# 2. caret package 이해하기
# caret Classfication and Regression Training 약자
# 주 관심 대상이 되는 종속변수(예측변수)가 명목형 변수라면
# "Classification", 연속형 변수라면 "Regression" 데이터를 "Training"
# caret 패키지 사용하면 자동으로 파라미터를 조정
# 242개의 머신러닝 알고리즘을 표준화된 인터페이스를 통해 테스트 해 볼 수
# 있도록 준비가 되어 있고,
library(caret)
## Warning: 패키지 'caret'는 R 버전 4.1.3에서 작성되었습니다
## 필요한 패키지를 로딩중입니다: ggplot2
## Warning: 패키지 'ggplot2'는 R 버전 4.1.3에서 작성되었습니다
## 필요한 패키지를 로딩중입니다: lattice
library(dplyr)
## Warning: 패키지 'dplyr'는 R 버전 4.1.3에서 작성되었습니다
##
## 다음의 패키지를 부착합니다: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
set.seed(1234)
library(mlbench)
## Warning: 패키지 'mlbench'는 R 버전 4.1.3에서 작성되었습니다
data("Sonar")
Sonar %>% glimpse
## Rows: 208
## Columns: 61
## $ V1 <dbl> 0.0200, 0.0453, 0.0262, 0.0100, 0.0762, 0.0286, 0.0317, 0.0519, ~
## $ V2 <dbl> 0.0371, 0.0523, 0.0582, 0.0171, 0.0666, 0.0453, 0.0956, 0.0548, ~
## $ V3 <dbl> 0.0428, 0.0843, 0.1099, 0.0623, 0.0481, 0.0277, 0.1321, 0.0842, ~
## $ V4 <dbl> 0.0207, 0.0689, 0.1083, 0.0205, 0.0394, 0.0174, 0.1408, 0.0319, ~
## $ V5 <dbl> 0.0954, 0.1183, 0.0974, 0.0205, 0.0590, 0.0384, 0.1674, 0.1158, ~
## $ V6 <dbl> 0.0986, 0.2583, 0.2280, 0.0368, 0.0649, 0.0990, 0.1710, 0.0922, ~
## $ V7 <dbl> 0.1539, 0.2156, 0.2431, 0.1098, 0.1209, 0.1201, 0.0731, 0.1027, ~
## $ V8 <dbl> 0.1601, 0.3481, 0.3771, 0.1276, 0.2467, 0.1833, 0.1401, 0.0613, ~
## $ V9 <dbl> 0.3109, 0.3337, 0.5598, 0.0598, 0.3564, 0.2105, 0.2083, 0.1465, ~
## $ V10 <dbl> 0.2111, 0.2872, 0.6194, 0.1264, 0.4459, 0.3039, 0.3513, 0.2838, ~
## $ V11 <dbl> 0.1609, 0.4918, 0.6333, 0.0881, 0.4152, 0.2988, 0.1786, 0.2802, ~
## $ V12 <dbl> 0.1582, 0.6552, 0.7060, 0.1992, 0.3952, 0.4250, 0.0658, 0.3086, ~
## $ V13 <dbl> 0.2238, 0.6919, 0.5544, 0.0184, 0.4256, 0.6343, 0.0513, 0.2657, ~
## $ V14 <dbl> 0.0645, 0.7797, 0.5320, 0.2261, 0.4135, 0.8198, 0.3752, 0.3801, ~
## $ V15 <dbl> 0.0660, 0.7464, 0.6479, 0.1729, 0.4528, 1.0000, 0.5419, 0.5626, ~
## $ V16 <dbl> 0.2273, 0.9444, 0.6931, 0.2131, 0.5326, 0.9988, 0.5440, 0.4376, ~
## $ V17 <dbl> 0.3100, 1.0000, 0.6759, 0.0693, 0.7306, 0.9508, 0.5150, 0.2617, ~
## $ V18 <dbl> 0.2999, 0.8874, 0.7551, 0.2281, 0.6193, 0.9025, 0.4262, 0.1199, ~
## $ V19 <dbl> 0.5078, 0.8024, 0.8929, 0.4060, 0.2032, 0.7234, 0.2024, 0.6676, ~
## $ V20 <dbl> 0.4797, 0.7818, 0.8619, 0.3973, 0.4636, 0.5122, 0.4233, 0.9402, ~
## $ V21 <dbl> 0.5783, 0.5212, 0.7974, 0.2741, 0.4148, 0.2074, 0.7723, 0.7832, ~
## $ V22 <dbl> 0.5071, 0.4052, 0.6737, 0.3690, 0.4292, 0.3985, 0.9735, 0.5352, ~
## $ V23 <dbl> 0.4328, 0.3957, 0.4293, 0.5556, 0.5730, 0.5890, 0.9390, 0.6809, ~
## $ V24 <dbl> 0.5550, 0.3914, 0.3648, 0.4846, 0.5399, 0.2872, 0.5559, 0.9174, ~
## $ V25 <dbl> 0.6711, 0.3250, 0.5331, 0.3140, 0.3161, 0.2043, 0.5268, 0.7613, ~
## $ V26 <dbl> 0.6415, 0.3200, 0.2413, 0.5334, 0.2285, 0.5782, 0.6826, 0.8220, ~
## $ V27 <dbl> 0.7104, 