AD2
2025-01-19
Установка пакетов и подключение библиотек
“install.packages(”caret”) install.packages(“FSelector”) install.packages(“Boruta”) install.packages(“mlbench”) install.packages(“arules”)”
library(caret)
library(mlbench)
library(ggplot2)
library(FSelector)
library(arules)
library(Boruta)
# выполнить команду names(getModelInfo())
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"# 1. Графический разведочный анализ данных с использованием featurePlot()
x <- matrix(rnorm(50 * 5), ncol = 5)
y <- factor(rep(c("A", "B"), 25))
featurePlot(x, y)
# Сохранение графика в файл
jpeg("feature_plot.jpg")
featurePlot(x, y)
dev.off()## png
## 2# Вывод: Большая часть значений находится в промежутке от -1 до 1.
# 2. Определение важности признаков с использованием FSelector
data(iris)
pairs(iris[, 1:4], col = iris[, 5], pch = 19, cex = 1.2, oma = c(4, 4, 6, 12))
par(xpd = TRUE)
legend("topright", legend = as.vector(unique(iris$Species)), fill = c(1, 2, 3), title = "Виды", cex = 0.8)
# Вывод: Sepal.Width является наименее значимым признаком, а Petal.Length наиболее значимым.
# 3. Преобразование непрерывной переменной в категориальную с использованием discretize()
breaks <- seq(from = 0, to = 10, by = 1)
# Метод "interval" (равная ширина интервала)
percents_interval <- discretize(iris[, 1], method = "interval", breaks = 10)
print(percents_interval)## [1] [5.02,5.38) [4.66,5.02) [4.66,5.02) [4.3,4.66) [4.66,5.02) [5.38,5.74)
## [7] [4.3,4.66) [4.66,5.02) [4.3,4.66) [4.66,5.02) [5.38,5.74) [4.66,5.02)
## [13] [4.66,5.02) [4.3,4.66) [5.74,6.1) [5.38,5.74) [5.38,5.74) [5.02,5.38)
## [19] [5.38,5.74) [5.02,5.38) [5.38,5.74) [5.02,5.38) [4.3,4.66) [5.02,5.38)
## [25] [4.66,5.02) [4.66,5.02) [4.66,5.02) [5.02,5.38) [5.02,5.38) [4.66,5.02)
## [31] [4.66,5.02) [5.38,5.74) [5.02,5.38) [5.38,5.74) [4.66,5.02) [4.66,5.02)
## [37] [5.38,5.74) [4.66,5.02) [4.3,4.66) [5.02,5.38) [4.66,5.02) [4.3,4.66)
## [43] [4.3,4.66) [4.66,5.02) [5.02,5.38) [4.66,5.02) [5.02,5.38) [4.3,4.66)
## [49] [5.02,5.38) [4.66,5.02) [6.82,7.18) [6.1,6.46) [6.82,7.18) [5.38,5.74)
## [55] [6.46,6.82) [5.38,5.74) [6.1,6.46) [4.66,5.02) [6.46,6.82) [5.02,5.38)
## [61] [4.66,5.02) [5.74,6.1) [5.74,6.1) [6.1,6.46) [5.38,5.74) [6.46,6.82)
## [67] [5.38,5.74) [5.74,6.1) [6.1,6.46) [5.38,5.74) [5.74,6.1) [6.1,6.46)
## [73] [6.1,6.46) [6.1,6.46) [6.1,6.46) [6.46,6.82) [6.46,6.82) [6.46,6.82)
## [79] [5.74,6.1) [5.38,5.74) [5.38,5.74) [5.38,5.74) [5.74,6.1) [5.74,6.1)
## [85] [5.38,5.74) [5.74,6.1) [6.46,6.82) [6.1,6.46) [5.38,5.74) [5.38,5.74)
## [91] [5.38,5.74) [6.1,6.46) [5.74,6.1) [4.66,5.02) [5.38,5.74) [5.38,5.74)
