Задание 1. Разведочный анализ данных с помощью featurePlot()
Установка и загрузка пакета CARET
library(caret)
Просмотр доступных методов выбора признаков
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"
Создание тестовых данных
set.seed(123)
x <- matrix(rnorm(50*5), ncol=5)
y <- factor(rep(c("A", "B"), 25))
df <- as.data.frame(x)
colnames(df) <- paste0("X", 1:5)
df$Class <- y
Построение графиков featurePlot()
featurePlot(x = df[, 1:5],
y = df$Class,
plot = "pairs")
featurePlot(x = df[, 1:5],
y = df$Class,
plot = "ellipse")
featurePlot(x = df[, 1:5],
y = df$Class,
plot = "box")
featurePlot(x = df[, 1:5],
y = df$Class,
plot = "density")
Сохранение графиков в *.jpg файлы
jpeg("featurePlot_pairs.jpg")
featurePlot(x = df[, 1:5], y = df$Class, plot = "pairs")
dev.off()
## png
## 2
jpeg("featurePlot_ellipse.jpg")
featurePlot(x = df[, 1:5], y = df$Class, plot = "ellipse")
dev.off()
## png
## 2
jpeg("featurePlot_box.jpg")
featurePlot(x = df[, 1:5], y = df$Class, plot = "box")
dev.off()
## png
## 2
jpeg("featurePlot_density.jpg")
featurePlot(x = df[, 1:5], y = df$Class, plot = "density")
dev.off()
## png
## 2
Задание 2. Определение важности признаков с помощью пакета
FSelector
library(FSelector)
data(iris)
Отбор лучших признаков
subset <- cutoff.k(weights, 2)
print(subset)
## [1] "Petal.Width" "Petal.Length"
Задание 3. Дискретизация непрерывных переменных с помощью пакета
arules
library(arules)
data(iris)
Метод “interval” (равная ширина интервала)
iris_interval <- discretize(iris$Sepal.Length, method = "interval", categories = 3)
head(iris_interval)
## [1] [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5)
## Levels: [4.3,5.5) [5.5,6.7) [6.7,7.9]
table(iris_interval)
## iris_interval
## [4.3,5.5) [5.5,6.7) [6.7,7.9]
## 52 70 28
Метод “frequency” (равная частота)
iris_frequency <- discretize(iris$Sepal.Length, method = "frequency", categories = 3)
head(iris_frequency)
## [1] [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [5.4,6.3)
## Levels: [4.3,5.4) [5.4,6.3) [6.3,7.9]
table(iris_frequency)
## iris_frequency
## [4.3,5.4) [5.4,6.3) [6.3,7.9]
## 46 53 51
Метод “cluster” (кластеризация)
iris_cluster <- discretize(iris$Sepal.Length, method = "cluster", categories = 3)
head(iris_cluster)
## [1] [4.3,5.33) [4.3,5.33) [4.3,5.33) [4.3,5.33) [4.3,5.33) [5.33,6.27)
## Levels: [4.3,5.33) [5.33,6.27) [6.27,7.9]
table(iris_cluster)
## iris_cluster
## [4.3,5.33) [5.33,6.27) [6.27,7.9]
## 46 53 51
Метод “fixed” (заданные границы интервалов)
iris_fixed <- discretize(iris$Sepal.Length, method = "fixed", breaks = c(4, 5.5, 7, 8))
head(iris_fixed)
## [1] [4,5.5) [4,5.5) [4,5.5) [4,5.5) [4,5.5) [4,5.5)
## Levels: [4,5.5) [5.5,7) [7,8]
table(iris_fixed)
## iris_fixed
## [4,5.5) [5.5,7) [7,8]
## 52 85 13
Задание 4. Выбор признаков с помощью пакета Boruta
library(Boruta)
library(mlbench)
data(Ozone)
Ozone <- na.omit(Ozone)
Запуск алгоритма Boruta
set.seed(123)
boruta_result <- Boruta(V4 ~ ., data = Ozone, doTrace = 0)
print(boruta_result)
## Boruta performed 18 iterations in 0.323199 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;
Статистика важности признаков
stats <- attStats(boruta_result)
print(stats)
## meanImp medianImp minImp maxImp normHits decision
## V1 0.40660229 0.39874710 0.37208192 0.50361585 1.00000000 Confirmed
## V2 0.04391890 0.03169822 -0.02604472 0.13137821 0.11111111 Rejected
## V3 -0.03235907 -0.04528594 -0.08039941 0.03178173 0.00000000 Rejected
## V5 0.37961385 0.37663333 0.33809868 0.42147363 1.00000000 Confirmed
## V6 0.04740489 0.05979747 -0.01572443 0.12718160 0.05555556 Rejected
## V7 0.51883205 0.50588169 0.46725744 0.59114026 1.00000000 Confirmed
## V8 0.77086858 0.76889989 0.73251688 0.81327051 1.00000000 Confirmed
## V9 0.86915268 0.86432645 0.84273725 0.92413075 1.00000000 Confirmed
## V10 0.42389058 0.41739463 0.38164901 0.49245967 1.00000000 Confirmed
## V11 0.55143690 0.54721914 0.49482770 0.61161304 1.00000000 Confirmed
## V12 0.66051279 0.65832222 0.60234621 0.73958611 1.00000000 Confirmed
## V13 0.42761454 0.42057856 0.38618408 0.46920282 1.00000000 Confirmed
Построение графика boxplot
plot(boruta_result, cex.axis = 0.7, las = 2, main = "Boruta: Важность признаков")
Дополнительный график истории важности
plotImpHistory(boruta_result)