0.3271, 0.5070, 0.5256, 0.6995, 0.5389, 0.5713, 0.8872, ~
## $ V28 <dbl> 0.8080, 0.2767, 0.8533, 0.2520, 1.0000, 0.3750, 0.5429, 0.6091, ~
## $ V29 <dbl> 0.6791, 0.4423, 0.6036, 0.2090, 0.7262, 0.3411, 0.2177, 0.2967, ~
## $ V30 <dbl> 0.3857, 0.2028, 0.8514, 0.3559, 0.4724, 0.5067, 0.2149, 0.1103, ~
## $ V31 <dbl> 0.1307, 0.3788, 0.8512, 0.6260, 0.5103, 0.5580, 0.5811, 0.1318, ~
## $ V32 <dbl> 0.2604, 0.2947, 0.5045, 0.7340, 0.5459, 0.4778, 0.6323, 0.0624, ~
## $ V33 <dbl> 0.5121, 0.1984, 0.1862, 0.6120, 0.2881, 0.3299, 0.2965, 0.0990, ~
## $ V34 <dbl> 0.7547, 0.2341, 0.2709, 0.3497, 0.0981, 0.2198, 0.1873, 0.4006, ~
## $ V35 <dbl> 0.8537, 0.1306, 0.4232, 0.3953, 0.1951, 0.1407, 0.2969, 0.3666, ~
## $ V36 <dbl> 0.8507, 0.4182, 0.3043, 0.3012, 0.4181, 0.2856, 0.5163, 0.1050, ~
## $ V37 <dbl> 0.6692, 0.3835, 0.6116, 0.5408, 0.4604, 0.3807, 0.6153, 0.1915, ~
## $ V38 <dbl> 0.6097, 0.1057, 0.6756, 0.8814, 0.3217, 0.4158, 0.4283, 0.3930, ~
## $ V39 <dbl> 0.4943, 0.1840, 0.5375, 0.9857, 0.2828, 0.4054, 0.5479, 0.4288, ~
## $ V40 <dbl> 0.2744, 0.1970, 0.4719, 0.9167, 0.2430, 0.3296, 0.6133, 0.2546, ~
## $ V41 <dbl> 0.0510, 0.1674, 0.4647, 0.6121, 0.1979, 0.2707, 0.5017, 0.1151, ~
## $ V42 <dbl> 0.2834, 0.0583, 0.2587, 0.5006, 0.2444, 0.2650, 0.2377, 0.2196, ~
## $ V43 <dbl> 0.2825, 0.1401, 0.2129, 0.3210, 0.1847, 0.0723, 0.1957, 0.1879, ~
## $ V44 <dbl> 0.4256, 0.1628, 0.2222, 0.3202, 0.0841, 0.1238, 0.1749, 0.1437, ~
## $ V45 <dbl> 0.2641, 0.0621, 0.2111, 0.4295, 0.0692, 0.1192, 0.1304, 0.2146, ~
## $ V46 <dbl> 0.1386, 0.0203, 0.0176, 0.3654, 0.0528, 0.1089, 0.0597, 0.2360, ~
## $ V47 <dbl> 0.1051, 0.0530, 0.1348, 0.2655, 0.0357, 0.0623, 0.1124, 0.1125, ~
## $ V48 <dbl> 0.1343, 0.0742, 0.0744, 0.1576, 0.0085, 0.0494, 0.1047, 0.0254, ~
## $ V49 <dbl> 0.0383, 0.0409, 0.0130, 0.0681, 0.0230, 0.0264, 0.0507, 0.0285, ~
## $ V50 <dbl> 0.0324, 0.0061, 0.0106, 0.0294, 0.0046, 0.0081, 0.0159, 0.0178, ~
## $ V51 <dbl> 0.0232, 0.0125, 0.0033, 0.0241, 0.0156, 0.0104, 0.0195, 0.0052, ~
## $ V52 <dbl> 0.0027, 0.0084, 0.0232, 0.0121, 0.0031, 0.0045, 0.0201, 0.0081, ~
## $ V53 <dbl> 0.0065, 0.0089, 0.0166, 0.0036, 0.0054, 0.0014, 0.0248, 0.0120, ~
## $ V54 <dbl> 0.0159, 0.0048, 0.0095, 0.0150, 0.0105, 0.0038, 0.0131, 0.0045, ~
## $ V55 <dbl> 0.0072, 0.0094, 0.0180, 0.0085, 0.0110, 0.0013, 0.0070, 0.0121, ~
## $ V56 <dbl> 0.0167, 0.0191, 0.0244, 0.0073, 0.0015, 0.0089, 0.0138, 0.0097, ~
## $ V57 <dbl> 0.0180, 0.0140, 0.0316, 0.0050, 0.0072, 0.0057, 0.0092, 0.0085, ~
## $ V58 <dbl> 0.0084, 0.0049, 0.0164, 0.0044, 0.0048, 0.0027, 0.0143, 0.0047, ~
## $ V59 <dbl> 0.0090, 0.0052, 0.0095, 0.0040, 0.0107, 0.0051, 0.0036, 0.0048, ~
## $ V60 <dbl> 0.0032, 0.0044, 0.0078, 0.0117, 0.0094, 0.0062, 0.0103, 0.0053, ~
## $ Class <fct> R, R, R, R, R, R, R, R, R, R, R, R, R, R, R, R, R, R, R, R, R, R~
str(Sonar)
