 20.90098 13.32220 23.0000
## 81 64.18761 -2.27422 401.028628 6.0000 18.31216 18.87146 22.0000
## 82 84.09234 50.63570 12.621466 4.1000 29.94454 26.86952 4.5000
## 83 161.74143 12.94086 910.005594 NA 21.16826 30.30356 4.6000
## 84 207.31980 -35.66660 362.571122 NA 28.22544 32.62790 4.2000
## 85 138.38958 51.69554 208.833638 NA 23.66948 21.26348 4.8000
## 86 148.12624 20.96404 64.648375 4.2000 26.17416 14.67168 NA
## 87 121.21618 39.83066 52.938074 2.1500 41.14624 36.51452 12.0000
## 88 116.71299 -20.74610 204.753978 4.1276 21.80948 20.42292 9.7000
## 89 74.25542 -12.25290 363.429119 1.6736 24.97170 24.32906 8.5000
## 90 61.34609 20.46164 262.232162 9.1000 16.10420 12.78448 6.5000
## 91 93.36164 27.71838 594.155788 3.7123 20.15800 20.38070 6.2000
## 92 113.24087 86.35888 230.736935 6.2000 17.22924 18.41932 7.1000
## 93 104.13747 9.42000 35.304238 4.9000 21.36214 23.25368 5.5000
## 94 163.71672 1.28492 146.400550 2.0000 42.35736 46.79924 0.1200
## 95 74.41554 18.74188 248.716040 4.0580 23.69546 20.98926 5.0000
## 96 90.19331 38.24144 52.960139 5.0000 20.81872 17.03374 9.7000
## 97 122.72076 -30.73920 1471.003881 NA 22.78718 27.47832 5.4000
## 98 111.94390 36.62538 10.332054 4.5000 22.69110 11.11020 NA
## 99 NA -62.91130 700.117867 NA 29.55294 29.68834 NA
## 100 45.41537 31.39798 1.170879 3.8700 34.72552 17.38966 4.5000
## Risk.Level
## 1 low
## 2 low
## 3 low
## 4 low
## 5 high
## 6 high
## 7 high
## 8 low
## 9 low
## 10 high
## 11 high
## 12 high
## 13 low
## 14 low
## 15 high
## 16 high
## 17 high
## 18 high
## 19 high
## 20 low
## 21 high
## 22 low
## 23 high
## 24 low
## 25 high
## 26 low
## 27 high
## 28 high
## 29 high
## 30 high
## 31 low
## 32 low
## 33 low
## 34 high
## 35 high
## 36 low
## 37 high
## 38 low
## 39 high
## 40 low
## 41 low
## 42 high
## 43 low
## 44 high
## 45 high
## 46 high
## 47 high
## 48 low
## 49 high
## 50 low
## 51 low
## 52 low
## 53 low
## 54 high
## 55 high
## 56 low
## 57 high
## 58 high
## 59 high
## 60 low
## 61 high
## 62 low
## 63 low
## 64 low
## 65 high
## 66 high
## 67 high
## 68 low
## 69 low
## 70 low
## 71 high
## 72 high
## 73 high
## 74 low
## 75 low
## 76 high
## 77 high
## 78 low
## 79 high
## 80 high
## 81 high
## 82 high
## 83 low
## 84 low
## 85 low
## 86 high
## 87 high
## 88 low
## 89 low
## 90 high
## 91 low
## 92 low
## 93 high
## 94 low
## 95 high
## 96 high
## 97 low
## 98 high
## 99 low
## 100 highMelihat Struktur Data
str(data3)## 'data.frame': 100 obs. of 16 variables:
