기계학습이 여기저기서 들려오는데 막상 R을 사용하면서도 아직 개념을 잘 이해하지 못하고 있어서 여기에 정리해 본다.
Gitbook
위 두개의 링크를 참고하였다.
library(tidyverse) # for tidy tools (pipe operation, tibble, etc..)## -- Attaching packages ---------------------------------- tidyverse 1.2.1 --## √ ggplot2 2.2.1.9000 √ purrr 0.2.4
## √ tibble 1.4.2 √ dplyr 0.7.5
## √ tidyr 0.8.1 √ stringr 1.3.1
## √ readr 1.1.1 √ forcats 0.3.0## -- Conflicts ------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## x dplyr::vars() masks ggplot2::vars()library(caret)## 필요한 패키지를 로딩중입니다: lattice##
## 다음의 패키지를 부착합니다: 'caret'## The following object is masked from 'package:purrr':
##
## liftset.seed(1234) # for reproducibility
data(Sonar, package = "mlbench")
Sonar <- Sonar %>% tbl_df
Sonar## # A tibble: 208 x 61
## V1 V2 V3 V4 V5 V6 V7 V8 V9 V10
## * <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0.02 0.0371 0.0428 0.0207 0.0954 0.0986 0.154 0.160 0.311 0.211
## 2 0.0453 0.0523 0.0843 0.0689 0.118 0.258 0.216 0.348 0.334 0.287
## 3 0.0262 0.0582 0.110 0.108 0.0974 0.228 0.243 0.377 0.560 0.619
## 4 0.01 0.0171 0.0623 0.0205 0.0205 0.0368 0.110 0.128 0.0598 0.126
## 5 0.0762 0.0666 0.0481 0.0394 0.059 0.0649 0.121 0.247 0.356 0.446
## 6 0.0286 0.0453 0.0277 0.0174 0.0384 0.099 0.120 0.183 0.210 0.304
## 7 0.0317 0.0956 0.132 0.141 0.167 0.171 0.0731 0.140 0.208 0.351
## 8 0.0519 0.0548 0.0842 0.0319 0.116 0.0922 0.103 0.0613 0.146 0.284
## 9 0.0223 0.0375 0.0484 0.0475 0.0647 0.0591 0.0753 0.0098 0.0684 0.149
## 10 0.0164 0.0173 0.0347 0.007 0.0187 0.0671 0.106 0.0697 0.0962 0.0251
## # ... with 198 more rows, and 51 more variables: V11 <dbl>, V12 <dbl>,
## # V13 <dbl>, V14 <dbl>, V15 <dbl>, V16 <dbl>, V17 <dbl>, V18 <dbl>,
## # V19 <dbl>, V20 <dbl>, V21 <dbl>, V22 <dbl>, V23 <dbl>, V24 <dbl>,
## # V25 <dbl>, V26 <dbl>, V27 <dbl>, V28 <dbl>, V29 <dbl>, V30 <dbl>,
## # V31 <dbl>, V32 <dbl>, V33 <dbl>, V34 <dbl>, V35 <dbl>, V36 <dbl>,
## # V37 <dbl>, V38 <dbl>, V39 <dbl>, V40 <dbl>, V41 <dbl>, V42 <dbl>,
## # V43 <dbl>, V44 <dbl>, V45 <dbl>, V46 <dbl>, V47 <dbl>, V48 <dbl>,
## # V49 <dbl>, V50 <dbl>, V51 <dbl>, V52 <dbl>, V53 <dbl>, V54 <dbl>,
## # V55 <dbl>, V56 <dbl>, V57 <dbl>, V58 <dbl>, V59 <dbl>, V60 <dbl>,
## # Class <fct>indexTrain <- sample(1:nrow(Sonar), round(nrow(Sonar) * .7))
training <- Sonar[ indexTrain, ]
testing <- Sonar[-indexTrain, ]
training## # A tibble: 146 x 61
## V1 V2 V3 V4 V5 V6 V7 V8 V9 V10
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0.0115 0.015 0.0136 0.0076 0.0211 0.106 0.102 0.044 0.0931 0.0734