## 'data.frame': 208 obs. of 61 variables:
## $ V1 : num 0.02 0.0453 0.0262 0.01 0.0762 0.0286 0.0317 0.0519 0.0223 0.0164 ...
## $ V2 : num 0.0371 0.0523 0.0582 0.0171 0.0666 0.0453 0.0956 0.0548 0.0375 0.0173 ...
## $ V3 : num 0.0428 0.0843 0.1099 0.0623 0.0481 ...
## $ V4 : num 0.0207 0.0689 0.1083 0.0205 0.0394 ...
## $ V5 : num 0.0954 0.1183 0.0974 0.0205 0.059 ...
## $ V6 : num 0.0986 0.2583 0.228 0.0368 0.0649 ...
## $ V7 : num 0.154 0.216 0.243 0.11 0.121 ...
## $ V8 : num 0.16 0.348 0.377 0.128 0.247 ...
## $ V9 : num 0.3109 0.3337 0.5598 0.0598 0.3564 ...
## $ V10 : num 0.211 0.287 0.619 0.126 0.446 ...
## $ V11 : num 0.1609 0.4918 0.6333 0.0881 0.4152 ...
## $ V12 : num 0.158 0.655 0.706 0.199 0.395 ...
## $ V13 : num 0.2238 0.6919 0.5544 0.0184 0.4256 ...
## $ V14 : num 0.0645 0.7797 0.532 0.2261 0.4135 ...
## $ V15 : num 0.066 0.746 0.648 0.173 0.453 ...
## $ V16 : num 0.227 0.944 0.693 0.213 0.533 ...
## $ V17 : num 0.31 1 0.6759 0.0693 0.7306 ...
## $ V18 : num 0.3 0.887 0.755 0.228 0.619 ...
## $ V19 : num 0.508 0.802 0.893 0.406 0.203 ...
## $ V20 : num 0.48 0.782 0.862 0.397 0.464 ...
## $ V21 : num 0.578 0.521 0.797 0.274 0.415 ...
## $ V22 : num 0.507 0.405 0.674 0.369 0.429 ...
## $ V23 : num 0.433 0.396 0.429 0.556 0.573 ...
## $ V24 : num 0.555 0.391 0.365 0.485 0.54 ...
## $ V25 : num 0.671 0.325 0.533 0.314 0.316 ...
## $ V26 : num 0.641 0.32 0.241 0.533 0.229 ...
## $ V27 : num 0.71 0.327 0.507 0.526 0.7 ...
## $ V28 : num 0.808 0.277 0.853 0.252 1 ...
## $ V29 : num 0.679 0.442 0.604 0.209 0.726 ...
## $ V30 : num 0.386 0.203 0.851 0.356 0.472 ...
## $ V31 : num 0.131 0.379 0.851 0.626 0.51 ...
## $ V32 : num 0.26 0.295 0.504 0.734 0.546 ...
## $ V33 : num 0.512 0.198 0.186 0.612 0.288 ...
## $ V34 : num 0.7547 0.2341 0.2709 0.3497 0.0981 ...
## $ V35 : num 0.854 0.131 0.423 0.395 0.195 ...
## $ V36 : num 0.851 0.418 0.304 0.301 0.418 ...
## $ V37 : num 0.669 0.384 0.612 0.541 0.46 ...
