laba2
Darya Pozdnyakova
2025-04-01
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.
Подключим необходимые пакеты.
library(ggplot2)## Warning: пакет 'ggplot2' был собран под R версии 4.4.3library(caret)## Warning: пакет 'caret' был собран под R версии 4.4.3## Загрузка требуемого пакета: latticeТеперь ознакомимся со списком доступных 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"Сгенерируем данные
# Генерация данных
set.seed(123)
x <- matrix(rnorm(50*5), ncol=5)
y <- factor(rep(c("A", "B"), 25))
df <- data.frame(x, y)
# Графический анализ данных
featurePlot(x = df[, 1:5], y = df$y, plot = "box")
Вывод: Значения распределены в промежутке между -1 и 1. Разброс данных в обоих классах примерно одинаковый.
Чтобы сохранить полученные графики необходимо прописать следующее:
featurePlot(x, y, plot = “box”) # Боксплот
ggsave(“feature_plot_box.jpg”) # Сохранение графика
featurePlot(x, y, plot = “density”) # График плотности
ggsave(“feature_plot_density.jpg”) # Сохранение
Задание №2: С использование функций из пакета Fselector [2] определить важность признаков для решения задачи классификации. Использовать набор data(iris)
# Построение матрицы диаграмм рассеяния с цветовой маркировкой классов
pairs(iris[, 1:4], col = iris[, 5], oma = c(4, 4, 6, 12))
# Добавление легенды
par(xpd = TRUE)
legend(0.85, 0.6, legend = as.vector(unique(iris$Species)), fill = c(1, 2, 3))
Вывод: Признаки Sepal.Length и Sepal.Width не являются важными для решения задачи.
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
Подключим необходимый пакет:
library(arules)## Warning: пакет 'arules' был собран под R версии 4.4.3## Загрузка требуемого пакета: Matrix##
## Присоединяю пакет: 'arules'## Следующие объекты скрыты от 'package:base':
##
## abbreviate, writeМетод равных интервалов (“interval”)
Разбивает диапазон данных на интервалы одинаковой длины. Недостаток метода проявляется, если данные распределены неравномерно — тогда некоторые интервалы могут содержать очень мало наблюдений.
# Дискретизация переменной Sepal.Length методом "interval" (равные интервалы)
iris_discrete <- discretize(iris$Sepal.Length, method = "interval", categories = 3)## Warning in discretize(iris$Sepal.Length, method = "interval", categories = 3):
## Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!# Вывод
print(iris_discrete)## [1] [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5)
## [8] [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5)
## [15] [5.5,6.7) [5.5,6.7) [4.3,5.5) [4.3,5.5) [5.5,6.7) [4.3,5.5) [4.3,5.5)
## [22] [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5)
## [29] [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [5.5,6.7) [4.3,5.5)
## [36] [4.3,5.5) [5.5,6.7) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5)
## [43] [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5) [4.3,5.5)
## [50] [4.3,5.5) [6.7,7.9] [5.5,6.7) [6.7,7.9] [5.5,6.7) [5.5,6.7) [5.5,6.7)
## [57] [5.5,6.7) [4.3,5.5) [5.5,6.7) [4.3,5.5) [4.3,5.5) [5.5,6.7) [5.5,6.7)
## [64] [5.5,6.7) [5.5,6.7) [6.7,7.9] [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7)
## [71] [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7) [6.7,7.9]
## [78] [6.7,7.9] [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7)
## [85] [4.3,5.5) [5.5,6.7) [6.7,7.9] [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7)
## [92] [5.5,6.7) [5.5,6.7) [4.3,5.5) [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7)
## [99] [4.3,5.5) [5.5,6.7) [5.5,6.7) [5.5,6.7) [6.7,7.9] [5.5,6.7) [5.5,6.7)
## [106] [6.7,7.9] [4.3,5.5) [6.7,7.9] [6.7,7.9] [6.7,7.9] [5.5,6.7) [5.5,6.7)
## [113] [6.7,7.9] [5.5,6.7) [5.5,6.7) [5.5,6.7) [5.5,6.7) [6.7,7.9] [6.7,7.9]
## [120] [5.5,6.7) [6.7,7.9] [5.5,6.7) [6.7,7.9] [5.5,6.7) [6.7,7.9] [6.7,7.9]
## [127] [5.5,6.7) [5.5,6.7) [5.5,6.7) [6.7,7.9] [6.7,7.9] [6.7,7.9] [5.5,6.7)
## [134] [5.5,6.7) [5.5,6.7) [6.7,7.9] [5.5,6.7) [5.5,6.7) [5.5,6.7) [6.7,7.9]
## [141] [6.7,7.9] [6.7,7.9] [5.5,6.7) [6.7,7.9] [6.7,7.9] [6.7,7.9] [5.5,6.7)
## [148] [5.5,6.7) [5.5,6.7) [5.5,6.7)
## attr(,"discretized:breaks")
## [1] 4.3 5.5 6.7 7.9
## attr(,"discretized:method")
## [1] interval
## Levels: [4.3,5.5) [5.5,6.7) [6.7,7.9]Метод фиксированных границ интервалов (“fixed”)
Границы категорий задаются вручную. Этот подход удобен, если заранее известны значимые пороги для группировки данных.
