lab2
volkov 211-7212
2024-02-13
Задание 1
Установим пакет caret и выполним команду names(getModelInfo()), чтобы ознакомиться со списком доступных методов выбора признаков:
install.packages("caret", repos = "http://cran.us.r-project.org")## Устанавливаю пакет в 'C:/Users/Rostislav/AppData/Local/R/win-library/4.3'
## (потому что 'lib' не определено)## пакет 'caret' успешно распакован, MD5-суммы проверены
##
## Скачанные бинарные пакеты находятся в
## C:\Users\Rostislav\AppData\Local\Temp\Rtmp6rClbu\downloaded_packageslibrary(caret)## Загрузка требуемого пакета: ggplot2## Загрузка требуемого пакета: latticenames(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"Далее выполним графический разведочный анализ данных с использованием функции featurePlot() для набора данных x:
set.seed(123)
x <- matrix(rnorm(50*5),ncol=5)
y <- factor(rep(c("A", "B"), 25))
featurePlot(x, y, plot="box")
featurePlot(x, y, plot="density")
jpeg("boxplot.jpg")
featurePlot(x, y, plot="box")
dev.off()## png
## 2jpeg("density.jpg")
featurePlot(x, y, plot="density")
dev.off()## png
## 2Задание 2
Установим пакет FSelector и загрузим набор данных iris:
install.packages("FSelector", repos = "http://cran.us.r-project.org")## Устанавливаю пакет в 'C:/Users/Rostislav/AppData/Local/R/win-library/4.3'
## (потому что 'lib' не определено)## пакет 'FSelector' успешно распакован, MD5-суммы проверены
##
## Скачанные бинарные пакеты находятся в
## C:\Users\Rostislav\AppData\Local\Temp\Rtmp6rClbu\downloaded_packageslibrary(FSelector)## java.home option:## JAVA_HOME environment variable: C:\Program Files\Java\jdk-1.8## 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.data(iris)Для определения важности признаков для решения задачи классификации воспользуемся функцией information.gain():
gain <- information.gain(Species ~ ., iris)
print(gain)## attr_importance
## Sepal.Length 0.4521286
## Sepal.Width 0.2672750
## Petal.Length 0.9402853
## Petal.Width 0.9554360Результат выполнения этой команды покажет, какой признак имеет наибольшую информационную выгоду при решении задачи классификации.
Задание 3
Установим пакет arules:
install.packages("arules", repos = "http://cran.us.r-project.org")## Устанавливаю пакет в 'C:/Users/Rostislav/AppData/Local/R/win-library/4.3'
## (потому что 'lib' не определено)## пакет 'arules' успешно распакован, MD5-суммы проверены
##
## Скачанные бинарные пакеты находятся в
## C:\Users\Rostislav\AppData\Local\Temp\Rtmp6rClbu\downloaded_packageslibrary(arules)## Загрузка требуемого пакета: Matrix##
## Присоединяю пакет: 'arules'## Следующие объекты скрыты от 'package:base':
##
## abbreviate, writedata(iris)Преобразуем непрерывную переменную в категориальную различными методами:
iris_interval <- discretize(iris$Sepal.Length, method="interval", breaks=5)
iris_frequency <- discretize(iris$Sepal.Length, method="frequency", breaks=5)
iris_cluster <- discretize(iris$Sepal.Length, method="cluster", breaks=5)
