lab2 AD
Ilya Dmitriev 211-723
2024-11-17
Задание 1
Установить пакет CARET, выполнить команду names(getModelInfo()), ознакомиться со списком доступных методов выбора признаков. Выполните графический разведочный анализ данных с использование функции featurePlot() для набора данных из справочного файла пакета CARET:
x <- matrix(rnorm(50*5),ncol=5)
y <- factor(rep(c(“A”, “B”), 25))
Сохранить полученные графики в *.jpg файлы. Сделать выводы.
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"x <- matrix(rnorm(50*5), ncol = 5)
y <- factor(rep(c("A", "B"), 25))
head(x)## [,1] [,2] [,3] [,4] [,5]
## [1,] -0.2913593 -0.7984708 0.6207537 0.3070331 -0.3745338
## [2,] 0.4683149 -0.4113322 1.3728651 -0.7939952 -1.1779494
## [3,] 0.4872370 0.6087493 0.3948069 0.9829658 1.4797188
## [4,] 0.9254749 0.6443967 0.2466801 -0.2688505 -0.6016650
## [5,] -0.1731256 1.5850139 0.3846899 -1.0466754 0.2371880
## [6,] 1.3485787 0.6907507 -0.5163391 0.2525980 -1.8201824head(y)## [1] A B A B A B
## Levels: A BГрафики
Вывод
Вывод: Плотностные графики для всех признаков показывают, что данные генерируются с нормальным распределением, что неудивительно, учитывая использование функции rnorm(). Так как данные были сгенерированы случайным образом, различие между классами A и B незначительно или вовсе отсутствует. Это видно по сильному перекрытию распределений для всех признаков.
Задача 2
С использование функций из пакета Fselector [2] определить важность признаков для решения задачи классификации. Использовать набор data(iris). Сделать выводы.
data(iris)
gain <- information.gain(Species ~ ., data = iris)
print(gain)## attr_importance
## Sepal.Length 0.4521286
## Sepal.Width 0.2672750
## Petal.Length 0.9402853
## Petal.Width 0.9554360Вывод
Вывод: бесполезные -sepal.len/sepal.width Остальные - полезные
Задание 3
С использованием функции discretize() из пакета arules выполните преобразование непрерывной переменной в категориальную [3] различными методами: «interval» (равная ширина интервала), «frequency» (равная частота), «cluster» (кластеризация) и «fixed» (категории задают границы интервалов). Используйте набор данных iris. Сделайте выводы
fixed
breaks <- seq(from = 0, to = 10, by = 1)
percents <- discretize(iris[,1], method = "fixed", breaks=breaks)
percents## [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]interval
breaks <- seq(from = 0, to = 10, by = 1)
percents <- discretize(iris[,1], method = "interval", breaks=10)
percents## [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]frequency
breaks <- seq(from = 0, to = 10, by = 1)
percents <- discretize(iris[,1], method = "frequency", breaks=10)
percents## [1] [5,5.27) [4.8,5) [4.3,4.8) [4.3,4.8) [5,5.27) [5.27,5.6)