## $ Country : Factor w/ 98 levels "AD","AE","AE-AZ",..: 1 2 3 4 5 6 7 8 9 10 ...
## $ X1 : num 17.5 18.2 18.7 NA 14 ...
## $ X2 : num 38675 40105 76038 27883 4251 ...
## $ X3 : num 172.8 103.5 31 24.8 89.6 ...
## $ X4 : num 0.68 1.77 2.63 1.29 1.44 ...
## $ X5 : num 1.221 0.87 1.489 1.753 0.256 ...
## $ X6 : num 1.79 2.66 1.85 2.23 4.75 ...
## $ X7 : num -2.084 -0.725 -1.901 -1.135 2.332 ...
## $ X8 : num 55 103 103 103 167 ...
## $ X9 : num -26.5 -13.6 -56.2 24.8 47.3 ...
## $ X10 : num 2.86 352.91 199.93 10.11 12.65 ...
## $ X11 : num 8 8.15 8.15 NA 6.6 ...
## $ X12 : num 23.1 24.9 20.4 21.7 19.4 ...
## $ X13 : num 26.9 32.5 31 17.3 15.1 ...
## $ X14 : num 3 2.45 NA NA 18.5 ...
## $ Risk.Level: Factor w/ 2 levels "high","low": 2 2 2 2 1 1 1 2 2 1 ...Menghapus Kolom Country
Penghapusan kolom country untuk memudahkan pengolahan data
data3 <- data3 %>% select(-Country)
head(data3)## X1 X2 X3 X4 X5 X6 X7 X8 X9
## 1 17.5 38674.616 172.75400 0.68000 1.2206 1.78560 -2.0843 55.00000 -26.52000
## 2 18.2 40105.120 103.52280 1.76600 0.8698 2.65884 -0.7254 102.52738 -13.59890
## 3 18.7 76037.997 31.03626 2.63056 1.4893 1.85034 -1.9008 102.52738 -56.24160
## 4 NA 27882.829 24.78532 1.29416 1.7530 2.23192 -1.1355 102.52738 24.78532
## 5 14.0 4251.398 89.61882 1.44000 0.2562 4.74800 2.3318 166.80851 47.27262
## 6 NA 2033.900 57.05566 22.35646 3.3422 -0.87800 -5.2032 34.81845 15.44938
## X10 X11 X12 X13 X14 Risk.Level
## 1 2.857862 8.000 23.08410 26.94344 3.00 low
## 2 352.910575 8.155 24.85976 32.47740 2.45 low
## 3 199.928422 8.155 20.39940 31.03926 NA low
## 4 10.108892 NA 21.69104 17.30888 NA low
## 5 12.645460 6.600 19.40300 15.11172 18.50 high
## 6 62.485865 10.300 31.12380 20.57210 10.50 highRingkasan Statistik
summary(data3)## X1 X2 X3 X4
## Min. : 4.20 Min. : 434.5 Min. : 13.63 Min. :-0.151
## 1st Qu.:15.93 1st Qu.: 4265.9 1st Qu.: 42.96 1st Qu.: 0.869
## Median :18.58 Median : 11659.1 Median : 70.42 Median : 1.700
## Mean :18.97 Mean : 22641.6 Mean : 191.94 Mean : 3.263
## 3rd Qu.:21.80 3rd Qu.: 34815.2 3rd Qu.: 130.63 3rd Qu.: 3.939
## Max. :47.50 Max. :124340.4 Max. :6908.35 Max. :36.703
## NA's :12
## X5 X6 X7 X8
## Min. :-0.8862 Min. :-5.135 Min. :-9.84530 Min. : 34.82
## 1st Qu.: 0.4419 1st Qu.: 1.765 1st Qu.:-1.18720 1st Qu.: 76.95
## Median : 1.1402 Median : 2.984 Median : 0.07155 Median : 90.19
## Mean : 1.2019 Mean : 3.076 Mean : 0.10804 Mean : 99.94
## 3rd Qu.: 1.9502 3rd Qu.: 4.305 3rd Qu.: 1.94108 3rd Qu.:113.39
## Max. : 4.4021 Max. :10.076 Max. : 6.07120 Max. :359.14
## NA's :7
## X9 X10 X11 X12
## Min. :-1955.72 Min. : 1.171 Min. : 0.3357 Min. :12.67
## 1st Qu.: -14.11 1st Qu.: 32.813 1st Qu.: 1.9250 1st Qu.:20.79
## Median : 12.67 Median : 106.872 Median : 3.9000 Median :23.40
## Mean : -13.58 Mean : 582.318 Mean : 5.5346 Mean :24.96
## 3rd Qu.: 36.67 3rd Qu.: 366.370 3rd Qu.: 7.9500 3rd Qu.:28.38
## Max. : 456.49 Max. :14866.703 Max. :26.9780 Max. :46.83
## NA's :17
## X13 X14 Risk.Level
## Min. :10.95 Min. : 0.120 high:54
## 1st Qu.:19.06 1st Qu.: 4.818 low :46
## Median :24.28 Median : 6.800
## Mean :24.48 Mean : 8.441
## 3rd Qu.:29.36 3rd Qu.:10.500
## Max. :55.09 Max. :24.650
## NA's :11Mengetahui jumlah data yang missing
Terdeteksi ada 47 data missing dari 1500 data yang ada
n_miss(data3)## [1] 47n_complete(data3)## [1] 1453Menampilkan PLot Data Missing
Dapat diketahui adanya missing data di X1,X8,X11,X14
dim(na.omit(data3))## [1] 67 15gg_miss_var(data3)
Memeriksa jumlah missing setiap variabel
sort(sapply(data3, function(x){sum(is.na(x))}), decreasing = TRUE)## X11 X1 X14 X8 X2 X3 X4
## 17 12 11 7 0 0 0
## X5 X6 X7 X9 X10 X12 X13
## 0 0 0 0 0 0 0
## Risk.Level
## 0Menangani Missing Value
data_cleann <- na.omit(data3)
for(i in 1:14) {
data3[is.na(data3[[i]]),i] <- mean(data3[[i]], na.rm = TRUE)
}
data3## X1 X2 X3 X4 X5 X6 X7 X8
