lab2
2025-09-22
Установка
if (!require("caret")) install.packages("caret")## Загрузка требуемого пакета: caret## Загрузка требуемого пакета: ggplot2## Загрузка требуемого пакета: latticelibrary(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"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:
set.seed(123)
x <- matrix(rnorm(50*5),ncol=5)
y <- factor(rep(c("A", "B"), 25))
colnames(x) <- paste0("Var", 1:5)
head(x)## Var1 Var2 Var3 Var4 Var5
## [1,] -0.56047565 0.25331851 -0.71040656 0.7877388 2.1988103
## [2,] -0.23017749 -0.02854676 0.25688371 0.7690422 1.3124130
## [3,] 1.55870831 -0.04287046 -0.24669188 0.3322026 -0.2651451
## [4,] 0.07050839 1.36860228 -0.34754260 -1.0083766 0.5431941
## [5,] 0.12928774 -0.22577099 -0.95161857 -0.1194526 -0.4143399
## [6,] 1.71506499 1.51647060 -0.04502772 -0.2803953 -0.4762469table(y)## y
## A B
## 25 25Scatterplot
featurePlot(x, y, plot = "pairs")
Boxplot
featurePlot(x, y, plot = "box")
Density Plot
featurePlot(x, y, plot = "density")
Вывод: Значимого различия между классами нет.
2. С использование функций из пакета Fselector [2] определить важность признаков для решения задачи классификации. Использовать набор data(iris). Сделать выводы.
if (!require("FSelector")) install.packages("FSelector")## Загрузка требуемого пакета: FSelectorlibrary(FSelector)
data(iris)
weights <- information.gain(Species ~ ., data = iris)
ordered_weights <- weights[order(-weights$attr_importance), , drop = FALSE]
barplot(ordered_weights$attr_importance,
names.arg = rownames(ordered_weights),
main = "Важность признаков",
col = "skyblue",
ylab = "Информационный выигрыш")
Вывод: признаки Petal.Length и Petal.Width являются наиболее
значимыми.
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
if (!require("arules")) install.packages("arules")## Загрузка требуемого пакета: arules## Загрузка требуемого пакета: Matrix##
## Присоединяю пакет: 'arules'## Следующие объекты скрыты от 'package:base':
##
## abbreviate, writelibrary(arules)
methods <- c("interval", "frequency", "cluster", "fixed")
res <- list()
for (method in methods) {
if (method == "fixed") {
disc <- discretize(iris$Sepal.Length, method = method, breaks = c(4, 5.5, 7, 8))
} else {
disc <- discretize(iris$Sepal.Length, method = method, breaks = 3)
}
res[[method]] <- disc
}
par(mfrow = c(2, 2))
for (i in 1:4) {
plot(res[[i]], main = paste("Метод:", methods[i]), col = rainbow(3))
}
Вывод: Методы cluster и frequency отражают более равномерное и точное распределение данных
if (!require("Boruta")) install.packages("Boruta")## Загрузка требуемого пакета: Borutaif (!require("mlbench")) install.packages("mlbench")## Загрузка требуемого пакета: mlbenchlibrary(Boruta)
library(mlbench)data(Ozone)
ozone_clean <- na.omit(Ozone)
colnames(ozone_clean) <- paste0("V", 1:13)
set.seed(234)
boruta_model <- Boruta(V4 ~ ., data = ozone_clean, doTrace = 0)
plot(boruta_model,
xlab = "Features",
ylab = "Z-value",
main = "Feature importance (Boruta)",
col = c("skyblue", "salmon", "gold"))
confirmed_features <- getSelectedAttributes(boruta_model, withTentative = FALSE)
cat("Important features:", confirmed_features)## Important features: V1 V5 V7 V8 V9 V10 V11 V12 V13Вывод: Несколько признаков имеют высокую значимость, самый значимым оказался признак V9