## $ V38 : num 0.61 0.106 0.676 0.881 0.322 ...
## $ V39 : num 0.494 0.184 0.537 0.986 0.283 ...
## $ V40 : num 0.274 0.197 0.472 0.917 0.243 ...
## $ V41 : num 0.051 0.167 0.465 0.612 0.198 ...
## $ V42 : num 0.2834 0.0583 0.2587 0.5006 0.2444 ...
## $ V43 : num 0.282 0.14 0.213 0.321 0.185 ...
## $ V44 : num 0.4256 0.1628 0.2222 0.3202 0.0841 ...
## $ V45 : num 0.2641 0.0621 0.2111 0.4295 0.0692 ...
## $ V46 : num 0.1386 0.0203 0.0176 0.3654 0.0528 ...
## $ V47 : num 0.1051 0.053 0.1348 0.2655 0.0357 ...
## $ V48 : num 0.1343 0.0742 0.0744 0.1576 0.0085 ...
## $ V49 : num 0.0383 0.0409 0.013 0.0681 0.023 0.0264 0.0507 0.0285 0.0777 0.0092 ...
## $ V50 : num 0.0324 0.0061 0.0106 0.0294 0.0046 0.0081 0.0159 0.0178 0.0439 0.0198 ...
## $ V51 : num 0.0232 0.0125 0.0033 0.0241 0.0156 0.0104 0.0195 0.0052 0.0061 0.0118 ...
## $ V52 : num 0.0027 0.0084 0.0232 0.0121 0.0031 0.0045 0.0201 0.0081 0.0145 0.009 ...
## $ V53 : num 0.0065 0.0089 0.0166 0.0036 0.0054 0.0014 0.0248 0.012 0.0128 0.0223 ...
## $ V54 : num 0.0159 0.0048 0.0095 0.015 0.0105 0.0038 0.0131 0.0045 0.0145 0.0179 ...
## $ V55 : num 0.0072 0.0094 0.018 0.0085 0.011 0.0013 0.007 0.0121 0.0058 0.0084 ...
## $ V56 : num 0.0167 0.0191 0.0244 0.0073 0.0015 0.0089 0.0138 0.0097 0.0049 0.0068 ...
## $ V57 : num 0.018 0.014 0.0316 0.005 0.0072 0.0057 0.0092 0.0085 0.0065 0.0032 ...
## $ V58 : num 0.0084 0.0049 0.0164 0.0044 0.0048 0.0027 0.0143 0.0047 0.0093 0.0035 ...
## $ V59 : num 0.009 0.0052 0.0095 0.004 0.0107 0.0051 0.0036 0.0048 0.0059 0.0056 ...
## $ V60 : num 0.0032 0.0044 0.0078 0.0117 0.0094 0.0062 0.0103 0.0053 0.0022 0.004 ...
## $ Class: Factor w/ 2 levels "M","R": 2 2 2 2 2 2 2 2 2 2 ...
# Class 라는 명칭의 명목형으로 M, R 2개의 factor
# 1) createDataPartition()
# 이 함수에는 p 인자가 있어 특정비율로 파티셔닝할 때 편하다.
# 단 반환되는 타입이 기본적으로 list 이므로 list 인자값을 FALSE
idx<-createDataPartition(Sonar$Class,p=.7,list=F)
train<-Sonar[idx,]
test<-Sonar[-idx,]
#2) caret는 trainControl,train함수 이용한다.