## 2 0.0374 0.0586 0.0628 0.0534 0.0255 0.142 0.207 0.273 0.307 0.260
## 3 0.0228 0.0853 0.1 0.0428 0.112 0.165 0.160 0.212 0.330 0.352
## 4 0.0209 0.0261 0.012 0.0768 0.106 0.168 0.302 0.346 0.331 0.412
## 5 0.0294 0.0123 0.0117 0.0113 0.0497 0.0998 0.133 0.112 0.298 0.347
## 6 0.137 0.123 0.138 0.148 0.178 0.143 0.177 0.216 0.163 0.207
## 7 0.0453 0.0523 0.0843 0.0689 0.118 0.258 0.216 0.348 0.334 0.287
## 8 0.0308 0.0339 0.0202 0.0889 0.157 0.175 0.092 0.135 0.159 0.280
## 9 0.079 0.0707 0.0352 0.166 0.133 0.0226 0.0771 0.268 0.566 0.661
## 10 0.0587 0.121 0.127 0.150 0.144 0.0561 0.0832 0.0672 0.137 0.235
## # ... with 136 more rows, and 51 more variables: V11 <dbl>, V12 <dbl>,
## # V13 <dbl>, V14 <dbl>, V15 <dbl>, V16 <dbl>, V17 <dbl>, V18 <dbl>,
## # V19 <dbl>, V20 <dbl>, V21 <dbl>, V22 <dbl>, V23 <dbl>, V24 <dbl>,
## # V25 <dbl>, V26 <dbl>, V27 <dbl>, V28 <dbl>, V29 <dbl>, V30 <dbl>,
## # V31 <dbl>, V32 <dbl>, V33 <dbl>, V34 <dbl>, V35 <dbl>, V36 <dbl>,
## # V37 <dbl>, V38 <dbl>, V39 <dbl>, V40 <dbl>, V41 <dbl>, V42 <dbl>,
## # V43 <dbl>, V44 <dbl>, V45 <dbl>, V46 <dbl>, V47 <dbl>, V48 <dbl>,
## # V49 <dbl>, V50 <dbl>, V51 <dbl>, V52 <dbl>, V53 <dbl>, V54 <dbl>,
## # V55 <dbl>, V56 <dbl>, V57 <dbl>, V58 <dbl>, V59 <dbl>, V60 <dbl>,
## # Class <fct>testing## # A tibble: 62 x 61
## V1 V2 V3 V4 V5 V6 V7 V8 V9 V10
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0.02 0.0371 0.0428 0.0207 0.0954 0.0986 0.154 0.160 0.311 0.211
## 2 0.0762 0.0666 0.0481 0.0394 0.059 0.0649 0.121 0.247 0.356 0.446
## 3 0.0286 0.0453 0.0277 0.0174 0.0384 0.099 0.120 0.183 0.210 0.304
## 4 0.0039 0.0063 0.0152 0.0336 0.031 0.0284 0.0396 0.0272 0.0323 0.0452
## 5 0.0124 0.0433 0.0604 0.0449 0.0597 0.0355 0.0531 0.0343 0.105 0.212
## 6 0.027 0.0092 0.0145 0.0278 0.0412 0.0757 0.103 0.114 0.0794 0.152
## 7 0.0177 0.03 0.0288 0.0394 0.063 0.0526 0.0688 0.0633 0.0624 0.0613
## 8 0.01 0.0275 0.019 0.0371 0.0416 0.0201 0.0314 0.0651 0.190 0.267
## 9 0.024 0.0218 0.0324 0.0569 0.033 0.0513 0.0897 0.0713 0.0569 0.0389
## 10 0.0195 0.0213 0.00580 0.019 0.0319 0.0571 0.100 0.0668 0.0691 0.0242
## # ... with 52 more rows, and 51 more variables: V11 <dbl>, V12 <dbl>,
## # V13 <dbl>, V14 <dbl>, V15 <dbl>, V16 <dbl>, V17 <dbl>, V18 <dbl>,
## # V19 <dbl>, V20 <dbl>, V21 <dbl>, V22 <dbl>, V23 <dbl>, V24 <dbl>,
## # V25 <dbl>, V26 <dbl>, V27 <dbl>, V28 <dbl>, V29 <dbl>, V30 <dbl>,
## # V31 <dbl>, V32 <dbl>, V33 <dbl>, V34 <dbl>, V35 <dbl>, V36 <dbl>,
## # V37 <dbl>, V38 <dbl>, V39 <dbl>, V40 <dbl>, V41 <dbl>, V42 <dbl>,
## # V43 <dbl>, V44 <dbl>, V45 <dbl>, V46 <dbl>, V47 <dbl>, V48 <dbl>,
## # V49 <dbl>, V50 <dbl>, V51 <dbl>, V52 <dbl>, V53 <dbl>, V54 <dbl>,
## # V55 <dbl>, V56 <dbl>, V57 <dbl>, V58 <dbl>, V59 <dbl>, V60 <dbl>,
## # Class <fct>fitControl <- trainControl(method = "repeatedcv", number = 10, repeats = 5)
# RandomForest 로 학습시켜보기
rf_fit <- train(Class ~ ., data = training, method = "rf", trControl = fitControl, verbose = F)
rf_fit## Random Forest
##
## 146 samples
## 60 predictor
## 2 classes: 'M', 'R'
##
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 5 times)
## Summary of sample sizes: 132, 132, 131, 131, 130, 132, ...
## Resampling results across tuning parameters:
##
## mtry Accuracy Kappa
## 2 0.8197381 0.6378550
## 31 0.7972381 0.5938628
## 60 0.7805714 0.5598370
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 2.