lab2
Dezzzmond
2025-01-09
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:
Устанавливаем пакет caret
if(!require(caret))
{
install.packages("caret")
library(caret)
}## Загрузка требуемого пакета: caret## Загрузка требуемого пакета: ggplot2## Загрузка требуемого пакета: latticeОтображаем список 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"Генерируем данные
x <- matrix(rnorm(50*5), ncol = 5)
y <- factor(rep(c("A", "B"), 25))
head(x)## [,1] [,2] [,3] [,4] [,5]
## [1,] 1.0366083 0.8278346 0.3491889 -0.9013591 1.1550878
## [2,] 1.2050843 0.8770722 -1.0615512 1.3692724 -1.8927438
## [3,] -1.6046110 -1.0601709 1.0693973 0.3977903 -0.5249970
## [4,] 0.2191387 -0.9584352 -0.2287909 0.7383253 0.9840672
## [5,] 0.9809709 -2.3513764 -1.4742715 -0.6477671 1.5500128
## [6,] -0.3032803 -0.1480190 0.3401708 -1.3347801 -0.7332655head(y)## [1] A B A B A B
## Levels: A BРисуем графики
featurePlot(x, y, plot = "density")
featurePlot(x, y, plot = "box")
featurePlot(x, y, plot = "pairs")
featurePlot(x, y, plot = "strip")
Сохраняем графики в файлы
jpeg("plot_density.jpg")
featurePlot(x, y, plot = "density")jpeg("plot_box.jpg")
featurePlot(x, y, plot = "box")jpeg("plot_pairs.jpg")
featurePlot(x, y, plot = "pairs")jpeg("plot_strip.jpg")
featurePlot(x, y, plot = "strip")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 (V1–V5).
Задание 2
С использование функций из пакета Fselector [2] определить важность признаков для решения задачи классификации. Использовать набор data(iris). Сделать выводы.
Устанавливаем пакет FSelector
if(!require(FSelector)) {
install.packages("FSelector")
library(FSelector)
}## Загрузка требуемого пакета: FSelectorЗагружаем данные
data(iris)Вычисляем информационную ценность каждого признака
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
Признаки Petal.Length и Petal.Width являются более значимыми
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 Устанавливаем пакет arules
Устанавливаем пакет Arules
if(!require(arules)) {
install.packages("arules")
library(arules)
}## Загрузка требуемого пакета: arules## Загрузка требуемого пакета: Matrix##
## Присоединяю пакет: 'arules'## Следующие объекты скрыты от 'package:base':
##
## abbreviate, writeЗагружаем данные
data(iris)Дискретизация и просмотр результатов # Method 1: interval
iris$Petal.Length.interval <- discretize(iris$Petal.Length, method = "interval")
# Method 2: frequency
iris$Petal.Length.frequency <- discretize(iris$Petal.Length, method = "frequency")