# Дискретизация переменной Sepal.Length методом "fixed" (равная частота)
iris_discrete <- discretize(iris$Sepal.Length, method = "fixed", categories = c(4.5, 5.5, 6.5))## Warning in discretize(iris$Sepal.Length, method = "fixed", categories = c(4.5,
## : Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!# Вывод
print(iris_discrete)## [1] [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5)
## [8] [4.5,5.5) <NA> [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) <NA>
## [15] [5.5,6.5] [5.5,6.5] [4.5,5.5) [4.5,5.5) [5.5,6.5] [4.5,5.5) [4.5,5.5)
## [22] [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5)
## [29] [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [5.5,6.5] [4.5,5.5)
## [36] [4.5,5.5) [5.5,6.5] [4.5,5.5) <NA> [4.5,5.5) [4.5,5.5) [4.5,5.5)
## [43] <NA> [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5) [4.5,5.5)
## [50] [4.5,5.5) <NA> [5.5,6.5] <NA> [5.5,6.5] [5.5,6.5] [5.5,6.5]
## [57] [5.5,6.5] [4.5,5.5) <NA> [4.5,5.5) [4.5,5.5) [5.5,6.5] [5.5,6.5]
## [64] [5.5,6.5] [5.5,6.5] <NA> [5.5,6.5] [5.5,6.5] [5.5,6.5] [5.5,6.5]
## [71] [5.5,6.5] [5.5,6.5] [5.5,6.5] [5.5,6.5] [5.5,6.5] <NA> <NA>
## [78] <NA> [5.5,6.5] [5.5,6.5] [5.5,6.5] [5.5,6.5] [5.5,6.5] [5.5,6.5]
## [85] [4.5,5.5) [5.5,6.5] <NA> [5.5,6.5] [5.5,6.5] [5.5,6.5] [5.5,6.5]
## [92] [5.5,6.5] [5.5,6.5] [4.5,5.5) [5.5,6.5] [5.5,6.5] [5.5,6.5] [5.5,6.5]
## [99] [4.5,5.5) [5.5,6.5] [5.5,6.5] [5.5,6.5] <NA> [5.5,6.5] [5.5,6.5]
## [106] <NA> [4.5,5.5) <NA> <NA> <NA> [5.5,6.5] [5.5,6.5]
## [113] <NA> [5.5,6.5] [5.5,6.5] [5.5,6.5] [5.5,6.5] <NA> <NA>
## [120] [5.5,6.5] <NA> [5.5,6.5] <NA> [5.5,6.5] <NA> <NA>
## [127] [5.5,6.5] [5.5,6.5] [5.5,6.5] <NA> <NA> <NA> [5.5,6.5]
## [134] [5.5,6.5] [5.5,6.5] <NA> [5.5,6.5] [5.5,6.5] [5.5,6.5] <NA>
## [141] <NA> <NA> [5.5,6.5] <NA> <NA> <NA> [5.5,6.5]
## [148] [5.5,6.5] [5.5,6.5] [5.5,6.5]
## attr(,"discretized:breaks")
## [1] 4.5 5.5 6.5
## attr(,"discretized:method")
## [1] fixed
## Levels: [4.5,5.5) [5.5,6.5]Метод равных частот (“frequency”)
Обеспечивает примерно одинаковое количество значений в каждой группе. Хорошо подходит для случаев, когда данные сконцентрированы в отдельных диапазонах.
