laba2Artem
2025-03-18
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:
library(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", main = "Pairs Plot")
featurePlot(x = x, y = y, plot = "density", layout = c(1, 5), main = "Density Plot")
featurePlot(x = x, y = y, plot = "box", layout = c(5, 1), main = "Box Plot")
Вывод: исходя из визуализации данных видно, что данные случайны и
большая часть значений находится в диапазоне от -1 до 1. Медианные
значения класса А зачастую выше значений класса B в рамках одного
Feature.
Задание 2. С использованием функций из пакета Fselector определить важность признаков для решения задачи классификации.
library(FSelector)
data(iris)
weights <- information.gain(Species ~ ., data = iris)
print(weights)## attr_importance
## Sepal.Length 0.4521286
## Sepal.Width 0.2672750
## Petal.Length 0.9402853
## Petal.Width 0.9554360Вывод: наибольшей важностью обладают атрибуты ширины и длины Petal, в то время как Sepal обладает меньшей важностью для классификации, особенно ширина.
Задание 3 Преобразование непрерывной переменной в категориальную различными методами.
library(arules)
library(ggplot2)
# Создаем копию данных
iris_disc <- iris
# Методы дискретизации
iris_disc$Sepal.Length_interval <- discretize(iris$Sepal.Length, method = "interval", breaks = 3)
iris_disc$Sepal.Length_frequency <- discretize(iris$Sepal.Length, method = "frequency", breaks = 3)
iris_disc$Sepal.Length_cluster <- discretize(iris$Sepal.Length, method = "cluster", breaks = 3)
iris_disc$Sepal.Length_fixed <- discretize(iris$Sepal.Length, method = "fixed", breaks = c(-Inf, 5.5, 6.5, Inf))
# Графики
ggplot(iris_disc, aes(x = Sepal.Length_interval)) +
geom_bar(fill = "salmon", color = "black") +
labs(title = "Метод: Равная ширина (interval)")
ggplot(iris_disc, aes(x = Sepal.Length_frequency)) +
geom_bar(fill = "lightgreen", color = "black") +
labs(title = "Метод: Равная частота (frequency)")
ggplot(iris_disc, aes(x = Sepal.Length_cluster)) +
geom_bar(fill = "gold", color = "black") +
labs(title = "Метод: Кластеризация (cluster)")
ggplot(iris_disc, aes(x = Sepal.Length_fixed)) +
geom_bar(fill = "violet", color = "black") +
labs(title = "Метод: Фиксированные границы (fixed)")
Вывод: разные методы дискретизации дают различное распределение данных,
что может быть полезно для разных аналитических задач.
Задание 4 Выбор признаков с использованием пакета Boruta.
library(Boruta)
library(mlbench)
data("Ozone", package = "mlbench")
# Очистка данных
ozone_clean <- na.omit(Ozone)
ozone_clean <- droplevels(ozone_clean)
# Анализ для V4
invisible(capture.output(
boruta_v4 <- Boruta(V4 ~ ., data = ozone_clean, doTrace = 0, maxRuns = 100)
))
print(boruta_v4)## Boruta performed 46 iterations in 3.177295 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;plot(boruta_v4, main = "Важность признаков для V4")
# Анализ для V5
invisible(capture.output(
boruta_v5 <- Boruta(V5 ~ ., data = ozone_clean, doTrace = 0, maxRuns = 100)
))
print(boruta_v5)## Boruta performed 11 iterations in 0.812077 secs.
## 11 attributes confirmed important: V1, V10, V11, V12, V13 and 6 more;
## 1 attributes confirmed unimportant: V3;plot(boruta_v5, main = "Важность признаков для V5")
# Анализ для V6
invisible(capture.output(
boruta_v6 <- Boruta(V6 ~ ., data = ozone_clean, doTrace = 0, maxRuns = 100)
))
print(boruta_v6)## Boruta performed 86 iterations in 6.012737 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V4 and 4 more;
## 3 attributes confirmed unimportant: V13, V2, V3;plot(boruta_v6, main = "Важность признаков для V6")
Вывод: алгоритм Boruta позволяет определить наиболее значимые признаки
для каждого целевого переменного, что полезно для feature selection.