# Method 3: cluster
iris$Petal.Length.cluster <- discretize(iris$Petal.Length, method = "cluster")
# Method 4: fixed
iris$Petal.Length.fixed <- discretize(iris$Petal.Length, method = "fixed", c(0, 2, 4, 6, 8))
# Просмотр результатов
print(iris[, c("Petal.Length", "Petal.Length.interval", "Petal.Length.frequency", "Petal.Length.cluster", "Petal.Length.fixed")])## Petal.Length Petal.Length.interval Petal.Length.frequency
## 1 1.4 [1,2.97) [1,2.63)
## 2 1.4 [1,2.97) [1,2.63)
## 3 1.3 [1,2.97) [1,2.63)
## 4 1.5 [1,2.97) [1,2.63)
## 5 1.4 [1,2.97) [1,2.63)
## 6 1.7 [1,2.97) [1,2.63)
## 7 1.4 [1,2.97) [1,2.63)
## 8 1.5 [1,2.97) [1,2.63)
## 9 1.4 [1,2.97) [1,2.63)
## 10 1.5 [1,2.97) [1,2.63)
## 11 1.5 [1,2.97) [1,2.63)
## 12 1.6 [1,2.97) [1,2.63)
## 13 1.4 [1,2.97) [1,2.63)
## 14 1.1 [1,2.97) [1,2.63)
## 15 1.2 [1,2.97) [1,2.63)
## 16 1.5 [1,2.97) [1,2.63)
## 17 1.3 [1,2.97) [1,2.63)
## 18 1.4 [1,2.97) [1,2.63)
## 19 1.7 [1,2.97) [1,2.63)
## 20 1.5 [1,2.97) [1,2.63)
## 21 1.7 [1,2.97) [1,2.63)
## 22 1.5 [1,2.97) [1,2.63)
## 23 1.0 [1,2.97) [1,2.63)
## 24 1.7 [1,2.97) [1,2.63)
## 25 1.9 [1,2.97) [1,2.63)
## 26 1.6 [1,2.97) [1,2.63)
## 27 1.6 [1,2.97) [1,2.63)
## 28 1.5 [1,2.97) [1,2.63)
## 29 1.4 [1,2.97) [1,2.63)
## 30 1.6 [1,2.97) [1,2.63)
## 31 1.6 [1,2.97) [1,2.63)
## 32 1.5 [1,2.97) [1,2.63)
## 33 1.5 [1,2.97) [1,2.63)
## 34 1.4 [1,2.97) [1,2.63)
## 35 1.5 [1,2.97) [1,2.63)
## 36 1.2 [1,2.97) [1,2.63)
## 37 1.3 [1,2.97) [1,2.63)
## 38 1.4 [1,2.97) [1,2.63)
## 39 1.3 [1,2.97) [1,2.63)
## 40 1.5 [1,2.97) [1,2.63)
## 41 1.3 [1,2.97) [1,2.63)
## 42 1.3 [1,2.97) [1,2.63)
## 43 1.3 [1,2.97) [1,2.63)
## 44 1.6 [1,2.97) [1,2.63)
## 45 1.9 [1,2.97) [1,2.63)
## 46 1.4 [1,2.97) [1,2.63)
## 47 1.6 [1,2.97) [1,2.63)
## 48 1.4 [1,2.97) [1,2.63)
## 49 1.5 [1,2.97) [1,2.63)
## 50 1.4 [1,2.97) [1,2.63)
## 51 4.7 [2.97,4.93) [2.63,4.9)
## 52 4.5 [2.97,4.93) [2.63,4.9)
## 53 4.9 [2.97,4.93) [4.9,6.9]
## 54 4.0 [2.97,4.93) [2.63,4.9)
## 55 4.6 [2.97,4.93) [2.63,4.9)
## 56 4.5 [2.97,4.93) [2.63,4.9)
## 57 4.7 [2.97,4.93) [2.63,4.9)
## 58 3.3 [2.97,4.93) [2.63,4.9)
## 59 4.6 [2.97,4.93) [2.63,4.9)
## 60 3.9 [2.97,4.93) [2.63,4.9)
## 61 3.5 [2.97,4.93) [2.63,4.9)
## 62 4.2 [2.97,4.93) [2.63,4.9)
## 63 4.0 [2.97,4.93) [2.63,4.9)
## 64 4.7 [2.97,4.93) [2.63,4.9)
## 65 3.6 [2.97,4.93) [2.63,4.9)
## 66 4.4 [2.97,4.93) [2.63,4.9)
## 67 4.5 [2.97,4.93) [2.63,4.9)
## 68 4.1 [2.97,4.93) [2.63,4.9)
## 69 4.5 [2.97,4.93) [2.63,4.9)
## 70 3.9 [2.97,4.93) [2.63,4.9)
## 71 4.8 [2.97,4.93) [2.63,4.9)
## 72 4.0 [2.97,4.93) [2.63,4.9)
## 73 4.9 [2.97,4.93) [4.9,6.9]
## 74 4.7 [2.97,4.93) [2.63,4.9)
## 75 4.3 [2.97,4.93) [2.63,4.9)
## 76 4.4 [2.97,4.93) [2.63,4.9)
## 77 4.8 [2.97,4.93) [2.63,4.9)
## 78 5.0 [4.93,6.9] [4.9,6.9]
## 79 4.5 [2.97,4.93) [2.63,4.9)
## 80 3.5 [2.97,4.93) [2.63,4.9)
## 81 3.8 [2.97,4.93) [2.63,4.9)
## 82 3.7 [2.97,4.93) [2.63,4.9)
## 83 3.9 [2.97,4.93) [2.63,4.9)
## 84 5.1 [4.93,6.9] [4.9,6.9]
## 85 4.5 [2.97,4.93) [2.63,4.9)
## 86 4.5 [2.97,4.93) [2.63,4.9)
## 87 4.7 [2.97,4.93) [2.63,4.9)
## 88 4.4 [2.97,4.93) [2.63,4.9)
## 89 4.1 [2.97,4.93) [2.63,4.9)
## 90 4.0 [2.97,4.93) [2.63,4.9)
## 91 4.4 [2.97,4.93) [2.63,4.9)
## 92 4.6 [2.97,4.93) [2.63,4.9)
## 93 4.0 [2.97,4.93) [2.63,4.9)
## 94 3.3 [2.97,4.93) [2.63,4.9)
## 95 4.2 [2.97,4.93) [2.63,4.9)
## 96 4.2 [2.97,4.93) [2.63,4.9)
## 97 4.2 [2.97,4.93) [2.63,4.9)
## 98 4.3 [2.97,4.93) [2.63,4.9)
## 99 3.0 [2.97,4.93) [2.63,4.9)
## 100 4.1 [2.97,4.93) [2.63,4.9)
## 101 6.0 [4.93,6.9] [4.9,6.9]
## 102 5.1 [4.93,6.9] [4.9,6.9]
## 103 5.9 [4.93,6.9] [4.9,6.9]
## 104 5.6 [4.93,6.9] [4.9,6.9]
## 105 5.8 [4.93,6.9] [4.9,6.9]
## 106 6.6 [4.93,6.9] [4.9,6.9]
## 107 4.5 [2.97,4.93) [2.63,4.9)
## 108 6.3 [4.93,6.9] [4.9,6.9]
## 109 5.8 [4.93,6.9] [4.9,6.9]
## 110 6.1 [4.93,6.9] [4.9,6.9]
## 111 5.1 [4.93,6.9] [4.9,6.9]
## 112 5.3 [4.93,6.9] [4.9,6.9]
## 113 5.5 [4.93,6.9] [4.9,6.9]
## 114 5.0 [4.93,6.9] [4.9,6.9]
## 115 5.1 [4.93,6.9] [4.9,6.9]
## 116 5.3 [4.93,6.9] [4.9,6.9]
## 117 5.5 [4.93,6.9] [4.9,6.9]
## 118 6.7 [4.93,6.9] [4.9,6.9]
## 119 6.9 [4.93,6.9] [4.9,6.9]
## 120 5.0 [4.93,6.9] [4.9,6.9]
## 121 5.7 [4.93,6.9] [4.9,6.9]
## 122 4.9 [2.97,4.93) [4.9,6.9]
## 123 6.7 [4.93,6.9] [4.9,6.9]
## 124 4.9 [2.97,4.93) [4.9,6.9]
## 125 5.7 [4.93,6.9] [4.9,6.9]
## 126 6.0 [4.93,6.9] [4.9,6.9]
## 127 4.8 [2.97,4.93) [2.63,4.9)
## 128 4.9 [2.97,4.93) [4.9,6.9]
## 129 5.6 [4.93,6.9] [4.9,6.9]
## 130 5.8 [4.93,6.9] [4.9,6.9]
## 131 6.1 [4.93,6.9] [4.9,6.9]
## 132 6.4 [4.93,6.9] [4.9,6.9]
## 133 5.6 [4.93,6.9] [4.9,6.9]
## 134 5.1 [4.93,6.9] [4.9,6.9]
## 135 5.6 [4.93,6.9] [4.9,6.9]
## 136 6.1 [4.93,6.9] [4.9,6.9]
## 137 5.6 [4.93,6.9] [4.9,6.9]
## 138 5.5 [4.93,6.9] [4.9,6.9]
## 139 4.8 [2.97,4.93) [2.63,4.9)
## 140 5.4 [4.93,6.9] [4.9,6.9]
## 141 5.6 [4.93,6.9] [4.9,6.9]
## 142 5.1 [4.93,6.9] [4.9,6.9]
## 143 5.1 [4.93,6.9] [4.9,6.9]
## 144 5.9 [4.93,6.9] [4.9,6.9]
## 145 5.7 [4.93,6.9] [4.9,6.9]
## 146 5.2 [4.93,6.9] [4.9,6.9]
## 147 5.0 [4.93,6.9] [4.9,6.9]
## 148 5.2 [4.93,6.9] [4.9,6.9]
## 149 5.4 [4.93,6.9] [4.9,6.9]
## 150 5.1 [4.93,6.9] [4.9,6.9]
