Lab2
Vlada
2025-10-21
knitr::opts_chunk$set(echo = TRUE, warning = FALSE, message = FALSE)1. Работа с пакетом caret
# Установка и загрузка необходимых пакетов
# install.packages(c("caret", "lattice", "ggplot2", "FSelector", "arules", "Boruta", "mlbench"))
library(caret)
library(lattice)
library(ggplot2)# Список доступных моделей в пакете 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"x <- matrix(rnorm(50*5), ncol = 5)
y <- factor(rep(c("A","B"), 25))
featurePlot(x = x, y = y, plot = "pairs")
featurePlot(x = x, y = y, plot = "box")
featurePlot(x = x, y = y, plot = "density")
Вывод:
Графики демонстрируют распределения признаков между классами
A и B. Поскольку данные сгенерированы
случайно, различий не видно. В реальных данных
featurePlot() помогает находить информативные признаки.
2. Работа с пакетом FSelector
library(FSelector)
data(iris)
information.gain(Species ~ ., iris)## attr_importance
## Sepal.Length 0.4521286
## Sepal.Width 0.2672750
## Petal.Length 0.9402853
## Petal.Width 0.9554360gain.ratio(Species ~ ., iris)## attr_importance
## Sepal.Length 0.4196464
## Sepal.Width 0.2472972
## Petal.Length 0.8584937
## Petal.Width 0.8713692chi.squared(Species ~ ., iris)## attr_importance
## Sepal.Length 0.6288067
## Sepal.Width 0.4922162
## Petal.Length 0.9346311
## Petal.Width 0.9432359relief(Species ~ ., iris, neighbours.count = 5, sample.size = 30)## attr_importance
## Sepal.Length 0.1487963
## Sepal.Width 0.1622222
## Petal.Length 0.3557627
## Petal.Width 0.3431944Вывод:
Самые важные признаки для iris — Petal.Length
и Petal.Width. Они дают лучшее разделение классов. Методы
согласуются между собой, что подтверждает достоверность оценки важности
признаков.
3. Работа с функцией discretize() из пакета arules
library(arules)
vec <- iris$Sepal.Length
d_interval <- discretize(vec, method = "interval", categories = 4)
d_frequency <- discretize(vec, method = "frequency", categories = 4)
d_cluster <- discretize(vec, method = "cluster", categories = 4)
breaks <- c(-Inf, 5, 6, 7, Inf)
d_fixed <- discretize(vec, method = "fixed", breaks = breaks, onlycuts = FALSE)
par(mfrow = c(1,4))
plot(d_interval, main = "interval")
plot(d_frequency, main = "frequency")
plot(d_cluster, main = "cluster")
plot(d_fixed, main = "fixed")
Вывод:
Методы interval, frequency,
cluster и fixed по-разному группируют
значения: по равной ширине, равной частоте, кластеризации или заданным
порогам.
4. Работа с пакетом Boruta
library(Boruta)
library(mlbench)
data("Ozone", package = "mlbench")
ozone <- na.omit(Ozone) # удаляем пропущенные значения
set.seed(123)
boruta_result <- Boruta(V4 ~ ., data = ozone, doTrace = 0)
plot(boruta_result, las = 2, cex.axis = 0.7, main = "Важность признаков (Boruta)")
boruta_result$finalDecision## V1 V2 V3 V5 V6 V7 V8 V9
## Confirmed Rejected Rejected Confirmed Rejected Confirmed Confirmed Confirmed
## V10 V11 V12 V13
## Confirmed Confirmed Confirmed Confirmed
## Levels: Tentative Confirmed RejectedВывод:
Boruta использует случайные леса и теневые признаки для
отбора. Значимые переменные (Confirmed) имеют статистически
подтверждённое влияние на целевую переменную.