iris_fixed <- discretize(iris$Sepal.Length, method="fixed", categories=c("0-4","4-6","6-8","8-10"))## Warning in discretize(iris$Sepal.Length, method = "fixed", categories =
## c("0-4", : Parameter categories is deprecated. Use breaks instead! Also, the
## default method is now frequency!## Warning in sort.int(as.double(breaks)): в результате преобразования созданы NAprint(iris_interval)## [1] [5.02,5.74) [4.3,5.02) [4.3,5.02) [4.3,5.02) [4.3,5.02) [5.02,5.74)
## [7] [4.3,5.02) [4.3,5.02) [4.3,5.02) [4.3,5.02) [5.02,5.74) [4.3,5.02)
## [13] [4.3,5.02) [4.3,5.02) [5.74,6.46) [5.02,5.74) [5.02,5.74) [5.02,5.74)
## [19] [5.02,5.74) [5.02,5.74) [5.02,5.74) [5.02,5.74) [4.3,5.02) [5.02,5.74)
## [25] [4.3,5.02) [4.3,5.02) [4.3,5.02) [5.02,5.74) [5.02,5.74) [4.3,5.02)
## [31] [4.3,5.02) [5.02,5.74) [5.02,5.74) [5.02,5.74) [4.3,5.02) [4.3,5.02)
## [37] [5.02,5.74) [4.3,5.02) [4.3,5.02) [5.02,5.74) [4.3,5.02) [4.3,5.02)
## [43] [4.3,5.02) [4.3,5.02) [5.02,5.74) [4.3,5.02) [5.02,5.74) [4.3,5.02)
## [49] [5.02,5.74) [4.3,5.02) [6.46,7.18) [5.74,6.46) [6.46,7.18) [5.02,5.74)
## [55] [6.46,7.18) [5.02,5.74) [5.74,6.46) [4.3,5.02) [6.46,7.18) [5.02,5.74)
## [61] [4.3,5.02) [5.74,6.46) [5.74,6.46) [5.74,6.46) [5.02,5.74) [6.46,7.18)
## [67] [5.02,5.74) [5.74,6.46) [5.74,6.46) [5.02,5.74) [5.74,6.46) [5.74,6.46)
## [73] [5.74,6.46) [5.74,6.46) [5.74,6.46) [6.46,7.18) [6.46,7.18) [6.46,7.18)
## [79] [5.74,6.46) [5.02,5.74) [5.02,5.74) [5.02,5.74) [5.74,6.46) [5.74,6.46)
## [85] [5.02,5.74) [5.74,6.46) [6.46,7.18) [5.74,6.46) [5.02,5.74) [5.02,5.74)
## [91] [5.02,5.74) [5.74,6.46) [5.74,6.46) [4.3,5.02) [5.02,5.74) [5.02,5.74)
## [97] [5.02,5.74) [5.74,6.46) [5.02,5.74) [5.02,5.74) [5.74,6.46) [5.74,6.46)
## [103] [6.46,7.18) [5.74,6.46) [6.46,7.18) [7.18,7.9] [4.3,5.02) [7.18,7.9]
## [109] [6.46,7.18) [7.18,7.9] [6.46,7.18) [5.74,6.46) [6.46,7.18) [5.02,5.74)
## [115] [5.74,6.46) [5.74,6.46) [6.46,7.18) [7.18,7.9] [7.18,7.9] [5.74,6.46)
## [121] [6.46,7.18) [5.02,5.74) [7.18,7.9] [5.74,6.46) [6.46,7.18) [7.18,7.9]
## [127] [5.74,6.46) [5.74,6.46) [5.74,6.46) [7.18,7.9] [7.18,7.9] [7.18,7.9]
## [133] [5.74,6.46) [5.74,6.46) [5.74,6.46) [7.18,7.9] [5.74,6.46) [5.74,6.46)
## [139] [5.74,6.46) [6.46,7.18) [6.46,7.18) [6.46,7.18) [5.74,6.46) [6.46,7.18)
## [145] [6.46,7.18) [6.46,7.18) [5.74,6.46) [6.46,7.18) [5.74,6.46) [5.74,6.46)
## attr(,"discretized:breaks")
## [1] 4.30 5.02 5.74 6.46 7.18 7.90
## attr(,"discretized:method")
## [1] interval
## Levels: [4.3,5.02) [5.02,5.74) [5.74,6.46) [6.46,7.18) [7.18,7.9]print(iris_frequency)## [1] [5,5.6) [4.3,5) [4.3,5) [4.3,5) [5,5.6) [5,5.6)
## [7] [4.3,5) [5,5.6) [4.3,5) [4.3,5) [5,5.6) [4.3,5)
## [13] [4.3,5) [4.3,5) [5.6,6.1) [5.6,6.1) [5,5.6) [5,5.6)
## [19] [5.6,6.1) [5,5.6) [5,5.6) [5,5.6) [4.3,5) [5,5.6)
## [25] [4.3,5) [5,5.6) [5,5.6) [5,5.6) [5,5.6) [4.3,5)
## [31] [4.3,5) [5,5.6) [5,5.6) [5,5.6) [4.3,5) [5,5.6)
## [37] [5,5.6) [4.3,5) [4.3,5) [5,5.6) [5,5.6) [4.3,5)
## [43] [4.3,5) [5,5.6) [5,5.6) [4.3,5) [5,5.6) [4.3,5)
## [49] [5,5.6) [5,5.6) [6.52,7.9] [6.1,6.52) [6.52,7.9] [5,5.6)