## [7] [4.3,4.8) [5,5.27) [4.3,4.8) [4.8,5) [5.27,5.6) [4.8,5)
## [13] [4.8,5) [4.3,4.8) [5.8,6.1) [5.6,5.8) [5.27,5.6) [5,5.27)
## [19] [5.6,5.8) [5,5.27) [5.27,5.6) [5,5.27) [4.3,4.8) [5,5.27)
## [25] [4.8,5) [5,5.27) [5,5.27) [5,5.27) [5,5.27) [4.3,4.8)
## [31] [4.8,5) [5.27,5.6) [5,5.27) [5.27,5.6) [4.8,5) [5,5.27)
## [37] [5.27,5.6) [4.8,5) [4.3,4.8) [5,5.27) [5,5.27) [4.3,4.8)
## [43] [4.3,4.8) [5,5.27) [5,5.27) [4.8,5) [5,5.27) [4.3,4.8)
## [49] [5.27,5.6) [5,5.27) [6.9,7.9] [6.3,6.52) [6.9,7.9] [5.27,5.6)
## [55] [6.3,6.52) [5.6,5.8) [6.3,6.52) [4.8,5) [6.52,6.9) [5,5.27)
## [61] [5,5.27) [5.8,6.1) [5.8,6.1) [6.1,6.3) [5.6,5.8) [6.52,6.9)
## [67] [5.6,5.8) [5.8,6.1) [6.1,6.3) [5.6,5.8) [5.8,6.1) [6.1,6.3)
## [73] [6.3,6.52) [6.1,6.3) [6.3,6.52) [6.52,6.9) [6.52,6.9) [6.52,6.9)
## [79] [5.8,6.1) [5.6,5.8) [5.27,5.6) [5.27,5.6) [5.8,6.1) [5.8,6.1)
## [85] [5.27,5.6) [5.8,6.1) [6.52,6.9) [6.3,6.52) [5.6,5.8) [5.27,5.6)
## [91] [5.27,5.6) [6.1,6.3) [5.8,6.1) [5,5.27) [5.6,5.8) [5.6,5.8)
## [97] [5.6,5.8) [6.1,6.3) [5,5.27) [5.6,5.8) [6.3,6.52) [5.8,6.1)
## [103] [6.9,7.9] [6.3,6.52) [6.3,6.52) [6.9,7.9] [4.8,5) [6.9,7.9]
## [109] [6.52,6.9) [6.9,7.9] [6.3,6.52) [6.3,6.52) [6.52,6.9) [5.6,5.8)
## [115] [5.8,6.1) [6.3,6.52) [6.3,6.52) [6.9,7.9] [6.9,7.9] [5.8,6.1)
## [121] [6.9,7.9] [5.6,5.8) [6.9,7.9] [6.3,6.52) [6.52,6.9) [6.9,7.9]
## [127] [6.1,6.3) [6.1,6.3) [6.3,6.52) [6.9,7.9] [6.9,7.9] [6.9,7.9]
## [133] [6.3,6.52) [6.3,6.52) [6.1,6.3) [6.9,7.9] [6.3,6.52) [6.3,6.52)
## [139] [5.8,6.1) [6.9,7.9] [6.52,6.9) [6.9,7.9] [5.8,6.1) [6.52,6.9)
## [145] [6.52,6.9) [6.52,6.9) [6.3,6.52) [6.3,6.52) [6.1,6.3) [5.8,6.1)
## attr(,"discretized:breaks")
## [1] 4.30 4.80 5.00 5.27 5.60 5.80 6.10 6.30 6.52 6.90 7.90
## attr(,"discretized:method")
## [1] frequency
## 10 Levels: [4.3,4.8) [4.8,5) [5,5.27) [5.27,5.6) [5.6,5.8) ... [6.9,7.9]cluster
breaks <- seq(from = 0, to = 10, by = 1)
percents <- discretize(iris[,1], method = "cluster", breaks=10)
percents## [1] [5.03,5.32) [4.73,5.03) [4.3,4.73) [4.3,4.73) [4.73,5.03) [5.32,5.66)
## [7] [4.3,4.73) [4.73,5.03) [4.3,4.73) [4.73,5.03) [5.32,5.66) [4.73,5.03)
## [13] [4.73,5.03) [4.3,4.73) [5.66,6.05) [5.66,6.05) [5.32,5.66) [5.03,5.32)
## [19] [5.66,6.05) [5.03,5.32) [5.32,5.66) [5.03,5.32) [4.3,4.73) [5.03,5.32)
## [25] [4.73,5.03) [4.73,5.03) [4.73,5.03) [5.03,5.32) [5.03,5.32) [4.3,4.73)
## [31] [4.73,5.03) [5.32,5.66) [5.03,5.32) [5.32,5.66) [4.73,5.03) [4.73,5.03)
## [37] [5.32,5.66) [4.73,5.03) [4.3,4.73) [5.03,5.32) [4.73,5.03) [4.3,4.73)
## [43] [4.3,4.73) [4.73,5.03) [5.03,5.32) [4.73,5.03) [5.03,5.32) [4.3,4.73)
## [49] [5.03,5.32) [4.73,5.03) [6.75,7.05) [6.05,6.44) [6.75,7.05) [5.32,5.66)
## [55] [6.44,6.75) [5.66,6.05) [6.05,6.44) [4.73,5.03) [6.44,6.75) [5.03,5.32)
## [61] [4.73,5.03) [5.66,6.05) [5.66,6.05) [6.05,6.44) [5.32,5.66) [6.44,6.75)
## [67] [5.32,5.66) [5.66,6.05) [6.05,6.44) [5.32,5.66) [5.66,6.05) [6.05,6.44)
## [73] [6.05,6.44) [6.05,6.44) [6.05,6.44) [6.44,6.75) [6.75,7.05) [6.44,6.75)
## [79] [5.66,6.05) [5.66,6.05) [5.32,5.66) [5.32,5.66) [5.66,6.05) [5.66,6.05)
## [85] [5.32,5.66) [5.66,6.05) [6.44,6.75) [6.05,6.44) [5.32,5.66) [5.32,5.66)
## [91] [5.32,5.66) [6.05,6.44) [5.66,6.05) [4.73,5.03) [5.32,5.66) [5.66,6.05)