## 1 17.50000 38674.6160 172.75400 0.68000 1.2206 1.78560 -2.0843 55.00000
## 2 18.20000 40105.1201 103.52280 1.76600 0.8698 2.65884 -0.7254 102.52738
## 3 18.70000 76037.9968 31.03626 2.63056 1.4893 1.85034 -1.9008 102.52738
## 4 18.97167 27882.8286 24.78532 1.29416 1.7530 2.23192 -1.1355 102.52738
## 5 14.00000 4251.3977 89.61882 1.44000 0.2562 4.74800 2.3318 166.80851
## 6 18.97167 2033.8999 57.05566 22.35646 3.3422 -0.87800 -5.2032 34.81845
## 7 23.25270 9203.4287 43.25546 36.70346 0.9657 -0.23680 -3.7297 99.94174
## 8 18.57400 53174.2385 159.39690 1.52348 0.7259 1.88048 -0.3001 116.41876
## 9 15.70000 63972.3400 121.98890 1.65124 1.4790 2.44592 0.0306 191.74943
## 10 33.50000 24642.7034 92.84624 1.21694 0.7972 2.06486 -4.7211 80.54508
## 11 25.30120 5083.2568 43.35272 6.85276 1.0510 0.39070 -1.7366 110.63987
## 12 4.20000 2323.5586 19.74352 5.81200 1.0568 7.39000 6.0712 78.40700
## 13 19.31880 49537.5785 256.72570 1.64000 0.5259 1.70044 -0.4905 90.42874
## 14 22.74060 11288.8489 70.29080 0.77854 -0.7095 3.61996 2.7008 72.99709
## 15 20.00000 22003.1172 214.20080 1.82200 4.4021 2.80902 -3.2531 99.94174
## 16 10.50000 1420.6492 49.56500 0.22520 2.7684 4.87736 2.2133 81.54536
## 17 12.28000 3372.3576 32.27932 2.92384 1.4362 3.95132 -0.0467 101.29834
## 18 19.14000 7372.9153 35.67380 5.72400 0.7789 -0.46082 -1.3423 76.95112
## 19 18.97167 6453.9238 69.54962 8.39000 0.0197 0.10000 0.6603 149.03716
## 20 16.09560 51704.8992 117.76010 1.67406 1.1918 1.79828 -0.5879 106.86400
## 21 22.30000 2378.0444 70.34826 2.03374 2.5889 -5.13500 -8.1338 84.09314
## 22 19.30000 89770.8521 275.61690 0.00116 0.8402 1.88522 0.1733 82.50000
## 23 18.97167 2594.7038 35.68100 0.75212 2.5779 7.29640 3.3099 83.29876
## 24 14.28000 15986.3031 65.82414 2.97824 1.2484 1.97106 -0.8925 116.51738
## 25 9.10000 1690.8639 39.74812 1.54052 2.6442 4.35350 0.7177 87.68676
## 26 14.70450 12226.6610 13.63044 2.00000 0.4575 6.64354 5.2661 94.22575
## 27 17.20000 5859.6535 47.58910 4.70940 1.3766 2.44972 -0.8876 117.32727
## 28 13.28400 11954.5890 44.98044 1.34600 0.9961 3.24766 0.7026 125.26214
## 29 19.42000 3466.2500 115.31060 0.37920 1.1636 3.92138 -0.4036 67.45486
## 30 16.00000 30630.2905 1026.49500 -0.15102 0.1535 4.62534 2.8078 68.15254
## 31 21.37960 27044.7929 79.21186 1.57500 0.2067 3.72134 1.3165 76.50765
## 32 18.58000 50891.5812 165.29300 1.20768 0.4835 1.62892 -0.1226 138.35724
## 33 22.60000 67565.6556 155.84030 0.54000 0.3613 2.68708 1.3106 359.13886
## 34 18.65000 8172.2496 42.49502 2.22228 0.9213 6.05690 2.4036 80.10580
## 35 13.40000 5830.4242 49.66284 1.23328 1.7062 0.50846 -2.7675 99.71869
## 36 25.31200 26427.0455 84.20358 2.03974 0.2136 3.94866 2.6995 104.68417
## 37 20.10000 3756.4221 31.92960 16.16054 2.0540 4.44796 2.2412 53.29829
## 38 16.98220 30488.0476 176.49180 0.71830 0.3949 2.84406 -0.4857 117.48908
## 39 18.97167 891.6737 33.04222 10.37682 2.6572 9.06000 5.5428 99.94174
## 40 20.10000 53937.2819 257.89490 0.67100 0.2165 1.82644 0.9465 175.16013
## 41 19.65010 44939.9046 247.44200 0.99026 0.2532 1.63728 -0.4225 139.57196
## 42 18.97167 7803.8309 39.13694 2.80396 2.7047 2.25300 -1.5934 72.26748
## 43 21.60000 46723.9041 406.04150 1.53050 0.6090 1.70254 -1.3484 91.33396
## 44 17.60000 4422.7082 104.45110 3.93800 -0.0317 4.12018 2.3147 145.18138
## 45 15.00000 2353.8541 59.62672 12.94200 2.2431 5.29400 2.6949 50.13182
## 46 16.66430 19404.1830 239.31940 0.26994 -0.2217 0.75896 -0.5866 89.84441
## 47 16.10000 4478.2807 34.07538 3.74200 1.9677 3.40778 0.3178 72.98978
## 48 20.70000 50214.6484 446.31540 2.43600 0.8510 1.99164 -0.5657 68.82672
## 49 25.50000 16617.8744 89.53644 0.55302 -0.7565 3.00696 1.6712 82.18115
## 50 18.28020 18224.0904 115.04970 1.84622 -0.2417 4.07978 2.5449 79.03623
## 51 23.90000 4223.4646 35.44648 3.94398 1.1454 5.03546 2.5001 96.57359
## 52 25.46920 91715.2029 815.34610 0.32334 1.1977 10.07624 4.5268 84.42461
## 53 18.97167 50813.0432 26.75248 0.14240 1.6423 3.36048 0.7084 85.93030
## 54 13.60000 2218.5362 20.80796 4.24752 1.0491 6.72450 2.6258 73.69553
## 55 18.97167 4270.7893 37.55918 0.44192 2.4876 3.80000 -1.3546 99.94174
## 56 24.82000 66458.8741 108.86200 0.41926 2.0438 4.63556 0.3121 160.95762
## 57 16.00000 34641.2557 129.37690 0.65218 -0.0396 0.98170 -0.8850 111.19617
## 58 14.30000 4938.6880 90.75014 3.60208 0.4806 1.18000 -1.4606 88.86704
## 59 17.93000 4433.1037 70.49410 1.37566 1.9443 2.02956 -0.6875 93.88143
## 60 17.30000 40838.2838 75.76394 0.51938 -0.1929 0.91240 -0.1394 70.95343
## 61 18.44440 2025.2907 52.90428 6.28796 2.8000 5.62820 1.9242 87.40996
## 62 14.80000 35337.0758 26.36510 1.09614 0.3751 2.77248 1.6542 123.99717
## 63 18.97167 30276.8754 47.57912 1.88400 1.9857 0.13772 -3.7375 99.94174
## 64 26.97000 10589.0517 56.21532 7.95000 1.3350 3.00000 0.9054 83.52300
## 65 16.50000 3822.1732 59.36342 4.21800 0.8755 3.67800 1.0805 89.13270
## 66 22.95200 1010.6177 61.18192 5.00340 0.7958 0.39388 -3.2384 59.50145
## 67 11.00000 2637.6890 85.47152 1.81194 1.5534 6.57820 3.6709 99.94174
## 68 21.80730 22636.1217 78.06336 