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 из справочного файла пакета CARET:
x <- matrix(rnorm(50*5),ncol=5)
y <- factor(rep(c(“A”, “B”), 25))
Сохранить полученные графики в *.jpg файлы. Сделать выводы.
Импортируем caret и выводим доступные методы.
library(caret)## Warning: пакет 'caret' был собран под R версии 4.4.3## Загрузка требуемого пакета: ggplot2## Загрузка требуемого пакета: latticenames(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"Задаем наборы данных и создаем графики на их основе.
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 = "density", layout = c(1, 5))
featurePlot(x = x, y = y, plot = "box", layout = c(5, 1))
jpeg("featurePlot_pairs.jpg")
featurePlot(x = x, y = y, plot = "pairs")
dev.off()## png
## 2jpeg("featurePlot_density.jpg")
featurePlot(x = x, y = y, plot = "density")
dev.off()## png
## 2jpeg("featurePlot_box.jpg")
featurePlot(x = x, y = y, plot = "box")
dev.off()## png
## 2Вывод: исходя из визуализации данных видно, что данные случайны и большая часть значений находится в диапозоне 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. Использовать набор data(iris). Сделать выводы.
library(FSelector)## Warning: пакет 'FSelector' был собран под R версии 4.4.3data(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: из данных важности аттрибутов можно сделать вывод, что наибольшей важностью обладют атрибуты ширины и длины Petal, в то время кака Sepal обладает нименьшей важностью для классификации, особенно ширина.
Задание 3
С использованием функции discretize() из пакета arules выполните преобразование непрерывной переменной в категориальную различными методами: «interval» (равная ширина интервала), «frequency» (равная частота), «cluster» (кластеризация) и «fixed» (категории задают границы интервалов). Используйте набор данных iris. Сделайте выводы
library(arules)## Warning: пакет 'arules' был собран под R версии 4.4.3## Загрузка требуемого пакета: Matrix##
## Присоединяю пакет: 'arules'## Следующие объекты скрыты от 'package:base':
##
## abbreviate, writeiris$Sepal.Length_interval <- discretize(iris$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))
plot_interval <- ggplot(iris, aes(x = Sepal.Length_interval)) +
geom_bar(fill = "salmon", color = "black") +
labs(title = "Метод: Равная ширина (interval)")
plot_interval
plot_frequency <- ggplot(iris, aes(x = Sepal.Length_frequency)) +
geom_bar(fill = "lightgreen", color = "black") +
labs(title = "Метод: Равная частота (frequency)")
plot_frequency
plot_cluster <- ggplot(iris, aes(x = Sepal.Length_cluster)) +
geom_bar(fill = "gold", color = "black") +
labs(title = "Метод: Кластеризация (cluster)")
plot_cluster
plot_fixed <- ggplot(iris, aes(x = Sepal.Length_fixed)) +
geom_bar(fill = "violet", color = "black") +
labs(title = "Метод: Фиксированные границы (fixed)")
plot_fixed
Вывод: Таким образом можнно сделать вывод, что:
interval делит данные на интервалы равной ширины;
frequency делит данные на интервалы с равным количеством записей;
cluster делит данные за счет алгоритмов кластеризации (группирует значения по схожести);
fixed делит данные на интервалы, заданные вручную.
Каждый метод дискретизации имеет место быть для той или иной задачи.
Задание 4
Установите пакет Boruta и проведите выбор признаков для набора данных data(“Ozone”) [4, 5, 6]. Построить график boxplot, сделать выводы. Проверим, какие признаки являются важными для признаков 4, 5 и 6.
library(Boruta)## Warning: пакет 'Boruta' был собран под R версии 4.4.3library(mlbench)## Warning: пакет 'mlbench' был собран под R версии 4.4.3data("Ozone", package = "mlbench")
ozone_clean <- na.omit(Ozone)
str(ozone_clean)## 'data.frame': 203 obs. of 13 variables:
## $ V1 : Factor w/ 12 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ V2 : Factor w/ 31 levels "1","2","3","4",..: 5 6 7 8 9 12 13 14 15 16 ...