## [97] [5.38,5.74) [6.1,6.46) [5.02,5.38) [5.38,5.74) [6.1,6.46) [5.74,6.1)
## [103] [6.82,7.18) [6.1,6.46) [6.46,6.82) [7.54,7.9] [4.66,5.02) [7.18,7.54)
## [109] [6.46,6.82) [7.18,7.54) [6.46,6.82) [6.1,6.46) [6.46,6.82) [5.38,5.74)
## [115] [5.74,6.1) [6.1,6.46) [6.46,6.82) [7.54,7.9] [7.54,7.9] [5.74,6.1)
## [121] [6.82,7.18) [5.38,5.74) [7.54,7.9] [6.1,6.46) [6.46,6.82) [7.18,7.54)
## [127] [6.1,6.46) [6.1,6.46) [6.1,6.46) [7.18,7.54) [7.18,7.54) [7.54,7.9]
## [133] [6.1,6.46) [6.1,6.46) [6.1,6.46) [7.54,7.9] [6.1,6.46) [6.1,6.46)
## [139] [5.74,6.1) [6.82,7.18) [6.46,6.82) [6.82,7.18) [5.74,6.1) [6.46,6.82)
## [145] [6.46,6.82) [6.46,6.82) [6.1,6.46) [6.46,6.82) [6.1,6.46) [5.74,6.1)
## attr(,"discretized:breaks")
## [1] 4.30 4.66 5.02 5.38 5.74 6.10 6.46 6.82 7.18 7.54 7.90
## attr(,"discretized:method")
## [1] interval
## 10 Levels: [4.3,4.66) [4.66,5.02) [5.02,5.38) [5.38,5.74) ... [7.54,7.9]# Метод "cluster" (кластеризация)
percents_cluster <- discretize(iris[, 1], method = "cluster", breaks = 10)
print(percents_cluster)## [1] [4.95,5.28) [4.66,4.95) [4.66,4.95) [4.3,4.66) [4.95,5.28) [5.28,5.63)
## [7] [4.3,4.66) [4.95,5.28) [4.3,4.66) [4.66,4.95) [5.28,5.63) [4.66,4.95)
## [13] [4.66,4.95) [4.3,4.66) [5.63,5.91) [5.63,5.91) [5.28,5.63) [4.95,5.28)
## [19] [5.63,5.91) [4.95,5.28) [5.28,5.63) [4.95,5.28) [4.3,4.66) [4.95,5.28)
## [25] [4.66,4.95) [4.95,5.28) [4.95,5.28) [4.95,5.28) [4.95,5.28) [4.66,4.95)
## [31] [4.66,4.95) [5.28,5.63) [4.95,5.28) [5.28,5.63) [4.66,4.95) [4.95,5.28)
## [37] [5.28,5.63) [4.66,4.95) [4.3,4.66) [4.95,5.28) [4.95,5.28) [4.3,4.66)
## [43] [4.3,4.66) [4.95,5.28) [4.95,5.28) [4.66,4.95) [4.95,5.28) [4.3,4.66)
## [49] [5.28,5.63) [4.95,5.28) [6.64,7.16) [6.37,6.64) [6.64,7.16) [5.28,5.63)
## [55] [6.37,6.64) [5.63,5.91) [6.16,6.37) [4.66,4.95) [6.37,6.64) [4.95,5.28)
## [61] [4.95,5.28) [5.63,5.91) [5.91,6.16) [5.91,6.16) [5.28,5.63) [6.64,7.16)
## [67] [5.28,5.63) [5.63,5.91) [6.16,6.37) [5.28,5.63) [5.63,5.91) [5.91,6.16)
## [73] [6.16,6.37) [5.91,6.16) [6.37,6.64) [6.37,6.64) [6.64,7.16) [6.64,7.16)
## [79] [5.91,6.16) [5.63,5.91) [5.28,5.63) [5.28,5.63) [5.63,5.91) [5.91,6.16)
## [85] [5.28,5.63) [5.91,6.16) [6.64,7.16) [6.16,6.37) [5.28,5.63) [5.28,5.63)
## [91] [5.28,5.63) [5.91,6.16) [5.63,5.91) [4.95,5.28) [5.28,5.63) [5.63,5.91)
## [97] [5.63,5.91) [6.16,6.37) [4.95,5.28) [5.63,5.91) [6.16,6.37) [5.63,5.91)
## [103] [6.64,7.16) [6.16,6.37) [6.37,6.64) [7.16,7.9] [4.66,4.95) [7.16,7.9]
## [109] [6.64,7.16) [7.16,7.9] [6.37,6.64) [6.37,6.64) [6.64,7.16) [5.63,5.91)
## [115] [5.63,5.91) [6.37,6.64) [6.37,6.64) [7.16,7.9] [7.16,7.9] [5.91,6.16)