1.69862 -0.8862 3.42028 3.7273 68.23179
## 69 23.90000 124340.3835 6908.35200 1.17428 2.0218 3.22626 0.0792 42.65388
## 70 24.96800 19638.1070 134.37960 1.70144 -0.7032 3.13634 2.3134 77.92536
## 71 15.20000 3301.6090 45.30954 1.18800 1.2641 3.09514 -0.4997 102.28671
## 72 16.69660 6571.8228 72.20372 0.62200 0.0389 2.77890 1.0689 94.67722
## 73 18.97167 4393.3037 218.85680 4.98958 1.8006 4.25820 0.9093 77.34337
## 74 14.50000 52074.0604 194.62240 2.78282 1.2126 -1.66952 -9.8453 81.91411
## 75 23.96000 31441.2784 761.28590 1.32032 3.1949 6.53774 -0.1381 67.94252
## 76 47.50000 8656.5566 35.18078 0.88000 3.5095 6.30000 -3.6495 78.58290
## 77 17.70000 9729.2631 37.27282 4.02524 1.1350 2.01104 -1.4444 99.03247
## 78 18.30000 11363.6075 65.23842 1.91000 1.3474 4.87800 1.3926 113.38897
## 79 26.00000 434.4606 356.19670 9.04260 2.9384 3.92880 -0.4276 49.29687
## 80 15.20000 5051.3480 60.48620 4.85712 1.8806 0.75446 -3.5756 91.29415
## 81 15.40000 2149.7791 24.81464 12.94034 2.6197 1.19458 -2.3145 64.18761
## 82 21.75000 1986.7204 83.97706 4.34306 1.0414 1.37996 -1.0152 84.09234
## 83 18.90260 57230.6715 512.18330 1.17730 0.5927 2.21984 0.4875 161.74143
## 84 23.10000 82858.2833 155.89490 2.61900 0.8375 1.46654 0.1530 207.31980
## 85 18.97167 48925.4692 103.06840 1.20152 2.0008 3.39204 0.0639 138.38958
## 86 19.10000 14957.4883 88.59674 0.76000 2.3197 1.99976 -2.3013 148.12624
## 87 16.25000 13872.7952 156.66240 0.42400 1.6872 4.58302 -1.8406 121.21618
## 88 15.58880 6528.2061 35.38870 2.69720 1.0511 3.17022 -0.7479 116.71299
## 89 14.93960 3658.9600 32.33956 2.49528 1.4217 6.56308 1.9917 74.25542
## 90 17.20000 1406.1297 29.25594 4.73824 1.8710 4.29018 1.5142 61.34609
## 91 20.14900 17732.6481 67.90290 0.80874 -0.0948 4.34840 3.1314 93.36164
## 92 16.70000 25282.8171 203.15930 0.83600 -0.3333 2.53122 0.9934 113.24087
## 93 19.10000 5054.1153 43.10920 3.52000 1.2931 2.96754 0.8830 104.13747
## 94 18.80000 55338.4835 108.79850 0.82252 2.3456 1.66590 -2.3610 163.71672
## 95 23.20000 14981.8900 52.57054 1.51808 -0.5878 4.71770 3.9390 74.41554
## 96 21.80000 8768.7320 86.54676 1.90000 -0.5088 3.17400 3.1268 90.19331
## 97 12.70000 10274.3779 33.40582 6.72076 0.1073 0.97740 0.6743 122.72076
## 98 23.30000 825.5581 52.98370 4.20636 2.6417 7.36908 2.2852 111.94390
## 99 18.97167 21664.6362 48.19680 0.76200 2.5009 1.56022 -2.5833 99.94174
## 100 19.02000 13490.5158 109.22200 1.18702 1.0858 3.51306 -1.1137 45.41537
## X9 X10 X11 X12 X13 X14 Risk.Level
## 1 -26.52000 2.857862 8.000000 23.08410 26.94344 3.000000 low
## 2 -13.59890 352.910575 8.155000 24.85976 32.47740 2.450000 low
## 3 -56.24160 199.928422 8.155000 20.39940 31.03926 8.440889 low
## 4 24.78532 10.108892 5.534602 21.69104 17.30888 8.440889 low
## 5 47.27262 12.645460 6.600000 19.40300 15.11172 18.500000 high
## 6 15.44938 62.485865 10.300000 31.12380 20.57210 10.500000 high
## 7 -5.01348 375.190755 10.600000 16.71368 13.81918 11.050000 high
## 8 15.36980 429.980978 2.019000 24.78244 26.89982 6.000000 low
## 9 57.95768 1359.132847 0.960000 24.28828 22.49670 5.447800 low
## 10 28.09668 2.383969 5.000000 21.13634 24.49756 8.000000 high
## 11 -174.36800 42.607177 5.534602 23.63816 29.44668 7.000000 high
## 12 4.91586 347.147671 7.700000 32.70006 32.19390 5.000000 high
## 13 -18.98450 514.176961 5.534602 24.55938 24.73148 6.000000 low
## 14 -12.95970 69.103768 5.798400 20.46028 23.25440 5.300000 low
## 15 -51.11920 34.539229 5.534602 31.14198 28.74462 4.000000 high
## 16 20.59038 15.355253 17.000000 23.40036 19.12786 2.300000 high
## 17 -20.17800 37.238307 5.534602 20.84156 16.34698 8.500000 high
## 18 10.01940 1444.733210 5.534602 15.49512 13.50872 13.950000 high
## 19 42.60472 60.258857 4.829200 28.15432 18.39389 4.500000 high
## 20 45.53354 1721.506090 0.533300 23.26748 20.61472 7.450300 low
## 21 54.86688 9.707663 24.400000 46.82746 35.13040 8.440889 high
## 22 -152.44500 749.017673 0.750000 24.41888 32.83370 3.172800 low
## 23 7.37624 61.348608 8.800000 20.82476 19.42264 12.000000 high
## 24 14.00910 252.940034 1.722900 22.48684 20.37026 10.000000 low
## 25 26.04546 40.349134 20.000000 28.82414 25.75278 8.440889 high
## 26 -26.98080 14866.703370 1.839600 43.17774 44.69396 4.900000 low
## 27 9.92820 271.346897 3.180000 22.22970 18.09570 13.000000 high
## 28 1.74676 61.520675 2.700000 17.93502 15.88014 15.000000 high
## 29 51.37952 1.703701 9.520000 35.67148 32.54966 15.800000 high
## 30 456.48640 23.804052 