## [55] [6.1,6.52) [5.6,6.1) [6.1,6.52) [4.3,5) [6.52,7.9] [5,5.6)
## [61] [5,5.6) [5.6,6.1) [5.6,6.1) [6.1,6.52) [5.6,6.1) [6.52,7.9]
## [67] [5.6,6.1) [5.6,6.1) [6.1,6.52) [5.6,6.1) [5.6,6.1) [6.1,6.52)
## [73] [6.1,6.52) [6.1,6.52) [6.1,6.52) [6.52,7.9] [6.52,7.9] [6.52,7.9]
## [79] [5.6,6.1) [5.6,6.1) [5,5.6) [5,5.6) [5.6,6.1) [5.6,6.1)
## [85] [5,5.6) [5.6,6.1) [6.52,7.9] [6.1,6.52) [5.6,6.1) [5,5.6)
## [91] [5,5.6) [6.1,6.52) [5.6,6.1) [5,5.6) [5.6,6.1) [5.6,6.1)
## [97] [5.6,6.1) [6.1,6.52) [5,5.6) [5.6,6.1) [6.1,6.52) [5.6,6.1)
## [103] [6.52,7.9] [6.1,6.52) [6.1,6.52) [6.52,7.9] [4.3,5) [6.52,7.9]
## [109] [6.52,7.9] [6.52,7.9] [6.1,6.52) [6.1,6.52) [6.52,7.9] [5.6,6.1)
## [115] [5.6,6.1) [6.1,6.52) [6.1,6.52) [6.52,7.9] [6.52,7.9] [5.6,6.1)
## [121] [6.52,7.9] [5.6,6.1) [6.52,7.9] [6.1,6.52) [6.52,7.9] [6.52,7.9]
## [127] [6.1,6.52) [6.1,6.52) [6.1,6.52) [6.52,7.9] [6.52,7.9] [6.52,7.9]
## [133] [6.1,6.52) [6.1,6.52) [6.1,6.52) [6.52,7.9] [6.1,6.52) [6.1,6.52)
## [139] [5.6,6.1) [6.52,7.9] [6.52,7.9] [6.52,7.9] [5.6,6.1) [6.52,7.9]
## [145] [6.52,7.9] [6.52,7.9] [6.1,6.52) [6.1,6.52) [6.1,6.52) [5.6,6.1)
## attr(,"discretized:breaks")
## [1] 4.30 5.00 5.60 6.10 6.52 7.90
## attr(,"discretized:method")
## [1] frequency
## Levels: [4.3,5) [5,5.6) [5.6,6.1) [6.1,6.52) [6.52,7.9]print(iris_cluster)## [1] [4.77,5.32) [4.77,5.32) [4.3,4.77) [4.3,4.77) [4.77,5.32) [5.32,5.95)
## [7] [4.3,4.77) [4.77,5.32) [4.3,4.77) [4.77,5.32) [5.32,5.95) [4.77,5.32)
## [13] [4.77,5.32) [4.3,4.77) [5.32,5.95) [5.32,5.95) [5.32,5.95) [4.77,5.32)
## [19] [5.32,5.95) [4.77,5.32) [5.32,5.95) [4.77,5.32) [4.3,4.77) [4.77,5.32)
## [25] [4.77,5.32) [4.77,5.32) [4.77,5.32) [4.77,5.32) [4.77,5.32) [4.3,4.77)
## [31] [4.77,5.32) [5.32,5.95) [4.77,5.32) [5.32,5.95) [4.77,5.32) [4.77,5.32)
## [37] [5.32,5.95) [4.77,5.32) [4.3,4.77) [4.77,5.32) [4.77,5.32) [4.3,4.77)
## [43] [4.3,4.77) [4.77,5.32) [4.77,5.32) [4.77,5.32) [4.77,5.32) [4.3,4.77)
## [49] [4.77,5.32) [4.77,5.32) [6.68,7.9] [5.95,6.68) [6.68,7.9] [5.32,5.95)
## [55] [5.95,6.68) [5.32,5.95) [5.95,6.68) [4.77,5.32) [5.95,6.68) [4.77,5.32)
## [61] [4.77,5.32) [5.32,5.95) [5.95,6.68) [5.95,6.68) [5.32,5.95) [6.68,7.9]
## [67] [5.32,5.95) [5.32,5.95) [5.95,6.68) [5.32,5.95) [5.32,5.95) [5.95,6.68)
## [73] [5.95,6.68) [5.95,6.68) [5.95,6.68) [5.95,6.68) [6.68,7.9] [6.68,7.9]
## [79] [5.95,6.68) [5.32,5.95) [5.32,5.95) [5.32,5.95) [5.32,5.95) [5.95,6.68)
## [85] [5.32,5.95) [5.95,6.68) [6.68,7.9] [5.95,6.68) [5.32,5.95) [5.32,5.95)
## [91] [5.32,5.95) [5.95,6.68) [5.32,5.95) [4.77,5.32) [5.32,5.95) [5.32,5.95)
## [97] [5.32,5.95) [5.95,6.68) [4.77,5.32) [5.32,5.95) [5.95,6.68) [5.32,5.95)
## [103] [6.68,7.9] [5.95,6.68) [5.95,6.68) [6.68,7.9] [4.77,5.32) [6.68,7.9]
## [109] [6.68,7.9] [6.68,7.9] [5.95,6.68) [5.95,6.68) [6.68,7.9] [5.32,5.95)
## [115] [5.32,5.95) [5.95,6.68) [5.95,6.68) [6.68,7.9] [6.68,7.9] [5.95,6.68)
## [121] [6.68,7.9] [5.32,5.95) [6.68,7.9] [5.95,6.68) [6.68,7.9] [6.68,7.9]
## [127] [5.95,6.68) [5.95,6.68) [5.95,6.68) [6.68,7.9] [6.68,7.9] [6.68,7.9]