# Дискретизация переменной Sepal.Length методом "frequency" (категории задают границы интервалов)
iris_discrete <- discretize(iris$Sepal.Length, method = "frequency", categories = 3)## Warning in discretize(iris$Sepal.Length, method = "frequency", categories = 3):
## Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!# Вывод
print(iris_discrete)## [1] [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [5.4,6.3) [4.3,5.4)
## [8] [4.3,5.4) [4.3,5.4) [4.3,5.4) [5.4,6.3) [4.3,5.4) [4.3,5.4) [4.3,5.4)
## [15] [5.4,6.3) [5.4,6.3) [5.4,6.3) [4.3,5.4) [5.4,6.3) [4.3,5.4) [5.4,6.3)
## [22] [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4)
## [29] [4.3,5.4) [4.3,5.4) [4.3,5.4) [5.4,6.3) [4.3,5.4) [5.4,6.3) [4.3,5.4)
## [36] [4.3,5.4) [5.4,6.3) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4)
## [43] [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4) [4.3,5.4)
## [50] [4.3,5.4) [6.3,7.9] [6.3,7.9] [6.3,7.9] [5.4,6.3) [6.3,7.9] [5.4,6.3)
## [57] [6.3,7.9] [4.3,5.4) [6.3,7.9] [4.3,5.4) [4.3,5.4) [5.4,6.3) [5.4,6.3)
## [64] [5.4,6.3) [5.4,6.3) [6.3,7.9] [5.4,6.3) [5.4,6.3) [5.4,6.3) [5.4,6.3)
## [71] [5.4,6.3) [5.4,6.3) [6.3,7.9] [5.4,6.3) [6.3,7.9] [6.3,7.9] [6.3,7.9]
## [78] [6.3,7.9] [5.4,6.3) [5.4,6.3) [5.4,6.3) [5.4,6.3) [5.4,6.3) [5.4,6.3)
## [85] [5.4,6.3) [5.4,6.3) [6.3,7.9] [6.3,7.9] [5.4,6.3) [5.4,6.3) [5.4,6.3)
## [92] [5.4,6.3) [5.4,6.3) [4.3,5.4) [5.4,6.3) [5.4,6.3) [5.4,6.3) [5.4,6.3)
## [99] [4.3,5.4) [5.4,6.3) [6.3,7.9] [5.4,6.3) [6.3,7.9] [6.3,7.9] [6.3,7.9]
## [106] [6.3,7.9] [4.3,5.4) [6.3,7.9] [6.3,7.9] [6.3,7.9] [6.3,7.9] [6.3,7.9]
## [113] [6.3,7.9] [5.4,6.3) [5.4,6.3) [6.3,7.9] [6.3,7.9] [6.3,7.9] [6.3,7.9]
## [120] [5.4,6.3) [6.3,7.9] [5.4,6.3) [6.3,7.9] [6.3,7.9] [6.3,7.9] [6.3,7.9]
## [127] [5.4,6.3) [5.4,6.3) [6.3,7.9] [6.3,7.9] [6.3,7.9] [6.3,7.9] [6.3,7.9]
## [134] [6.3,7.9] [5.4,6.3) [6.3,7.9] [6.3,7.9] [6.3,7.9] [5.4,6.3) [6.3,7.9]
## [141] [6.3,7.9] [6.3,7.9] [5.4,6.3) [6.3,7.9] [6.3,7.9] [6.3,7.9] [6.3,7.9]
## [148] [6.3,7.9] [5.4,6.3) [5.4,6.3)
## attr(,"discretized:breaks")
## [1] 4.3 5.4 6.3 7.9
## attr(,"discretized:method")
## [1] frequency
## Levels: [4.3,5.4) [5.4,6.3) [6.3,7.9]Метод кластерного анализа (“cluster”)
Применяет алгоритмы кластеризации для автоматического разделения данных. Хорошо адаптируется к структуре данных, но требует предварительного выбора количества кластеров.