5.534602 17.90342 14.38300 7.800000 high
## 31 -16.61460 243.530380 2.656200 27.97028 30.60572 3.400000 low
## 32 -15.64810 3793.593164 5.534602 20.71144 28.03106 4.817700 low
## 33 -5.59082 355.184032 1.800000 22.06322 29.24874 5.400000 low
## 34 20.97700 79.001191 1.850000 23.77748 23.65308 5.700000 high
## 35 8.90856 98.808010 5.534602 26.15664 26.23654 7.200000 high
## 36 -13.26730 30.960228 0.379100 26.20832 28.47148 6.400000 low
## 37 11.90716 361.845786 3.900000 15.78406 11.70278 7.000000 high
## 38 83.40662 1278.325953 2.851200 19.68004 22.06638 16.163900 low
## 39 27.57822 107.795527 11.100000 39.33340 31.44122 18.000000 high
## 40 68.78926 270.625631 1.400000 23.67910 22.42012 7.800000 low
## 41 36.80590 2609.943503 2.841500 23.40664 22.34918 9.324200 low
## 42 29.34950 15.062255 11.200000 32.40134 32.38396 19.000000 high
## 43 31.42504 2707.744043 1.215700 17.99490 14.01296 5.566500 low
## 44 62.38444 15.891616 2.300000 27.43172 19.16908 20.000000 high
## 45 47.67084 67.471195 15.000000 26.24074 23.15904 8.440889 high
## 46 134.16510 188.985393 26.978000 12.66678 10.94992 18.300000 high
## 47 2.81678 77.604632 1.830100 14.07878 15.21612 4.000000 high
## 48 -283.26700 349.444713 0.902400 21.19750 24.59920 6.500000 low
## 49 32.12062 56.170837 7.177600 21.94236 25.00206 7.500000 high
## 50 11.68846 155.013041 0.925000 24.36458 27.06952 4.400000 low
## 51 9.73972 1062.299663 3.060000 33.99662 32.80276 6.500000 low
## 52 -345.29200 417.683180 3.540600 34.89774 43.30982 6.500000 low
## 53 -47.40690 403.526464 1.476000 21.12638 24.84940 4.500000 low
## 54 0.68776 2660.261329 9.500000 31.20112 30.23156 7.500000 high
## 55 1.49128 165.493039 5.534602 19.14184 22.59400 13.500000 high
## 56 28.71610 21.714538 2.902200 20.96484 26.28896 7.800000 low
## 57 50.94154 1880.708359 5.534602 17.86622 20.23166 10.883900 high
## 58 38.11946 13.812422 2.800000 22.55048 21.29292 8.500000 high
## 59 10.63962 43.697563 5.400000 18.98000 11.38420 22.000000 high
## 60 -44.36040 5043.573440 1.073400 25.31864 27.87758 2.738300 low
## 61 39.30272 100.470001 14.139000 17.13230 11.00750 11.453700 high
## 62 -26.86070 1631.134780 1.000000 30.95906 36.10606 4.000000 low
## 63 -271.87800 105.949023 5.534602 26.68898 32.14778 8.440889 low
## 64 -38.63250 171.239891 7.900000 26.82074 26.28400 5.100000 low
## 65 46.95208 80.676726 5.300000 29.69044 27.95642 5.000000 high
## 66 12.39604 1.844513 4.199100 28.89906 16.64574 24.650000 high
## 67 72.94226 19.129116 3.200000 33.45200 30.12460 8.440889 high
## 68 16.85362 55.761983 0.991500 19.48272 20.31900 9.000000 low
## 69 -1955.72000 73.055370 1.028000 18.38978 34.25134 6.800000 low
## 70 22.27304 33.430044 3.522100 22.67616 23.11992 8.100000 low
## 71 15.76728 112.869983 8.351500 32.29572 29.09784 11.500000 high
## 72 23.32864 12.263700 3.261300 32.41148 31.85910 16.300000 high
## 73 180.83030 13.269000 11.678800 32.50458 24.22642 7.300000 high
## 74 -213.14400 24.333081 0.335700 19.61144 55.08932 2.400000 low
## 75 -212.97000 14.474956 3.662900 22.98726 29.32880 4.300000 low
## 76 -0.57864 3.767023 8.300000 20.09944 25.59820 6.500000 high
## 77 8.52064 1073.915464 2.429200 22.74344 21.51140 4.000000 high
## 78 -16.25250 336.664465 1.660000 24.38356 27.92792 4.000000 low
## 79 282.81000 14.374968 11.800000 42.66772 15.14566 8.440889 high
## 80 19.01378 10.710329 6.400000 20.90098 13.32220 23.000000 high
## 81 -2.27422 401.028628 6.000000 18.31216 18.87146 22.000000 high
## 82 50.63570 12.621466 4.100000 29.94454 26.86952 4.500000 high
## 83 12.94086 910.005594 5.534602 21.16826 30.30356 4.600000 low
## 84 -35.66660 362.571122 5.534602 28.22544 32.62790 4.200000 low
## 85 51.69554 208.833638 5.534602 23.66948 21.26348 4.800000 low
## 86 20.96404 64.648375 4.200000 26.17416 14.67168 8.440889 high
## 87 39.83066 52.938074 2.150000 41.14624 36.51452 12.000000 high
## 88 -20.74610 204.753978 4.127600 21.80948 20.42292 9.700000 low
## 89 -12.25290 363.429119 1.673600 24.97170 24.32906 8.500000 low
## 90 20.46164 262.232162 9.100000 16.10420 12.78448 6.500000 high
## 91 27.71838 594.155788 3.712300 20.15800 20.38070 6.200000 low
## 92 86.35888 230.736935 6.200000 17.22924 18.41932 7.100000 low
## 93 9.42000 35.304238 4.900000 21.36214 23.25368 5.500000 high
## 94 1.28492 146.400550 2.000000 42.35736 46.79924 0.120000 low
## 95 18.74188 248.716040 4.058000 23.69546 20.98926 5.000000 high
## 96 38.24144 52.960139 5.000000 20.81872 17.03374 9.700000 high
## 97 -30.73920 1471.003881 5.534602 22.78718 27.47832 5.400000 low
## 98 36.62538 10.332054 4.500000 22.69110 11.11020 8.440889 high
## 99 -62.91130 700.117867 5.534602 29.55294 29.68834 8.440889 low
## 100 31.39798 1.170879 3.870000 34.72552 17.38966 4.500000 highSplit Data
Data dibagi menjadi dua data, yaitu data training dan data testing. Data training yang digunakan untuk membuat model dengan proporsi data 0,7 artinya 70% dari data akan digunakan untuk melatih model dan 30% untuk menguji model
