Работа с пакетами CARET и BORUTA на языке R
Иванов Семён Андреевич 231-333
2026-03-07
Задание 1. Исследовательский анализ данных с использованием пакета caret
Установка и подготовка
if(!require(caret)) install.packages("caret")## Загрузка требуемого пакета: caret## Загрузка требуемого пакета: ggplot2## Загрузка требуемого пакета: latticelibrary(caret)Установка и подготовка
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"Построение графиков
Создадим данные:
x <- matrix(rnorm(50*5), ncol = 5)
y <- factor(rep(c("A", "B"), 25))
head(x)## [,1] [,2] [,3] [,4] [,5]
## [1,] 0.03281685 0.8620855 0.5291390 -1.0135241 0.4401972
## [2,] 1.76284054 -0.3697356 0.8452511 1.2091196 -0.9718031
## [3,] -0.09688061 0.1809049 0.9395595 -0.8043179 0.5969633
## [4,] -1.41093240 -0.8495276 0.5914474 0.3235852 -1.4435659
## [5,] -0.88455832 1.0763509 -0.9345247 0.1864100 1.4229137
## [6,] 0.38996104 0.4748437 0.9232960 1.2119906 -1.9344471Построим графики с использованием функции
featurePlot():
featurePlot(x, y, plot = "density")
featurePlot(x, y, plot = "box")
featurePlot(x, y, plot = "pairs")
featurePlot(x, y, plot = "strip")
Сохранение графики в JPEG
jpeg("plot_density.jpg")
featurePlot(x, y, plot = "density")
jpeg("plot_box.jpg")
featurePlot(x, y, plot = "box")
jpeg("plot_pairs.jpg")
featurePlot(x, y, plot = "pairs")
jpeg("plot_strip.jpg")
featurePlot(x, y, plot = "strip")Выводы по заданию 1:
Графики для всех признаков показывают, что данные генерируются с
нормальным распределением. При отсутствии явной структуры признаки не
обеспечивают разделение классов, что ожидаемо для случайных данных.
Задание 2. Определение важности признаков с использованием пакета FSelector
Установка и подготовка
if (!require(FSelector)) install.packages("FSelector", dependencies = TRUE)## Загрузка требуемого пакета: FSelectorlibrary(FSelector)Используем набор данных iris:
data(iris)
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 setosaВычисление важности признаков
Рассчитаем информационный выигрыш для каждого признака:
weights <- information.gain(Species ~ ., data = iris)
print(weights)## attr_importance
## Sepal.Length 0.4521286
## Sepal.Width 0.2672750
## Petal.Length 0.9402853
## Petal.Width 0.9554360Построим столбчатую диаграмму важности признаков:
barplot(weights$attr_importance,
names.arg = rownames(weights),
las = 2,
main = "Важность признаков (information gain)",
col = "skyblue")
Выводы по заданию 2:
Результаты показывают, что признаки, связанные с длиной и шириной
лепестка, оказывают наибольшее влияние на классификацию видов в наборе
iris, что соответствует классическим результатам.
Задание 3. Дискретизация непрерывной переменной с использованием функции discretize() из пакета arules
Установка и подготовка
if (!require(Boruta)) install.packages("Boruta", dependencies = TRUE)## Загрузка требуемого пакета: Borutalibrary(Boruta)
if(!require(arules)) {
install.packages("arules")
library(arules)
}## Загрузка требуемого пакета: arules## Загрузка требуемого пакета: Matrix##
## Присоединяю пакет: 'arules'## Следующие объекты скрыты от 'package:base':
##
## abbreviate, writeПрименим функцию discretize() к переменной
Sepal.Length набора данных iris с различными
методами:
iris$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$Sepal.Length, method = "cluster", breaks = 3)
breaks <- c(min(iris$Sepal.Length) - 0.1, 5, 6, max(iris$Sepal.Length) + 0.1)
iris$Sepal.Length.fixed <- discretize(iris$Sepal.Length, method = "fixed", breaks = breaks)Построим распределение полученных категорий для каждого метода:
par(mfrow = c(2, 2))
barplot(table(iris$Sepal.Length.interval), main = "Метод interval", col = "lightblue")
barplot(table(iris$Sepal.Length.frequency), main = "Метод frequency", col = "lightgreen")
barplot(table(iris$Sepal.Length.cluster), main = "Метод cluster", col = "lightcoral")
barplot(table(iris$Sepal.Length.fixed), main = "Метод fixed", col = "lightgoldenrod")
par(mfrow = c(1,1))Выводы по заданию 3:
Различные методы дискретизации дают разные группировки:
Interval: делит диапазон на равные по ширине интервалы, что может приводить к неравномерному числу наблюдений.
Frequency: обеспечивает примерно равное число наблюдений в каждом интервале.
Cluster: группирует значения на основе схожести, используя алгоритмы кластеризации.
Fixed: позволяет вручную задать границы интервалов.