# Дискретизация переменной Sepal.Length методом "cluster" (кластеризация)
iris_discrete <- discretize(iris$Sepal.Length, method = "cluster", categories = 3)## Warning in discretize(iris$Sepal.Length, method = "cluster", categories = 3):
## Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!# Вывод
print(iris_discrete)## [1] [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45)
## [7] [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45)
## [13] [4.3,5.45) [4.3,5.45) [5.45,6.46) [5.45,6.46) [4.3,5.45) [4.3,5.45)
## [19] [5.45,6.46) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45)
## [25] [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45)
## [31] [4.3,5.45) [4.3,5.45) [4.3,5.45) [5.45,6.46) [4.3,5.45) [4.3,5.45)
## [37] [5.45,6.46) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45)
## [43] [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45) [4.3,5.45)
## [49] [4.3,5.45) [4.3,5.45) [6.46,7.9] [5.45,6.46) [6.46,7.9] [5.45,6.46)
## [55] [6.46,7.9] [5.45,6.46) [5.45,6.46) [4.3,5.45) [6.46,7.9] [4.3,5.45)
## [61] [4.3,5.45) [5.45,6.46) [5.45,6.46) [5.45,6.46) [5.45,6.46) [6.46,7.9]
## [67] [5.45,6.46) [5.45,6.46) [5.45,6.46) [5.45,6.46) [5.45,6.46) [5.45,6.46)
## [73] [5.45,6.46) [5.45,6.46) [5.45,6.46) [6.46,7.9] [6.46,7.9] [6.46,7.9]
## [79] [5.45,6.46) [5.45,6.46) [5.45,6.46) [5.45,6.46) [5.45,6.46) [5.45,6.46)
## [85] [4.3,5.45) [5.45,6.46) [6.46,7.9] [5.45,6.46) [5.45,6.46) [5.45,6.46)
## [91] [5.45,6.46) [5.45,6.46) [5.45,6.46) [4.3,5.45) [5.45,6.46) [5.45,6.46)
## [97] [5.45,6.46) [5.45,6.46) [4.3,5.45) [5.45,6.46) [5.45,6.46) [5.45,6.46)
## [103] [6.46,7.9] [5.45,6.46) [6.46,7.9] [6.46,7.9] [4.3,5.45) [6.46,7.9]
## [109] [6.46,7.9] [6.46,7.9] [6.46,7.9] [5.45,6.46) [6.46,7.9] [5.45,6.46)
## [115] [5.45,6.46) [5.45,6.46) [6.46,7.9] [6.46,7.9] [6.46,7.9] [5.45,6.46)
## [121] [6.46,7.9] [5.45,6.46) [6.46,7.9] [5.45,6.46) [6.46,7.9] [6.46,7.9]
## [127] [5.45,6.46) [5.45,6.46) [5.45,6.46) [6.46,7.9] [6.46,7.9] [6.46,7.9]
## [133] [5.45,6.46) [5.45,6.46) [5.45,6.46) [6.46,7.9] [5.45,6.46) [5.45,6.46)
## [139] [5.45,6.46) [6.46,7.9] [6.46,7.9] [6.46,7.9] [5.45,6.46) [6.46,7.9]
## [145] [6.46,7.9] [6.46,7.9] [5.45,6.46) [6.46,7.9] [5.45,6.46) [5.45,6.46)
## attr(,"discretized:breaks")
## [1] 4.300000 5.452320 6.461111 7.900000
## attr(,"discretized:method")
## [1] cluster
## Levels: [4.3,5.45) [5.45,6.46) [6.46,7.9]Вывод: Каждый метод группировки данных имеет свои преимущества в зависимости от поставленных задач: метод “frequency” обеспечивает сбалансированность категорий, “interval” подходит для равномерных распределений, “cluster” выявляет скрытые закономерности в сложно структурированных данных, а “fixed” позволяет задать точные границы категорий в соответствии с экспертными требованиями. Выбор конкретного подхода зависит от характера данных и целей анализа.
Задание №4: Установите пакет Boruta и проведите выбор признаков для набора данных data(“Ozone”) [4, 5, 6]. Построить график boxplot, сделать выводы.
library(Boruta)## Warning: пакет 'Boruta' был собран под R версии 4.4.3library(mlbench)## Warning: пакет 'mlbench' был собран под R версии 4.4.3data("Ozone", package = "mlbench")
# Выбор признаков для данных Ozone и вывод результатов
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, +0.67 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...## 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, +1.4 secs:## rejected 1 attribute: V6;## still have 1 attribute left.## 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...## 34. run of importance source...## 35. run of importance source...## 36. run of importance source...## After 36 iterations, +2.1 secs:## rejected 1 attribute: V2;## no more attributes left.print(boruta_result)## Boruta performed 36 iterations in 2.13576 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;plot(boruta_result)
Вывод: Атрибуты расположены по важности в порядке возрастания.