set.seed(123)
index <- createDataPartition(data3$Risk.Level, p = 0.7, list = FALSE)
train_data1 <- data3[index, ]
test_data1 <- data3[-index, ]
head(train_data1)## X1 X2 X3 X4 X5 X6 X7 X8
## 1 17.5000 38674.616 172.75400 0.68000 1.2206 1.78560 -2.0843 55.00000
## 2 18.2000 40105.120 103.52280 1.76600 0.8698 2.65884 -0.7254 102.52738
## 7 23.2527 9203.429 43.25546 36.70346 0.9657 -0.23680 -3.7297 99.94174
## 8 18.5740 53174.238 159.39690 1.52348 0.7259 1.88048 -0.3001 116.41876
## 9 15.7000 63972.340 121.98890 1.65124 1.4790 2.44592 0.0306 191.74943
## 10 33.5000 24642.703 92.84624 1.21694 0.7972 2.06486 -4.7211 80.54508
## X9 X10 X11 X12 X13 X14 Risk.Level
## 1 -26.52000 2.857862 8.000 23.08410 26.94344 3.0000 low
## 2 -13.59890 352.910575 8.155 24.85976 32.47740 2.4500 low
## 7 -5.01348 375.190755 10.600 16.71368 13.81918 11.0500 high
## 8 15.36980 429.980978 2.019 24.78244 26.89982 6.0000 low
## 9 57.95768 1359.132847 0.960 24.28828 22.49670 5.4478 low
## 10 28.09668 2.383969 5.000 21.13634 24.49756 8.0000 highhead(test_data1)## X1 X2 X3 X4 X5 X6 X7 X8
## 3 18.70000 76037.997 31.03626 2.63056 1.4893 1.85034 -1.9008 102.52738
## 4 18.97167 27882.829 24.78532 1.29416 1.7530 2.23192 -1.1355 102.52738
## 5 14.00000 4251.398 89.61882 1.44000 0.2562 4.74800 2.3318 166.80851
## 6 18.97167 2033.900 57.05566 22.35646 3.3422 -0.87800 -5.2032 34.81845
## 12 4.20000 2323.559 19.74352 5.81200 1.0568 7.39000 6.0712 78.40700
## 22 19.30000 89770.852 275.61690 0.00116 0.8402 1.88522 0.1733 82.50000
## X9 X10 X11 X12 X13 X14 Risk.Level
## 3 -56.24160 199.92842 8.155000 20.39940 31.03926 8.440889 low
## 4 24.78532 10.10889 5.534602 21.69104 17.30888 8.440889 low
## 5 47.27262 12.64546 6.600000 19.40300 15.11172 18.500000 high
## 6 15.44938 62.48586 10.300000 31.12380 20.57210 10.500000 high
## 12 4.91586 347.14767 7.700000 32.70006 32.19390 5.000000 high
## 22 -152.44500 749.01767 0.750000 24.41888 32.83370 3.172800 lowModel
A-priori probabilities menunjukkan probabilitas awal sebelum mempertimbangkan prediktor. Prediktor itu adalah X1,X2,X3,….,X14
nb_model <- naiveBayes(Risk.Level ~ ., data = train_data1)
print(nb_model)##
## Naive Bayes Classifier for Discrete Predictors
##
## Call:
## naiveBayes.default(x = X, y = Y, laplace = laplace)
##
## A-priori probabilities:
## Y
## high low
## 0.5352113 0.4647887
##
## Conditional probabilities:
## X1
## Y [,1] [,2]
## high 18.77331 4.677976
## low 19.36531 3.585969
##
## X2
## Y [,1] [,2]
## high 7787.785 7648.396
## low 38703.461 25699.486
##
## X3
## Y [,1] [,2]
## high 79.79265 66.16116
## low 326.89118 1185.82721
##
## X4
## Y [,1] [,2]
## high 4.512117 6.513642
## low 1.886997 1.651655
##
## X5
## Y [,1] [,2]
## high 1.4678395 1.1552325
## low 0.8458121 0.8408339
##
## X6
## Y [,1] [,2]
## high 3.264319 2.659449
## low 2.600328 1.569226
##
## X7
## Y [,1] [,2]
## high 0.05282632 2.718461
## low 0.12402424 2.597326
##
## X8
## Y [,1] [,2]
## high 90.34624 22.77071
## low 114.16546 57.74593
##
## X9
## Y [,1] [,2]
## high 28.17189 60.85595
## low -84.19230 345.84389
##
## X10
## Y [,1] [,2]
## high 258.9664 565.9536
## low 1095.9332 2665.5127
##
## X11
## Y [,1] [,2]
## high 7.728421 6.056065
## low 3.106706 2.422555
##
## X12
## Y [,1] [,2]
## high 25.63437 8.288804
## low 24.84673 5.961012
##
## X13
## Y [,1] [,2]
## high 21.47126 7.469668
## low 28.23034 8.406431
##
## X14
## Y [,1] [,2]
## high 9.711153 5.054527
## low 5.698627 2.253403Prediksi
15 kasus high diprediksi dengan benar 8 kasus low diprediksi dengan benar 5 kasus ‘high’ salah prediksi sebagai ‘low’ 1 kasus ‘low’ yang salah prrediksi sebagai ‘high’
Dengan tingkat kepercayaan 95%, akurasi sebenarnya dari model tersebut berada diantara 60.28% dan 92.01%
Pada McNemar’s, p-value > 0.05 menunjukkan tidak ada perbedaan signifikan dalam proporsi kesalahan prediksi antar kelas
Model ini memiliki performa yang cukup baik dengan akurasi yaitu 79.31%.