## Petal.Length.cluster Petal.Length.fixed
## 1 [1,2.95) [0,2)
## 2 [1,2.95) [0,2)
## 3 [1,2.95) [0,2)
## 4 [1,2.95) [0,2)
## 5 [1,2.95) [0,2)
## 6 [1,2.95) [0,2)
## 7 [1,2.95) [0,2)
## 8 [1,2.95) [0,2)
## 9 [1,2.95) [0,2)
## 10 [1,2.95) [0,2)
## 11 [1,2.95) [0,2)
## 12 [1,2.95) [0,2)
## 13 [1,2.95) [0,2)
## 14 [1,2.95) [0,2)
## 15 [1,2.95) [0,2)
## 16 [1,2.95) [0,2)
## 17 [1,2.95) [0,2)
## 18 [1,2.95) [0,2)
## 19 [1,2.95) [0,2)
## 20 [1,2.95) [0,2)
## 21 [1,2.95) [0,2)
## 22 [1,2.95) [0,2)
## 23 [1,2.95) [0,2)
## 24 [1,2.95) [0,2)
## 25 [1,2.95) [0,2)
## 26 [1,2.95) [0,2)
## 27 [1,2.95) [0,2)
## 28 [1,2.95) [0,2)
## 29 [1,2.95) [0,2)
## 30 [1,2.95) [0,2)
## 31 [1,2.95) [0,2)
## 32 [1,2.95) [0,2)
## 33 [1,2.95) [0,2)
## 34 [1,2.95) [0,2)
## 35 [1,2.95) [0,2)
## 36 [1,2.95) [0,2)
## 37 [1,2.95) [0,2)
## 38 [1,2.95) [0,2)
## 39 [1,2.95) [0,2)
## 40 [1,2.95) [0,2)
## 41 [1,2.95) [0,2)
## 42 [1,2.95) [0,2)
## 43 [1,2.95) [0,2)
## 44 [1,2.95) [0,2)
## 45 [1,2.95) [0,2)
## 46 [1,2.95) [0,2)
## 47 [1,2.95) [0,2)
## 48 [1,2.95) [0,2)
## 49 [1,2.95) [0,2)
## 50 [1,2.95) [0,2)
## 51 [2.95,5.13) [4,6)
## 52 [2.95,5.13) [4,6)
## 53 [2.95,5.13) [4,6)
## 54 [2.95,5.13) [4,6)
## 55 [2.95,5.13) [4,6)
## 56 [2.95,5.13) [4,6)
## 57 [2.95,5.13) [4,6)
## 58 [2.95,5.13) [2,4)
## 59 [2.95,5.13) [4,6)
## 60 [2.95,5.13) [2,4)
## 61 [2.95,5.13) [2,4)
## 62 [2.95,5.13) [4,6)
## 63 [2.95,5.13) [4,6)
## 64 [2.95,5.13) [4,6)
## 65 [2.95,5.13) [2,4)
## 66 [2.95,5.13) [4,6)
## 67 [2.95,5.13) [4,6)
## 68 [2.95,5.13) [4,6)
## 69 [2.95,5.13) [4,6)
## 70 [2.95,5.13) [2,4)
## 71 [2.95,5.13) [4,6)
## 72 [2.95,5.13) [4,6)
## 73 [2.95,5.13) [4,6)
## 74 [2.95,5.13) [4,6)
## 75 [2.95,5.13) [4,6)
## 76 [2.95,5.13) [4,6)
## 77 [2.95,5.13) [4,6)
## 78 [2.95,5.13) [4,6)
## 79 [2.95,5.13) [4,6)
## 80 [2.95,5.13) [2,4)
## 81 [2.95,5.13) [2,4)
## 82 [2.95,5.13) [2,4)
## 83 [2.95,5.13) [2,4)
## 84 [2.95,5.13) [4,6)
## 85 [2.95,5.13) [4,6)
## 86 [2.95,5.13) [4,6)
## 87 [2.95,5.13) [4,6)
## 88 [2.95,5.13) [4,6)
## 89 [2.95,5.13) [4,6)
## 90 [2.95,5.13) [4,6)
## 91 [2.95,5.13) [4,6)
## 92 [2.95,5.13) [4,6)
## 93 [2.95,5.13) [4,6)
## 94 [2.95,5.13) [2,4)
## 95 [2.95,5.13) [4,6)
## 96 [2.95,5.13) [4,6)
## 97 [2.95,5.13) [4,6)
## 98 [2.95,5.13) [4,6)
## 99 [2.95,5.13) [2,4)
## 100 [2.95,5.13) [4,6)
## 101 [5.13,6.9] [6,8]
## 102 [2.95,5.13) [4,6)
## 103 [5.13,6.9] [4,6)
## 104 [5.13,6.9] [4,6)
## 105 [5.13,6.9] [4,6)
## 106 [5.13,6.9] [6,8]
## 107 [2.95,5.13) [4,6)
## 108 [5.13,6.9] [6,8]
## 109 [5.13,6.9] [4,6)
## 110 [5.13,6.9] [6,8]
## 111 [2.95,5.13) [4,6)
## 112 [5.13,6.9] [4,6)
## 113 [5.13,6.9] [4,6)
## 114 [2.95,5.13) [4,6)
## 115 [2.95,5.13) [4,6)
## 116 [5.13,6.9] [4,6)
## 117 [5.13,6.9] [4,6)
## 118 [5.13,6.9] [6,8]
## 119 [5.13,6.9] [6,8]
## 120 [2.95,5.13) [4,6)
## 121 [5.13,6.9] [4,6)
## 122 [2.95,5.13) [4,6)
## 123 [5.13,6.9] [6,8]
## 124 [2.95,5.13) [4,6)
## 125 [5.13,6.9] [4,6)
## 126 [5.13,6.9] [6,8]
## 127 [2.95,5.13) [4,6)
## 128 [2.95,5.13) [4,6)
## 129 [5.13,6.9] [4,6)
## 130 [5.13,6.9] [4,6)
## 131 [5.13,6.9] [6,8]
## 132 [5.13,6.9] [6,8]
## 133 [5.13,6.9] [4,6)
## 134 [2.95,5.13) [4,6)
## 135 [5.13,6.9] [4,6)
## 136 [5.13,6.9] [6,8]
## 137 [5.13,6.9] [4,6)
## 138 [5.13,6.9] [4,6)
## 139 [2.95,5.13) [4,6)
## 140 [5.13,6.9] [4,6)
## 141 [5.13,6.9] [4,6)
## 142 [2.95,5.13) [4,6)
## 143 [2.95,5.13) [4,6)
## 144 [5.13,6.9] [4,6)
## 145 [5.13,6.9] [4,6)
## 146 [5.13,6.9] [4,6)
## 147 [2.95,5.13) [4,6)
## 148 [5.13,6.9] [4,6)
## 149 [5.13,6.9] [4,6)
## 150 [2.95,5.13) [4,6)Вывод
Каждый из методов разбивает непрерывную переменную на интервалы, но делает это по-разному.
Задание 4
Установите пакет Boruta и проведите выбор признаков для набора данных data(“Ozone”) [4, 5, 6]. Построить график boxplot, сделать выводы. Устанавливаем пакеты Boruta и mlbench
Устанавливаем пакет Boruta
if(!require(Boruta)) {
install.packages("Boruta")
library(Boruta)
}## Загрузка требуемого пакета: BorutaУстанавливаем пакет mlbench
if(!require(mlbench)) {
install.packages("mlbench")
library(mlbench)
}## Загрузка требуемого пакета: mlbenchПодготавливаем данные
data(Ozone)
Ozone <- na.omit(Ozone)
head(Ozone)Ищем важные признаки для 4го признака
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, +0.63 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...## 16. run of importance source...## 17. run of importance source...## 18. run of importance source...## After 18 iterations, +1 secs:## rejected 1 attribute: V2;## still have 1 attribute left.## 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...## 25. run of importance source...## 26. run of importance source...## 27. run of importance source...## 28. run of importance source...## 29. run of importance source...## 30. run of importance source...## 31. run of importance source...## 32. run of importance source...## 33. run of importance source...## After 33 iterations, +1.8 secs:## rejected 1 attribute: V6;## no more attributes left.Рисуем графики
plot(boruta_result, cex.axis = 0.8)
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.