knitr::opts_chunk$set(echo = TRUE, warning = FALSE, message = TRUE)
library(caret)
## Warning: пакет 'caret' был собран под R версии 4.5.2
## Загрузка требуемого пакета: ggplot2
## Загрузка требуемого пакета: lattice
library(FSelectorRcpp)
## Warning: пакет 'FSelectorRcpp' был собран под R версии 4.5.2
library(arules)
## Warning: пакет 'arules' был собран под R версии 4.5.2
## Загрузка требуемого пакета: Matrix
##
## Присоединяю пакет: 'arules'
## Следующий объект скрыт от 'package:FSelectorRcpp':
##
## discretize
## Следующие объекты скрыты от 'package:base':
##
## abbreviate, write
library(Boruta)
## Warning: пакет 'Boruta' был собран под R версии 4.5.2
library(mlbench)
## Warning: пакет 'mlbench' был собран под R версии 4.5.2
# список доступных моделей и методов
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"
# генерация искусственного набора данных
set.seed(123)
x <- matrix(rnorm(50 * 5), ncol = 5)
y <- factor(rep(c("A", "B"), 25))
# сохранение графиков
jpeg("feature_pairs.jpg")
featurePlot(x = x, y = y, plot = "pairs")
dev.off()
## png
## 2
jpeg("feature_box.jpg")
featurePlot(x = x, y = y, plot = "box")
dev.off()
## png
## 2
data(iris)
weights <- information_gain(Species ~ ., iris)
weights
## attributes importance
## 1 Sepal.Length 0.4521286
## 2 Sepal.Width 0.2672750
## 3 Petal.Length 0.9402853
## 4 Petal.Width 0.9554360
iris_interval <- discretize(iris$Sepal.Length, method = "interval")
iris_frequency <- discretize(iris$Sepal.Length, method = "frequency")
iris_cluster <- discretize(iris$Sepal.Length, method = "cluster")
iris_fixed <- discretize(
iris$Sepal.Length,
method = "fixed",
breaks = c(4, 5, 6, 7, 8)
)
summary(iris_interval)
## [4.3,5.5) [5.5,6.7) [6.7,7.9]
## 52 70 28
summary(iris_frequency)
## [4.3,5.4) [5.4,6.3) [6.3,7.9]
## 46 53 51
summary(iris_cluster)
## [4.3,5.45) [5.45,6.46) [6.46,7.9]
## 52 63 35
summary(iris_fixed)
## [4,5) [5,6) [6,7) [7,8]
## 22 61 54 13
data(Ozone)
Ozone_clean <- na.omit(Ozone)
boruta_model <- Boruta(V4 ~ ., data = Ozone_clean, doTrace = 0)
print(boruta_model)
## Boruta performed 36 iterations in 2.558699 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;
plot(boruta_model, las = 2, cex.axis = 0.7)
# таблица с результатами Boruta
boruta_results <- attStats(boruta_model)
boruta_results
## meanImp medianImp minImp maxImp normHits decision
## V1 9.330545 9.4573766 7.9233050 10.8569753 1.0000000 Confirmed
## V2 1.353045 1.2073362 -0.5181567 3.0845808 0.2222222 Rejected
## V3 -1.115597 -0.9874573 -2.9621754 0.2235833 0.0000000 Rejected
## V5 9.134280 9.2492877 7.1816729 10.4347912 1.0000000 Confirmed
## V6 1.117300 1.2581279 -0.9597883 3.1884637 0.1111111 Rejected
## V7 11.787633 11.7825798 10.5397462 13.2236626 1.0000000 Confirmed
## V8 17.329456 17.3275796 15.5666970 18.5129163 1.0000000 Confirmed
## V9 19.214847 19.2771453 17.3575238 21.2105628 1.0000000 Confirmed
## V10 9.908052 9.7573976 8.3048395 11.3235846 1.0000000 Confirmed
## V11 12.001480 11.8594547 10.6373230 13.7060709 1.0000000 Confirmed
## V12 14.931959 14.9438983 13.5383314 16.1010344 1.0000000 Confirmed
## V13 9.653286 9.6274549 8.2468179 11.3099483 1.0000000 Confirmed