Model ini cenderung lebih baik dalam memprediksi kasus ‘high’ dibandingkan ‘low’. Hal tersebut di dukung dengan nilai sensivity kelas high, sebesar 93,75%
testing_predik <- predict(nb_model, newdata = test_data1)
confusionMatrix(testing_predik, test_data1$Risk.Level)## Confusion Matrix and Statistics
##
## Reference
## Prediction high low
## high 15 5
## low 1 8
##
## Accuracy : 0.7931
## 95% CI : (0.6028, 0.9201)
## No Information Rate : 0.5517
## P-Value [Acc > NIR] : 0.00619
##
## Kappa : 0.5693
##
## Mcnemar's Test P-Value : 0.22067
##
## Sensitivity : 0.9375
## Specificity : 0.6154
## Pos Pred Value : 0.7500
## Neg Pred Value : 0.8889
## Prevalence : 0.5517
## Detection Rate : 0.5172
## Detection Prevalence : 0.6897
## Balanced Accuracy : 0.7764
##
## 'Positive' Class : high
## Memanggil Data Testing
testing_data<- read.csv("data_testing.csv", stringsAsFactors = TRUE)
testing_data## X1 X2 X3 X4 X5 X6 X7 X8
## 1 23.2000 60338.0204 175.42230 1.62000 0.6755 2.47168 0.3526 185.64097
## 2 16.8056 62432.9952 409.69700 0.10510 0.9068 2.77600 0.2912 94.00211
## 3 18.2857 28684.1682 103.06040 0.84352 0.0746 3.55290 1.9299 72.30708
## 4 19.6715 21042.7221 102.73060 1.17400 0.0734 3.21976 1.2325 111.78982
## 5 11.9000 49356.2618 60.15464 0.89594 0.5865 1.75420 -1.1342 88.60514
## 6 NA 3989.1913 65.55750 0.39400 0.5042 2.44734 -0.1248 88.88685
## 7 19.8000 7450.5523 33.22256 0.34500 0.3153 3.44058 1.2787 100.19298
## 8 12.9000 3616.8650 85.26668 5.55600 1.1173 1.60820 -1.5047 134.47988
## 9 18.0000 8652.9973 51.65878 11.65444 1.4844 4.15702 1.8070 116.52826
## 10 14.1400 31854.2815 48.51016 0.72360 0.1015 2.53870 2.7686 71.08310
## 11 22.0000 3955.0704 103.90710 19.17300 -0.3906 0.34000 1.8906 72.25639
## 12 21.5689 786.8776 42.26784 4.29470 3.6551 5.73874 0.4207 69.45587
## 13 16.3000 69324.7338 104.17110 1.55316 0.6255 2.45554 0.4867 NA
## 14 17.0400 15968.2306 73.01010 8.00348 0.3592 0.82090 -0.7169 49.05568
## 15 18.4000 1872.6699 30.04996 12.29840 1.6065 5.84000 3.0735 NA
## 16 12.0977 3886.5162 34.52492 2.79600 0.8506 6.94570 5.2762 86.56201
## 17 16.6000 6404.6725 50.79576 4.98278 1.4772 0.78940 -2.3230 107.24859
## X9 X10 X11 X12 X13 X14
## 1 64.14972 537.609866 0.5000 25.11320 27.95256 8.6000
## 2 -200.98100 339.988210 1.3095 26.76784 47.25374 3.0000
## 3 16.23838 52.761781 3.0176 19.90742 25.76882 5.0000
## 4 33.35258 102.567122 2.5300 22.83084 20.95780 7.0000
## 5 -145.43800 1.490827 63.5000 17.79208 23.21144 7.3000
## 6 27.33332 24.638720 1.5706 16.78238 14.52982 9.0000
## 7 -42.56340 501.644054 3.2000 23.05990 32.47950 2.0000
## 8 64.46288 39.218118 13.6000 18.80654 8.88180 17.0000
## 9 28.56998 720.244499 NA 28.55834 26.32778 13.2000
## 10 -189.14000 668.122597 NA 22.02936 33.80118 3.7000
## 11 -5.46582 155.581868 49.0000 17.79388 16.04966 9.5000
## 12 21.88058 33.538172 3.3357 24.85996 19.47826 NA
## 13 47.70210 20935.000000 1.0000 17.40650 17.20802 5.6146
## 14 -16.23150 53.628838 NA 16.44666 17.57796 10.3000
## 15 -45.16010 57.707193 2.1000 31.60162 29.24286 6.0000
## 16 7.39622 351.683014 1.6900 23.54764 25.80812 2.5000
## 17 15.04496 302.141270 NA 19.11740 16.25316 33.7000Mengatasi Missing Value
data_clean <- na.omit(testing_data)
for(i in 1:14) {
testing_data[is.na(testing_data[[i]]),i] <- mean(testing_data[[i]], na.rm = TRUE)
}
testing_data## X1 X2 X3 X4 X5 X6 X7 X8
## 1 23.20000 60338.0204 175.42230 1.62000 0.6755 2.47168 0.3526 185.64097
## 2 16.80560 62432.9952 409.69700 0.10510 0.9068 2.77600 0.2912 94.00211
## 3 18.28570 28684.1682 103.06040 0.84352 0.0746 3.55290 1.9299 72.30708
## 4 19.67150 21042.7221 102.73060 1.17400 0.0734 3.21976 1.2325 111.78982
## 5 11.90000 49356.2618 60.15464 0.89594 0.5865 1.75420 -1.1342 88.60514
## 6 17.41934 3989.1913 65.55750 0.39400 0.5042 2.44734 -0.1248 88.88685
## 7 19.80000 7450.5523 33.22256 0.34500 0.3153 3.44058 1.2787 100.19298
## 8 12.90000 3616.8650 85.26668 5.55600 1.1173 1.60820 -1.5047 134.47988
## 9 18.00000 8652.9973 51.65878 11.65444 1.4844 4.15702 1.8070 116.52826
## 10 14.14000 31854.2815 48.51016 0.72360 0.1015 2.53870 2.7686 71.08310
## 11 22.00000 3955.0704 103.90710 19.17300 -0.3906 0.34000 1.8906 72.25639
## 12 21.56890 786.8776 42.26784 4.29470 3.6551 5.73874 0.4207 69.45587
## 13 16.30000 69324.7338 104.17110 