## [133] [5.95,6.68) [5.95,6.68) [5.95,6.68) [6.68,7.9] [5.95,6.68) [5.95,6.68)
## [139] [5.95,6.68) [6.68,7.9] [6.68,7.9] [6.68,7.9] [5.32,5.95) [6.68,7.9]
## [145] [6.68,7.9] [6.68,7.9] [5.95,6.68) [5.95,6.68) [5.95,6.68) [5.32,5.95)
## attr(,"discretized:breaks")
## [1] 4.300000 4.769351 5.321931 5.952114 6.676969 7.900000
## attr(,"discretized:method")
## [1] cluster
## Levels: [4.3,4.77) [4.77,5.32) [5.32,5.95) [5.95,6.68) [6.68,7.9]print(iris_fixed)## [1] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## [16] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## [31] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## [46] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## [61] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## [76] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## [91] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## [106] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## [121] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## [136] <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## attr(,"discretized:breaks")
## [1] 0-4 4-6 6-8 8-10
## attr(,"discretized:method")
## [1] fixed
## Levels: [,)Задание 4
Установим пакет Boruta и загрузим набор данных Ozone:
install.packages("Boruta", repos = "http://cran.us.r-project.org")## Устанавливаю пакет в 'C:/Users/Rostislav/AppData/Local/R/win-library/4.3'
## (потому что 'lib' не определено)## пакет 'Boruta' успешно распакован, MD5-суммы проверены
##
## Скачанные бинарные пакеты находятся в
## C:\Users\Rostislav\AppData\Local\Temp\Rtmp6rClbu\downloaded_packageslibrary(Boruta)
install.packages("mlbench", repos = "http://cran.us.r-project.org")## Устанавливаю пакет в 'C:/Users/Rostislav/AppData/Local/R/win-library/4.3'
## (потому что 'lib' не определено)## пакет 'mlbench' успешно распакован, MD5-суммы проверены## Warning: не могу удалить прежнюю установку пакета 'mlbench'## Warning in file.copy(savedcopy, lib, recursive = TRUE): проблема с копированием
## C:\Users\Rostislav\AppData\Local\R\win-library\4.3\00LOCK\mlbench\libs\x64\mlbench.dll
## в C:\Users\Rostislav\AppData\Local\R\win-library\4.3\mlbench\libs\x64\mlbench.dll:
## Permission denied## Warning: восстановлен 'mlbench'##
## Скачанные бинарные пакеты находятся в
## C:\Users\Rostislav\AppData\Local\Temp\Rtmp6rClbu\downloaded_packageslibrary(mlbench)
data("Ozone")Проведем выбор признаков для набора данных с помощью алгоритма Боруты:
set.seed(123)
Ozone <- na.omit(Ozone)
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, +0.41 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, +0.84 secs:## rejected 1 attribute: V2;## no more attributes left.print(boruta_result)## Boruta performed 24 iterations in 0.8431001 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;Строим график boxplot для выбранных признаков
selected_features <- getSelectedAttributes(boruta_result)
Ozone_selected <- Ozone[,c(selected_features, "V4")]
boxplot(Ozone_selected, main="Selected Features Boxplot")