# trainControl 함수를 통해 모형적합과 평가에 대한 계산을 조절하는 옵션 설정
# method="cv":교차검증,repeats:데이터 샘플링 반복횟수, number:교차검증 몇 겹
# summaryFunction,이진분류:twoClassSummary,회귀:postResample
ctrl<-trainControl(method="cv",number=5,
summaryFunction=twoClassSummary,classProbs=TRUE)
rffit<-train(Class~.,data=train,method='rf',metric="ROC",
trControl=ctrl)
# 평가 메트릭. 분류 문제의 경우 정확도(accuracy), 회귀 문제일 경우 RMSE7로
# 지정한다.classProbs=TRUE ROC 계산을 위해 필요
names(getModelInfo())
## [1] "ada" "AdaBag" "AdaBoost.M1"
## [4] "adaboost" "amdai" "ANFIS"
## [7] "avNNet" "awnb" "awtan"
## [10] "bag" "bagEarth" "bagEarthGCV"
## [13] "bagFDA" "bagFDAGCV" "bam"
## [16] "bartMachine" "bayesglm" "binda"
## [19] "blackboost" "blasso" "blassoAveraged"
## [22] "bridge" "brnn" "BstLm"
## [25] "bstSm" "bstTree" "C5.0"
## [28] "C5.0Cost" "C5.0Rules" "C5.0Tree"
## [31] "cforest" "chaid" "CSimca"
## [34] "ctree" "ctree2" "cubist"
## [37] "dda" "deepboost" "DENFIS"
## [40] "dnn" "dwdLinear" "dwdPoly"
## [43] "dwdRadial" "earth" "elm"
## [46] "enet" "evtree" "extraTrees"
## [49] "fda" "FH.GBML" "FIR.DM"
## [52] "foba" "FRBCS.CHI" "FRBCS.W"
## [55] "FS.HGD" "gam" "gamboost"
## [58] "gamLoess" "gamSpline" "gaussprLinear"
## [61] "gaussprPoly" "gaussprRadial" "gbm_h2o"
## [64] "gbm" "gcvEarth" "GFS.FR.MOGUL"
## [67] "GFS.LT.RS" "GFS.THRIFT" "glm.nb"
## [70] "glm" "glmboost" "glmnet_h2o"
## [73] "glmnet" "glmStepAIC" "gpls"
## [76] "hda" "hdda" "hdrda"
## [79] "HYFIS" "icr" "J48"
## [82] "JRip" "kernelpls" "kknn"
## [85] "knn" "krlsPoly" "krlsRadial"
## [88] "lars" "lars2" "lasso"
## [91] "lda" "lda2" "leapBackward"
## [94] "leapForward" "leapSeq" "Linda"
## [97] "lm" "lmStepAIC" "LMT"
## [100] "loclda" "logicBag" "LogitBoost"
## [103] "logreg" "lssvmLinear" "lssvmPoly"
## [106] "lssvmRadial" "lvq" "M5"
## [109] "M5Rules" "manb" "mda"
## [112] "Mlda" "mlp" "mlpKerasDecay"
## [115] "mlpKerasDecayCost" "mlpKerasDropout" "mlpKerasDropoutCost"
## [118] "mlpML" "mlpSGD" "mlpWeightDecay"
## [121] "mlpWeightDecayML" "monmlp" "msaenet"
## [124] "multinom" "mxnet" "mxnetAdam"
## [127] "naive_bayes" "nb" "nbDiscrete"
## [130] "nbSearch" "neuralnet" "nnet"
## [133] "nnls" "nodeHarvest" "null"
## [136] "OneR" "ordinalNet" "ordinalRF"
## [139] "ORFlog" "ORFpls" "ORFridge"
## [142] "ORFsvm" "ownn" "pam"
## [145] "parRF" "PART" "partDSA"
## [148] "pcaNNet" "pcr" "pda"
## [151] "pda2" "penalized" "PenalizedLDA"
## [154] "plr" "pls" "plsRglm"
## [157] "polr" "ppr" "pre"
## [160] "PRIM" "protoclass" "qda"
## [163] "QdaCov" "qrf" "qrnn"
## [166] "randomGLM" "ranger" "rbf"
## [169] "rbfDDA" "Rborist" "rda"
## [172] "regLogistic" "relaxo" "rf"
## [175] "rFerns" "RFlda" "rfRules"
## [178] "ridge" "rlda" "rlm"
## [181] "rmda" "rocc" "rotationForest"
## [184] "rotationForestCp" "rpart" "rpart1SE"
## [187] "rpart2" "rpartCost" "rpartScore"
## [190] "rqlasso" "rqnc" "RRF"
## [193] "RRFglobal" "rrlda" "RSimca"
## [196] "rvmLinear" "rvmPoly" "rvmRadial"
## [199] "SBC" "sda" "sdwd"
## [202] "simpls" "SLAVE" "slda"
## [205] "smda" "snn" "sparseLDA"
## [208] "spikeslab" "spls" "stepLDA"
## [211] "stepQDA" "superpc" "svmBoundrangeString"
## [214] "svmExpoString" "svmLinear" "svmLinear2"