1.55316 0.6255 2.45554 0.4867 96.53965
## 14 17.04000 15968.2306 73.01010 8.00348 0.3592 0.82090 -0.7169 49.05568
## 15 18.40000 1872.6699 30.04996 12.29840 1.6065 5.84000 3.0735 96.53965
## 16 12.09770 3886.5162 34.52492 2.79600 0.8506 6.94570 5.2762 86.56201
## 17 16.60000 6404.6725 50.79576 4.98278 1.4772 0.78940 -2.3230 107.24859
## X9 X10 X11 X12 X13 X14
## 1 64.14972 537.609866 0.50000 25.11320 27.95256 8.600000
## 2 -200.98100 339.988210 1.30950 26.76784 47.25374 3.000000
## 3 16.23838 52.761781 3.01760 19.90742 25.76882 5.000000
## 4 33.35258 102.567122 2.53000 22.83084 20.95780 7.000000
## 5 -145.43800 1.490827 63.50000 17.79208 23.21144 7.300000
## 6 27.33332 24.638720 1.57060 16.78238 14.52982 9.000000
## 7 -42.56340 501.644054 3.20000 23.05990 32.47950 2.000000
## 8 64.46288 39.218118 13.60000 18.80654 8.88180 17.000000
## 9 28.56998 720.244499 11.25795 28.55834 26.32778 13.200000
## 10 -189.14000 668.122597 11.25795 22.02936 33.80118 3.700000
## 11 -5.46582 155.581868 49.00000 17.79388 16.04966 9.500000
## 12 21.88058 33.538172 3.33570 24.85996 19.47826 8.963413
## 13 47.70210 20935.000000 1.00000 17.40650 17.20802 5.614600
## 14 -16.23150 53.628838 11.25795 16.44666 17.57796 10.300000
## 15 -45.16010 57.707193 2.10000 31.60162 29.24286 6.000000
## 16 7.39622 351.683014 1.69000 23.54764 25.80812 2.500000
## 17 15.04496 302.141270 11.25795 19.11740 16.25316 33.700000Memprediksi Data Testing
Prediksi dilakukan dengan menggunakan model Naive Bayes
new_prediction <- predict(nb_model, newdata = testing_data)
print(new_prediction)## [1] low low low high high high high high high low high high low high high
## [16] high high
## Levels: high lowBerikut ini disertakan data dan prediksinya agar mudah dimengerti
hasil_prediksi <- cbind(testing_data, prediksi = new_prediction)
print(hasil_prediksi)## X1 X2 X3 X4 X5 X6 X7 X8
## 1 23.20000 60338.0204 175.42230 1.62000 0.6755 2.47168 0.3526 185.64097
## 2 16.80560 62432.9952 409.69700 0.10510 0.9068 2.77600 0.2912 94.00211
## 3 18.28570 28684.1682 103.06040 0.84352 0.0746 3.55290 1.9299 72.30708
## 4 19.67150 21042.7221 102.73060 1.17400 0.0734 3.21976 1.2325 111.78982
## 5 11.90000 49356.2618 60.15464 0.89594 0.5865 1.75420 -1.1342 88.60514
## 6 17.41934 3989.1913 65.55750 0.39400 0.5042 2.44734 -0.1248 88.88685
## 7 19.80000 7450.5523 33.22256 0.34500 0.3153 3.44058 1.2787 100.19298
## 8 12.90000 3616.8650 85.26668 5.55600 1.1173 1.60820 -1.5047 134.47988
## 9 18.00000 8652.9973 51.65878 11.65444 1.4844 4.15702 1.8070 116.52826
## 10 14.14000 31854.2815 48.51016 0.72360 0.1015 2.53870 2.7686 71.08310
## 11 22.00000 3955.0704 103.90710 19.17300 -0.3906 0.34000 1.8906 72.25639
## 12 21.56890 786.8776 42.26784 4.29470 3.6551 5.73874 0.4207 69.45587
## 13 16.30000 69324.7338 104.17110 1.55316 0.6255 2.45554 0.4867 96.53965
## 14 17.04000 15968.2306 73.01010 8.00348 0.3592 0.82090 -0.7169 49.05568
## 15 18.40000 1872.6699 30.04996 12.29840 1.6065 5.84000 3.0735 96.53965
## 16 12.09770 3886.5162 34.52492 2.79600 0.8506 6.94570 5.2762 86.56201
## 17 16.60000 6404.6725 50.79576 4.98278 1.4772 0.78940 -2.3230 107.24859
## X9 X10 X11 X12 X13 X14 prediksi
## 1 64.14972 537.609866 0.50000 25.11320 27.95256 8.600000 low
## 2 -200.98100 339.988210 1.30950 26.76784 47.25374 3.000000 low
## 3 16.23838 52.761781 3.01760 19.90742 25.76882 5.000000 low
## 4 33.35258 102.567122 2.53000 22.83084 20.95780 7.000000 high
## 5 -145.43800 1.490827 63.50000 17.79208 23.21144 7.300000 high
## 6 27.33332 24.638720 1.57060 16.78238 14.52982 9.000000 high
## 7 -42.56340 501.644054 3.20000 23.05990 32.47950 2.000000 high
## 8 64.46288 39.218118 13.60000 18.80654 8.88180 17.000000 high
## 9 28.56998 720.244499 11.25795 28.55834 26.32778 13.200000 high
## 10 -189.14000 668.122597 11.25795 22.02936 33.80118 3.700000 low
## 11 -5.46582 155.581868 49.00000 17.79388 16.04966 9.500000 high
## 12 21.88058 33.538172 3.33570 24.85996 19.47826 8.963413 high
## 13 47.70210 20935.000000 1.00000 17.40650 17.20802 5.614600 low
## 14 -16.23150 53.628838 11.25795 16.44666 17.57796 10.300000 high
## 15 -45.16010 57.707193 2.10000 31.60162 29.24286 6.000000 high
## 16 7.39622 351.683014 1.69000 23.54764 25.80812 2.500000 high
## 17 15.04496 302.141270 11.25795 19.11740 16.25316 33.700000 high