## [97] [5.66,6.05) [6.05,6.44) [5.03,5.32) [5.66,6.05) [6.05,6.44) [5.66,6.05)
## [103] [7.05,7.48) [6.05,6.44) [6.44,6.75) [7.48,7.9] [4.73,5.03) [7.05,7.48)
## [109] [6.44,6.75) [7.05,7.48) [6.44,6.75) [6.05,6.44) [6.75,7.05) [5.66,6.05)
## [115] [5.66,6.05) [6.05,6.44) [6.44,6.75) [7.48,7.9] [7.48,7.9] [5.66,6.05)
## [121] [6.75,7.05) [5.32,5.66) [7.48,7.9] [6.05,6.44) [6.44,6.75) [7.05,7.48)
## [127] [6.05,6.44) [6.05,6.44) [6.05,6.44) [7.05,7.48) [7.05,7.48) [7.48,7.9]
## [133] [6.05,6.44) [6.05,6.44) [6.05,6.44) [7.48,7.9] [6.05,6.44) [6.05,6.44)
## [139] [5.66,6.05) [6.75,7.05) [6.44,6.75) [6.75,7.05) [5.66,6.05) [6.75,7.05)
## [145] [6.44,6.75) [6.44,6.75) [6.05,6.44) [6.44,6.75) [6.05,6.44) [5.66,6.05)
## attr(,"discretized:breaks")
## [1] 4.300000 4.725541 5.033333 5.321429 5.664583 6.047276 6.442692 6.747500
## [9] 7.054167 7.475000 7.900000
## attr(,"discretized:method")
## [1] cluster
## 10 Levels: [4.3,4.73) [4.73,5.03) [5.03,5.32) [5.32,5.66) ... [7.48,7.9]Вывод
Вывод: Каждый метод предлагает различные разбиения на интервалы
Задание 4
Всю представленную работу собрать в единый файл Rmarkdown. Опубликовать его на RPubs, в качестве отчета о лабораторной работе представить ссылку на полученный файл.
if(!require(Boruta)) {
install.packages("Boruta")
library(Boruta)
}## Загрузка требуемого пакета: Boruta## Загрузка требуемого пакета: Boruta
if(!require(mlbench)) {
install.packages("mlbench")
library(mlbench)
}## Загрузка требуемого пакета: mlbench## Загрузка требуемого пакета: mlbench
data(Ozone)
Ozone <- na.omit(Ozone)
head(Ozone)## V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13
## 5 1 5 1 5 5760 3 51 54 45.32 1450 25 57.02 60
## 6 1 6 2 6 5720 4 69 35 49.64 1568 15 53.78 60
## 7 1 7 3 4 5790 6 19 45 46.40 2631 -33 54.14 100
## 8 1 8 4 4 5790 3 25 55 52.70 554 -28 64.76 250
## 9 1 9 5 6 5700 3 73 41 48.02 2083 23 52.52 120
## 12 1 12 1 6 5720 3 44 51 54.32 111 9 63.14 150boruta_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, +0.43 secs:## confirmed 9 attributes: V1, V10, V11, V12, V13 and 4 more;## rejected 1 attribute: V3;## still have 2 attributes left.## 12. run of importance source...## 13. run of importance source...## 14. run of importance source...## 15. run of importance source...## After 15 iterations, +0.58 secs:## rejected 1 attribute: V2;## still have 1 attribute left.## 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...## After 21 iterations, +0.8 secs:## rejected 1 attribute: V6;## no more attributes left.print(boruta_result)## Boruta performed 21 iterations in 0.8051319 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;important_vars <- getSelectedAttributes(boruta_result, withTentative = TRUE)
boxplot(Ozone[, important_vars], main = "Selected Features Boxplot", las = 2, col = "lightblue")
Вывод
Вывод: На 4 признак больше всего влияют признаки: v9, v8, v12, v11, v7, v10, v13, v1, v5. Значения 5го признака значительно выше значений остальных. 10й признак имеет большой разброс.