## [121] [6.64,7.16) [5.28,5.63) [7.16,7.9] [6.16,6.37) [6.64,7.16) [7.16,7.9]
## [127] [6.16,6.37) [5.91,6.16) [6.37,6.64) [7.16,7.9] [7.16,7.9] [7.16,7.9]
## [133] [6.37,6.64) [6.16,6.37) [5.91,6.16) [7.16,7.9] [6.16,6.37) [6.37,6.64)
## [139] [5.91,6.16) [6.64,7.16) [6.64,7.16) [6.64,7.16) [5.63,5.91) [6.64,7.16)
## [145] [6.64,7.16) [6.64,7.16) [6.16,6.37) [6.37,6.64) [6.16,6.37) [5.63,5.91)
## attr(,"discretized:breaks")
## [1] 4.300000 4.659829 4.952341 5.281957 5.631111 5.911111 6.159615 6.366758
## [9] 6.635084 7.157487 7.900000
## attr(,"discretized:method")
## [1] cluster
## 10 Levels: [4.3,4.66) [4.66,4.95) [4.95,5.28) [5.28,5.63) ... [7.16,7.9]# Метод "fixed" (заданные границы интервалов)
percents_fixed <- discretize(iris[, 1], method = "fixed", breaks = breaks)
print(percents_fixed)## [1] [5,6) [4,5) [4,5) [4,5) [5,6) [5,6) [4,5) [5,6) [4,5) [4,5) [5,6) [4,5)
## [13] [4,5) [4,5) [5,6) [5,6) [5,6) [5,6) [5,6) [5,6) [5,6) [5,6) [4,5) [5,6)
## [25] [4,5) [5,6) [5,6) [5,6) [5,6) [4,5) [4,5) [5,6) [5,6) [5,6) [4,5) [5,6)
## [37] [5,6) [4,5) [4,5) [5,6) [5,6) [4,5) [4,5) [5,6) [5,6) [4,5) [5,6) [4,5)
## [49] [5,6) [5,6) [7,8) [6,7) [6,7) [5,6) [6,7) [5,6) [6,7) [4,5) [6,7) [5,6)
## [61] [5,6) [5,6) [6,7) [6,7) [5,6) [6,7) [5,6) [5,6) [6,7) [5,6) [5,6) [6,7)
## [73] [6,7) [6,7) [6,7) [6,7) [6,7) [6,7) [6,7) [5,6) [5,6) [5,6) [5,6) [6,7)
## [85] [5,6) [6,7) [6,7) [6,7) [5,6) [5,6) [5,6) [6,7) [5,6) [5,6) [5,6) [5,6)
## [97] [5,6) [6,7) [5,6) [5,6) [6,7) [5,6) [7,8) [6,7) [6,7) [7,8) [4,5) [7,8)
## [109] [6,7) [7,8) [6,7) [6,7) [6,7) [5,6) [5,6) [6,7) [6,7) [7,8) [7,8) [6,7)
## [121] [6,7) [5,6) [7,8) [6,7) [6,7) [7,8) [6,7) [6,7) [6,7) [7,8) [7,8) [7,8)
## [133] [6,7) [6,7) [6,7) [7,8) [6,7) [6,7) [6,7) [6,7) [6,7) [6,7) [5,6) [6,7)
## [145] [6,7) [6,7) [6,7) [6,7) [6,7) [5,6)
## attr(,"discretized:breaks")
## [1] 0 1 2 3 4 5 6 7 8 9 10
## attr(,"discretized:method")
## [1] fixed
## Levels: [0,1) [1,2) [2,3) [3,4) [4,5) [5,6) [6,7) [7,8) [8,9) [9,10]# Вывод: В зависимости от выбранного метода изменяются границы интервалов в категориальной переменной.
# 4. Выбор признаков с использованием Boruta
data("Ozone", package = "mlbench")
Ozone <- na.omit(Ozone)
boruta_result <- Boruta(V4 ~ ., data = Ozone, doTrace = 2)
# Печать результатов Boruta
print(boruta_result)## Boruta performed 21 iterations in 1.320453 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;# Построение графика результатов Boruta
plot(boruta_result)
# Сохранение графика в файл
jpeg("boruta_plot.jpg")
plot(boruta_result)
dev.off()## png
## 2# Вывод: Boruta подтвердил важность 9 признаков, отклонил 3 признака как неважные.