## [217] "svmLinear3" "svmLinearWeights" "svmLinearWeights2"
## [220] "svmPoly" "svmRadial" "svmRadialCost"
## [223] "svmRadialSigma" "svmRadialWeights" "svmSpectrumString"
## [226] "tan" "tanSearch" "treebag"
## [229] "vbmpRadial" "vglmAdjCat" "vglmContRatio"
## [232] "vglmCumulative" "widekernelpls" "WM"
## [235] "wsrf" "xgbDART" "xgbLinear"
## [238] "xgbTree" "xyf"
# metric='ROC' , ctrl 객체를 trContrl 인자에 입력
# metric= 옵션에는 "accuracy", "Kappa", "RMSE", "Rsquared"기 있다. 이 옵션은 최
# 종모형의 선택에 사용되는 목적함수를 지정함
# mtry=2 일때 최적의 분류모형, 랜덤포레스트 ntree(트리갯수),mtry(변수갯수)
prefit<-predict(rffit,newdata=test,type='raw')
class(prefit)
## [1] "factor"
prefit
## [1] R R R R R R M M R R R R R R R R R R R R R R R M M M M R R M M M M M M M M M
## [39] M M M M M M M M M M M R M M R M M M M M M M M M
## Levels: M R
library(pROC)
## Type 'citation("pROC")' for a citation.
##
## 다음의 패키지를 부착합니다: 'pROC'
## The following objects are masked from 'package:stats':
##
## cov, smooth, var
prefit_num<-as.numeric(prefit)
result<-roc(test$Class,prefit_num)
## Setting levels: control = M, case = R
## Setting direction: controls < cases
result$auc
## Area under the curve: 0.8662
predict(rffit,newdata=test) %>% confusionMatrix(test$Class)
## Confusion Matrix and Statistics
##
## Reference
## Prediction M R
## M 31 7
## R 2 22
##
## Accuracy : 0.8548
## 95% CI : (0.7422, 0.9314)
## No Information Rate : 0.5323
## P-Value [Acc > NIR] : 8.133e-08
##
## Kappa : 0.7054
##
## Mcnemar's Test P-Value : 0.1824
##
## Sensitivity : 0.9394
## Specificity : 0.7586
## Pos Pred Value : 0.8158
## Neg Pred Value : 0.9167
## Prevalence : 0.5323
## Detection Rate : 0.5000
## Detection Prevalence : 0.6129
## Balanced Accuracy : 0.8490
##
## 'Positive' Class : M
##
# 정확도, 특이도, 민감도 지표를 확인
ctrl<-trainControl(method="cv",number=5,
summaryFunction =twoClassSummary,classProbs=TRUE)
rffit1<-train(Class~.,data=train,method='rpart',metric="ROC",
trControl=ctrl)
# rpart CART수정 버젼
prefit1<-predict(rffit1,newdata=test)
class(prefit1)
## [1] "factor"
prefit1<-as.numeric(prefit1)
result1<-roc(test$Class,prefit1)
## Setting levels: control = M, case = R
## Setting direction: controls < cases
result1$auc
## Area under the curve: 0.7362
#glm
ctrl<-trainControl(method="cv",number=5,
summaryFunction =twoClassSummary,classProbs=TRUE)
rffit2<-train(Class~.,data=train,method='glm',family="binomial",
metric="ROC",trControl=ctrl)
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
prefit2<-predict(rffit2,newdata=test)
class(prefit2)
## [1] "factor"
prefit2
## [1] R M M M R R M M M R R R R R M R R R R R R R M R M M R M R R R M M M M M M R
## [39] M M M M M M M M M R M R M M R R M M M M M M M M
## Levels: M R
prefit2<-as.numeric(prefit2)
result2<-roc(test$Class,prefit2)
## Setting levels: control = M, case = R
## Setting direction: controls < cases
result1$auc
## Area under the curve: 0.7362
# 3. recipes package 이해하기
# 데이터 전처리 특화된 패키지
# recipe 생성에는 4단계가 있다.
# 1) 요리방식 정의 :recipe(), 응답변수 및 예측변수 지정
# 2) 레시피 작성:step_YeoJohnson(비대칭성 제거),
# step_center(표준화)
# step_scale('1'인 표준편차를 갖도록 정규화)
# 3)prep( ):적용된다.
# 4)juice():적용된 결과를 반환