Задание 4. Выбор признаков с использованием пакета Boruta для набора данных Ozone
Установка и подготовка
if (!require(Boruta)) install.packages("Boruta", dependencies = TRUE)
library(Boruta)
install.packages("mlbench", repos = "https://cloud.r-project.org/")## Warning: недоступен индекс для хранилища https://cloud.r-project.org/src/contrib:
## скачивание с 'https://cloud.r-project.org/src/contrib/PACKAGES' не удалось## Warning: пакет ''mlbench'' недоступен (for this version of R
##
## Другая версия этого пакета может быть доступна для Вашей версии R из других источников,
## см. возможные варианты на
## https://cran.r-project.org/doc/manuals/r-patched/R-admin.html#Installing-packages)## Warning: недоступен индекс для хранилища https://cloud.r-project.org/bin/windows/contrib/4.5:
## скачивание с 'https://cloud.r-project.org/bin/windows/contrib/4.5/PACKAGES' не удалосьlibrary(mlbench) Загрузка и предварительный анализ данных
data(Ozone)
Ozone <- na.omit(Ozone)
head(Ozone)## V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13
## 5 1 5 1 5 5760 3 51 54 45.32 1450 25 57.02 60
## 6 1 6 2 6 5720 4 69 35 49.64 1568 15 53.78 60
## 7 1 7 3 4 5790 6 19 45 46.40 2631 -33 54.14 100
## 8 1 8 4 4 5790 3 25 55 52.70 554 -28 64.76 250
## 9 1 9 5 6 5700 3 73 41 48.02 2083 23 52.52 120
## 12 1 12 1 6 5720 3 44 51 54.32 111 9 63.14 150Применение алгоритма Boruta
Для V4
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, +0.94 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...## After 15 iterations, +1.2 secs:## rejected 1 attribute: V2;## still have 1 attribute left.## 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...## After 38 iterations, +3.1 secs:## rejected 1 attribute: V6;## no more attributes left.Строим графики
plot(boruta_result, cex.axis = 0.8)
important_vars <- getSelectedAttributes(boruta_result, withTentative = TRUE)
boxplot(Ozone[, important_vars], main = "Selected Features Boxplot", las = 2, col = "lightblue")
Вывод: На 4 признак больше всего влияют признаки: v9, v8, v12, v11, v7, v10, v13, v1, v5. Значения 5го признака значительно выше значений остальных. 10й признак имеет большой разброс.
Для V5
boruta_result <- Boruta(V5 ~ ., 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, +0.9 secs:## confirmed 11 attributes: V1, V10, V11, V12, V13 and 6 more;## rejected 1 attribute: V3;## no more attributes left.Строим графики
plot(boruta_result, cex.axis = 0.8)
important_vars <- getSelectedAttributes(boruta_result, withTentative = TRUE)
boxplot(Ozone[, important_vars], main = "Selected Features Boxplot", las = 2, col = "lightblue")
Вывод: На 5 признак больше всего влияют признаки: v6, v9, v8, v12, v11, v7, v13, v12, v1, v4. Значения 9го признака значительно выше значений остальных. 10й признак имеет большой разброс.
Для V6
boruta_result <- Boruta(V6 ~ ., 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, +0.9 secs:## confirmed 4 attributes: V1, V11, V5, V9;## rejected 2 attributes: V2, V3;## still have 6 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, +1.9 secs:## confirmed 2 attributes: V12, V7;## still have 4 attributes 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...## 37. run of importance source...## 38. run of importance source...## After 38 iterations, +3 secs:## confirmed 1 attribute: V10;## still have 3 attributes left.## 39. run of importance source...## 40. run of importance source...## 41. run of importance source...## After 41 iterations, +3.3 secs:## rejected 1 attribute: V13;## still have 2 attributes left.## 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...## 58. run of importance source...## 59. run of importance source...## 60. run of importance source...## 61. run of importance source...## 62. run of importance source...## 63. run of importance source...## 64. run of importance source...## After 64 iterations, +5.1 secs:## confirmed 1 attribute: V4;## still have 1 attribute left.## 65. run of importance source...## 66. run of importance source...## 67. run of importance source...## 68. run of importance source...## 69. run of importance source...## 70. run of importance source...## 71. run of importance source...## 72. run of importance source...## 73. run of importance source...## 74. run of importance source...## 75. run of importance source...## 76. run of importance source...## 77. run of importance source...## 78. run of importance source...## 79. run of importance source...## 80. run of importance source...## 81. run of importance source...## 82. run of importance source...## 83. run of importance source...## 84. run of importance source...## 85. run of importance source...## 86. run of importance source...## 87. run of importance source...## 88. run of importance source...## 89. run of importance source...## 90. run of importance source...## 91. run of importance source...## 92. run of importance source...## 93. run of importance source...## 94. run of importance source...## 95. run of importance source...## 96. run of importance source...## 97. run of importance source...## 98. run of importance source...## 99. run of importance source...Строим графики
plot(boruta_result, cex.axis = 0.8)
important_vars <- getSelectedAttributes(boruta_result, withTentative = TRUE)
boxplot(Ozone[, important_vars], main = "Selected Features Boxplot", las = 2, col = "lightblue")
Вывод: На 6 признак больше всего влияют признаки: v8, v10, v4, v12, v7, v5, v9, v11, v1. Значения 1го признака значительно выше значений остальных. 10й признак имеет большой разброс.
Выводы по заданию 4:
Алгоритм Boruta сравнивает реальные признаки с теневыми (перемешанными)
и выделяет значимые переменные для предсказания концентрации озона (O3).
Построенный boxplot демонстрирует распределение важности, позволяя
принять решение о включении или исключении признаков.