## $ V3 : Factor w/ 7 levels "1","2","3","4",..: 1 2 3 4 5 1 2 3 4 5 ...
## $ V4 : num 5 6 4 4 6 6 5 4 4 7 ...
## $ V5 : num 5760 5720 5790 5790 5700 5720 5760 5780 5830 5870 ...
## $ V6 : num 3 4 6 3 3 3 6 6 3 2 ...
## $ V7 : num 51 69 19 25 73 44 33 19 19 19 ...
## $ V8 : num 54 35 45 55 41 51 51 54 58 61 ...
## $ V9 : num 45.3 49.6 46.4 52.7 48 ...
## $ V10: num 1450 1568 2631 554 2083 ...
## $ V11: num 25 15 -33 -28 23 9 -44 -44 -53 -67 ...
## $ V12: num 57 53.8 54.1 64.8 52.5 ...
## $ V13: num 60 60 100 250 120 150 40 200 250 200 ...
## - attr(*, "na.action")= 'omit' Named int [1:163] 1 2 3 4 10 11 17 18 20 24 ...
## ..- attr(*, "names")= chr [1:163] "1" "2" "3" "4" ...ozone_clean <- droplevels(ozone_clean)
set.seed(123)
boruta_output <- Boruta(V4 ~ ., data = ozone_clean, doTrace = 2, maxRuns = 100)## 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, +0.8 secs:## confirmed 9 attributes: V1, V10, V11, V12, V13 and 4 more;## rejected 2 attributes: V3, V6;## still have 1 attribute 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, +1.7 secs:## rejected 1 attribute: V2;## no more attributes left.print(boruta_output)## Boruta performed 24 iterations in 1.663278 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;plot(boruta_output)
jpeg("attribute_importance.jpg", width = 1200, height = 800)
plot(boruta_output)
dev.off()## png
## 2boruta_output <- Boruta(V5 ~ ., data = ozone_clean, doTrace = 2, maxRuns = 100)## 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, +0.78 secs:## confirmed 11 attributes: V1, V10, V11, V12, V13 and 6 more;## still have 1 attribute left.## 12. run of importance source...## 13. run of importance source...## 14. run of importance source...## 15. run of importance source...## After 15 iterations, +1.1 secs:## rejected 1 attribute: V3;## no more attributes left.print(boruta_output)## Boruta performed 15 iterations in 1.063301 secs.
## 11 attributes confirmed important: V1, V10, V11, V12, V13 and 6 more;
## 1 attributes confirmed unimportant: V3;plot(boruta_output)
jpeg("attribute_importance.jpg", width = 1200, height = 800)
plot(boruta_output)
dev.off()## png
## 2boruta_output <- Boruta(V6 ~ ., data = ozone_clean, doTrace = 2, maxRuns = 100)## 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, +0.87 secs:## confirmed 5 attributes: V1, V11, V5, V7, V9;## rejected 2 attributes: V2, V3;## still have 5 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:## confirmed 3 attributes: V10, V12, V4;## still have 2 attributes 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...## After 24 iterations, +1.8 secs:## rejected 1 attribute: V13;## still have 1 attribute 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...## 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...## 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...## 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...## After 91 iterations, +6.3 secs:## confirmed 1 attribute: V8;## no more attributes left.print(boruta_output)## Boruta performed 91 iterations in 6.335165 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V4 and 4 more;
## 3 attributes confirmed unimportant: V13, V2, V3;plot(boruta_output)
jpeg("attribute_importance.jpg", width = 1200, height = 800)
plot(boruta_output)
dev.off()## png
## 2Вывод: Таким образом можно сделать вывод, что:
для признака 4 важными являются признаки 1,5,7,8,9,10,11,12,13 (все, кроме 2,3,4 и 6);
для признака 5 важными являются признаки 1,2,4,6,7,8,9,10,11,12,13 (все, кроме 3 и 5);
для признака 6 важными являются признаки 1,4,5,7,8,9,10,11,12 (все, кроме 2,3,13 и 6).