Lab2
Ruslan
2025-03-08
1. Использование пакета caret
Установка библиотеки caret:
Запуск библиотеки:
library(caret)Список доступных методов выбора признаков:
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"Набор данных:
x <- matrix(rnorm(50*5),ncol=5)
y <- factor(rep(c("A", "B"), 25))Построение графика pairs:
library(caret)
featurePlot(x=x, y=y, plot="pairs")
Сохранение графика в JPG-файл:
library(caret)
jpeg("featurePlot_pairs.jpg")
featurePlot(x=x, y=y, plot="pairs")
dev.off()## png
## 2Построение графика density:
library(caret)
featurePlot(x=x, y=y, plot="density")
Сохранение графика в JPG-файл:
library(caret)
jpeg("featurePlot_density.jpg")
featurePlot(x=x, y=y, plot="density")
dev.off()## png
## 2Построение графика box:
library(caret)
featurePlot(x=x, y=y, plot="box")
Сохранение графика в JPG-файл:
library(caret)
jpeg("featurePlot_box.jpg")
featurePlot(x=x, y=y, plot="box")
dev.off()## png
## 2Выводы:
График pairs позволяет визуализировать взаимосвязи между признаками.
График density показывает распределение значений признаков для каждого класса.
График box помогает оценить распределение и выбросы в данных.
2. Использование пакета FSelector
Установка библиотеки FSelector:
Запуск библиотеки:
library(FSelector)Определение важности признаков с помощью набора iris:
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 0.9554360Выводы:
Функция information.gain позволяет оценить важность каждого признака для задачи классификации.
Наиболее важные признаки имеют наибольшие значения весов.
3. Использование пакета arules
Установка библиотеки arules:
Запуск библиотеки:
library(arules)Преобразование переменной Sepal.Length различными методами и вывод результатов:
library(arules)
iris$Sepal.Length_interval <- discretize(iris$Sepal.Length, method="interval", breaks=3)
iris$Sepal.Length_frequency <- discretize(iris$Sepal.Length, method="frequency", breaks=3)
iris$Sepal.Length_cluster <- discretize(iris$Sepal.Length, method="cluster", breaks=3)
iris$Sepal.Length_fixed <- discretize(iris$Sepal.Length, method="fixed", breaks=c(-Inf, 5.5, 6.5, Inf))
head(iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## Sepal.Length_interval Sepal.Length_frequency Sepal.Length_cluster
## 1 [4.3,5.5) [4.3,5.4) [4.3,5.33)
## 2 [4.3,5.5) [4.3,5.4) [4.3,5.33)
## 3 [4.3,5.5) [4.3,5.4) [4.3,5.33)
## 4 [4.3,5.5) [4.3,5.4) [4.3,5.33)
## 5 [4.3,5.5) [4.3,5.4) [4.3,5.33)
## 6 [4.3,5.5) [5.4,6.3) [5.33,6.27)
## Sepal.Length_fixed
## 1 [-Inf,5.5)
## 2 [-Inf,5.5)
## 3 [-Inf,5.5)
## 4 [-Inf,5.5)
## 5 [-Inf,5.5)
## 6 [-Inf,5.5)Выводы:
Метод interval создает интервалы равной ширины.
Метод frequency создает интервалы с равным количеством наблюдений.
Метод cluster использует кластеризацию для определения интервалов.
Метод fixed позволяет задать границы интервалов вручную.
4. Использование пакета Boruta
Установка библиотеки Boruta:
Запуск библиотеки:
library(Boruta)Загрузка датасета airquality:
data("airquality")
str(airquality)## 'data.frame': 153 obs. of 6 variables:
## $ Ozone : int 41 36 12 18 NA 28 23 19 8 NA ...
## $ Solar.R: int 190 118 149 313 NA NA 299 99 19 194 ...
## $ Wind : num 7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
## $ Temp : int 67 72 74 62 56 66 65 59 61 69 ...
## $ Month : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Day : int 1 2 3 4 5 6 7 8 9 10 ...Удаление строк с пропущенными значениями и проведение выбора признаков с использованием Boruta:
airquality_clean <- na.omit(airquality)
set.seed(123)
boruta_output <- Boruta(Ozone ~ ., data = airquality_clean, 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...## After 9 iterations, +0.32 secs:## confirmed 4 attributes: Month, Solar.R, Temp, Wind;## still have 1 attribute left.## 10. run of importance source...## 11. run of importance source...## 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...## 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...## 37. run of importance source...## 38. run of importance source...## 39. run of importance source...## 40. run of importance source...## 41. run of importance source...## 42. run of importance source...## 43. run of importance source...## 44. run of importance source...## 45. run of importance source...## 46. run of importance source...## 47. run of importance source...## 48. run of importance source...## 49. run of importance source...## 50. run of importance source...## 51. run of importance source...## 52. run of importance source...## 53. run of importance source...## 54. run of importance source...## 55. run of importance source...## 56. run of importance source...## 57. run of importance source...## After 57 iterations, +1.9 secs:## confirmed 1 attribute: Day;## no more attributes left.print(boruta_output)## Boruta performed 57 iterations in 1.908043 secs.
## 5 attributes confirmed important: Day, Month, Solar.R, Temp, Wind;
## No attributes deemed unimportant.Выбор важных признаков и построение boxplot для выбранных признаков:
important_features <- getSelectedAttributes(boruta_output, withTentative = TRUE)
par(mfrow = c(1, length(important_features)))
for (feature in important_features) {
boxplot(airquality_clean[[feature]], main = feature, ylab = "Value")
}
Выводы:
Пакет Boruta помогает определить наиболее значимые признаки для задачи классификации.
График boxplot показывает важность каждого признака.