R Markdown
library(caret)
## Загрузка требуемого пакета: ggplot2
## Загрузка требуемого пакета: lattice
library(Boruta)
library(arules)
## Загрузка требуемого пакета: Matrix
##
## Присоединяю пакет: 'arules'
## Следующие объекты скрыты от 'package:base':
##
## abbreviate, write
library(ggplot2)
library(rmarkdown)
library(mlbench)
library(caret)
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"
set.seed(123)
x <- matrix(rnorm(50 * 5), ncol = 5)
y <- factor(rep(c("A", "B"), 25))
data <- data.frame(x, Class = y)
featurePlot(x = data[, 1:5], y = data$Class, plot = "box")
featurePlot(x = data[, 1:5], y = data$Class, plot = "density")
featurePlot(x = data[, 1:5], y = data$Class, plot = "density")
library(arules)
iris$Sepal.Length_interval <- discretize(iris$Sepal.Length, method = "interval", breaks = 3)
iris$Sepal.Length_frequency <- discretize(iris$Sepal.Length, method = "frequency", breaks = 3)
iris$Sepal.Length_cluster <- discretize(iris$Sepal.Length, method = "cluster", breaks = 3)
iris$Sepal.Length_fixed <- discretize(iris$Sepal.Length, method = "fixed", breaks = c(4, 5.5, 6.5, 8))
head(iris[, c("Sepal.Length", "Sepal.Length_interval", "Sepal.Length_frequency", "Sepal.Length_cluster", "Sepal.Length_fixed")])
## Sepal.Length Sepal.Length_interval Sepal.Length_frequency
## 1 5.1 [4.3,5.5) [4.3,5.4)
## 2 4.9 [4.3,5.5) [4.3,5.4)
## 3 4.7 [4.3,5.5) [4.3,5.4)
## 4 4.6 [4.3,5.5) [4.3,5.4)
## 5 5.0 [4.3,5.5) [4.3,5.4)
## 6 5.4 [4.3,5.5) [5.4,6.3)
## Sepal.Length_cluster Sepal.Length_fixed
## 1 [4.3,5.33) [4,5.5)
## 2 [4.3,5.33) [4,5.5)
## 3 [4.3,5.33) [4,5.5)
## 4 [4.3,5.33) [4,5.5)
## 5 [4.3,5.33) [4,5.5)
## 6 [5.33,6.27) [4,5.5)
install.packages("mlbench")
## Warning: пакет ''mlbench'' сейчас используется и не будет установлен
library(mlbench)
data("Ozone")
Ozone <- na.omit(Ozone)
set.seed(123)
library(Boruta)
boruta_result <- Boruta(V4 ~ ., 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, +0.87 secs:
## confirmed 9 attributes: V1, V10, V11, V12, V13 and 4 more;
## rejected 2 attributes: V3, V6;
## still have 1 attribute 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...
## 22. run of importance source...
## 23. run of importance source...
## 24. run of importance source...
## After 24 iterations, +1.8 secs:
## rejected 1 attribute: V2;
## no more attributes left.
print(boruta_result)
## Boruta performed 24 iterations in 1.7568 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;
plot(boruta_result)
boxplot(boruta_result$ImpHistory, las = 2, main = "Boruta Feature Importance")
