Работа с пакетами CARET и BORUTA на языке R
Артём Лозовенко
Задание 1: Установка и использование пакета caret
В этом задании мы установим пакет caret, получим
информацию о моделях и используем функцию featurePlot для
визуализации данных.
# CRAN зеркало для rmd
options(repos = c(CRAN = "https://cran.rstudio.com"))
# установка и загрузка пакета caret
install.packages("caret")## Installing package into 'C:/Users/art2m/AppData/Local/R/win-library/4.4'
## (as 'lib' is unspecified)## package 'caret' successfully unpacked and MD5 sums checked## Warning: cannot remove prior installation of package 'caret'## Warning in file.copy(savedcopy, lib, recursive = TRUE): problem copying
## C:\Users\art2m\AppData\Local\R\win-library\4.4\00LOCK\caret\libs\x64\caret.dll
## to C:\Users\art2m\AppData\Local\R\win-library\4.4\caret\libs\x64\caret.dll:
## Permission denied## Warning: restored 'caret'##
## The downloaded binary packages are in
## C:\Users\art2m\AppData\Local\Temp\RtmpoduoOa\downloaded_packageslibrary(caret)## Loading required package: ggplot2## Loading required package: lattice# С помощью команды names(getModelInfo()) получим список доступных методов выбора признака.
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"# Создадим матрицу непрерывных данных как первый параметр функции featurePlot, и фактор, указывающий на принадлежность к классу как второй параметр:
x <- matrix(rnorm(50*5), ncol=5)
y <- factor(rep(c("A", "B"), 25))
# Вызовем функцию featurePlot() с параметрами x, y заданными ранее:
featurePlot(x, y)
# Сохраним график в формате .jpg используя команды:
jpeg("lab2.jpg")
featurePlot(x, y)
dev.off()## png
## 2Задание 2. Работа с пакетом FSelector
# Установим и активируем FSelector с помощью команд
install.packages("FSelector")## Installing package into 'C:/Users/art2m/AppData/Local/R/win-library/4.4'
## (as 'lib' is unspecified)## package 'FSelector' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\art2m\AppData\Local\Temp\RtmpoduoOa\downloaded_packageslibrary(FSelector)## java.home option:## JAVA_HOME environment variable: C:\Users\art2m\jdk-18## Warning in fun(libname, pkgname): Java home setting is INVALID, it will be ignored.
## Please do NOT set it unless you want to override system settings.# Загрузка данных iris
data(iris)
# Для определения важности признаков для решения задачи классификации необходимо получить метрику с помощью команд
inf <- information.gain(Species ~ ., data=iris)
inf## attr_importance
## Sepal.Length 0.4521286
## Sepal.Width 0.2672750
## Petal.Length 0.9402853
## Petal.Width 0.9554360# Установка и загрузка пакета arules
install.packages("arules")## Installing package into 'C:/Users/art2m/AppData/Local/R/win-library/4.4'
## (as 'lib' is unspecified)## package 'arules' successfully unpacked and MD5 sums checked## Warning: cannot remove prior installation of package 'arules'## Warning in file.copy(savedcopy, lib, recursive = TRUE): problem copying
## C:\Users\art2m\AppData\Local\R\win-library\4.4\00LOCK\arules\libs\x64\arules.dll
## to C:\Users\art2m\AppData\Local\R\win-library\4.4\arules\libs\x64\arules.dll:
## Permission denied## Warning: restored 'arules'##
## The downloaded binary packages are in
## C:\Users\art2m\AppData\Local\Temp\RtmpoduoOa\downloaded_packageslibrary(arules)## Loading required package: Matrix##
## Attaching package: 'arules'## The following objects are masked from 'package:base':
##
## abbreviate, write# Для конвертации будем использовать функцию discretize() с двумя аргументами: набор данных и метод конвертации. Необходимо обновить столбец датасета путем присваивания результат работы функции.
# В данном случае набором данных является длина листа ириса, метод интервалов
iris$Sepal.Length <- discretize(iris$Sepal.Length, method="interval")
# Применим функцию discretize() к второму столбцу датасета, а так же заменим метод на частотный.
iris$Sepal.Width <- discretize(iris$Sepal.Width, method="frequency")
#Результатом работы данной функции будет конвертация непрерывных переменных второго столбца датасата ирис в категориальные с частотами: [2,2.9) [2.9,3.2) [3.2,4.4]
head(iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 [4.3,5.5) [3.2,4.4] 1.4 0.2 setosa
## 2 [4.3,5.5) [2.9,3.2) 1.4 0.2 setosa
## 3 [4.3,5.5) [3.2,4.4] 1.3 0.2 setosa
## 4 [4.3,5.5) [2.9,3.2) 1.5 0.2 setosa
## 5 [4.3,5.5) [3.2,4.4] 1.4 0.2 setosa
## 6 [4.3,5.5) [3.2,4.4] 1.7 0.4 setosa# Далее по аналогии конвертируем столбцы Petal.Length и Petal.Width с использованием методов кластеризации и «fixed». Вызов discretize(iris$Petal.Length, method="cluster") делит значения столбца Petal.Length на интервалы с использованием метода кластеризации. Эти интервалы представляют собой категории, например, [1,2.85).
iris$Petal.Length <- discretize(iris$Petal.Length, method="cluster")
# Для использования метода fixed необходимо указать количество интервалов, сделаем разбиение на интервал от 0 до 2, с границами 0,5 и 1.
iris$Petal.Width <- discretize(iris$Petal.Width, method="fixed", breaks=c(0, 0.5, 1, 2))
# Просмотр измененных данных
head(iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 [4.3,5.5) [3.2,4.4] [1,2.95) [0,0.5) setosa
## 2 [4.3,5.5) [2.9,3.2) [1,2.95) [0,0.5) setosa
## 3 [4.3,5.5) [3.2,4.4] [1,2.95) [0,0.5) setosa
## 4 [4.3,5.5) [2.9,3.2) [1,2.95) [0,0.5) setosa
## 5 [4.3,5.5) [3.2,4.4] [1,2.95) [0,0.5) setosa
## 6 [4.3,5.5) [3.2,4.4] [1,2.95) [0,0.5) setosaЗадание 3. Выбор признаков для набора данных data(“Ozone”)
# Установка и загрузка пакета Boruta
install.packages("Boruta")## Installing package into 'C:/Users/art2m/AppData/Local/R/win-library/4.4'
## (as 'lib' is unspecified)## package 'Boruta' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\art2m\AppData\Local\Temp\RtmpoduoOa\downloaded_packageslibrary(Boruta)
# Загрузка данных ozone (у меня не получилось методами языка, я скачал датасет и поместил в рабочую директорию)
ozone <- read.csv("ozone.csv")
head(ozone)## rownames Year Aug Sep Oct Nov Dec Jan Feb Mar Apr Annual
## 1 1 1956 0 313 311 370 359 334 296 288 274 318
## 2 2 1957 301 284 320 394 347 332 301 280 256 312
## 3 3 1958 0 0 305 349 378 341 328 297 0 333
## 4 4 1959 0 0 302 303 340 322 298 295 0 309
## 5 5 1960 0 287 292 345 375 318 303 304 0 318
## 6 6 1961 0 267 307 332 343 310 297 329 0 312tail(ozone)## rownames Year Aug Sep Oct Nov Dec Jan Feb Mar Apr Annual
## 40 40 1995 218 160 130 164 252 261 249 246 226 212
## 41 41 1996 173 155 148 181 260 278 265 247 243 217
## 42 42 1997 218 171 141 210 286 267 262 264 255 230
## 43 43 1998 221 162 140 183 255 272 259 254 267 224
## 44 44 1999 205 172 143 172 254 281 258 250 256 221
## 45 45 2000 179 151 137 267 299 286 261 251 245 231# Проведем анализа Boruta для выбора признаков
res <- Boruta(Annual ~ ., data=ozone, doTrace=2)## 1. run of importance source...## 2. run of importance source...## 3. run of importance source...## 4. run of importance source...## 5. run of importance source...## 6. run of importance source...## 7. run of importance source...## 8. run of importance source...## 9. run of importance source...## 10. run of importance source...## 11. run of importance source...## After 11 iterations, +0.3 secs:## confirmed 9 attributes: Dec, Feb, Jan, Mar, Nov and 4 more;## still have 2 attributes left.## 12. run of importance source...## 13. run of importance source...## 14. run of importance source...## 15. run of importance source...## 16. run of importance source...## 17. run of importance source...## 18. run of importance source...## 19. run of importance source...## 20. run of importance source...## 21. run of importance source...## After 21 iterations, +0.55 secs:## confirmed 1 attribute: Aug;## still have 1 attribute left.## 22. run of importance source...## 23. run of importance source...## 24. run of importance source...## 25. run of importance source...## 26. run of importance source...## 27. run of importance source...## 28. run of importance source...## 29. run of importance source...## 30. run of importance source...## 31. run of importance source...## 32. run of importance source...## 33. run of importance source...## 34. run of importance source...## 35. run of importance source...## 36. run of importance source...## 37. run of importance source...## 38. run of importance source...## 39. run of importance source...## 40. run of importance source...## 41. run of importance source...## 42. run of importance source...## 43. run of importance source...## 44. run of importance source...## 45. run of importance source...## 46. run of importance source...## 47. run of importance source...## 48. run of importance source...## 49. run of importance source...## 50. run of importance source...## 51. run of importance source...## 52. run of importance source...## 53. run of importance source...## 54. run of importance source...## 55. run of importance source...## 56. run of importance source...## 57. run of importance source...## 58. run of importance source...## 59. run of importance source...## 60. run of importance source...## 61. run of importance source...## 62. run of importance source...## 63. run of importance source...## 64. run of importance source...## 65. run of importance source...## 66. run of importance source...## 67. run of importance source...## 68. run of importance source...## 69. run of importance source...## 70. run of importance source...## 71. run of importance source...## 72. run of importance source...## 73. run of importance source...## 74. run of importance source...## 75. run of importance source...## 76. run of importance source...## 77. run of importance source...## 78. run of importance source...## 79. run of importance source...## 80. run of importance source...## 81. run of importance source...## 82. run of importance source...## 83. run of importance source...## 84. run of importance source...## 85. run of importance source...## 86. run of importance source...## 87. run of importance source...## 88. run of importance source...## 89. run of importance source...## 90. run of importance source...## 91. run of importance source...## 92. run of importance source...## 93. run of importance source...## 94. run of importance source...## 95. run of importance source...## 96. run of importance source...## 97. run of importance source...## 98. run of importance source...## 99. run of importance source...# Результаты и график
res## Boruta performed 99 iterations in 2.389535 secs.
## 10 attributes confirmed important: Aug, Dec, Feb, Jan, Mar and 5 more;
## No attributes deemed unimportant.
## 1 tentative attributes left: Apr;plot(res)
# Построение графика boxplot
boxplot(ozone[, -1], main="Концентрация озона", ylab="Концентрация")