Task 1: CARET Feature Plot
# Load libraries
library(caret)
library(ggplot2)
# Show available modeling methods
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"
# Create synthetic data
set.seed(123)
x <- matrix(rnorm(50*5), ncol = 5)
colnames(x) <- paste0('V', 1:5)
y <- factor(rep(c('A','B'), each = 25))
df <- data.frame(x, Class = y)
# Feature plots
featurePlot(x = x, y = y, plot = 'pairs')
featurePlot(x = x, y = y, plot = "box", auto.key = list(columns = 2), main = "Boxplots by Class")
featurePlot(x = x, y = y, plot = "density", auto.key = list(columns = 2), main = "Density Curves by Class")
library(FSelector)
data(iris)
# Show dataset info
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
table(iris$Species)
##
## setosa versicolor virginica
## 50 50 50
# Calculate feature importance
ig <- information.gain(Species ~ ., iris)
gr <- gain.ratio(Species ~ ., iris)
chi <- chi.squared(Species ~ ., iris)
res <- data.frame(InformationGain = ig$attr_importance,
GainRatio = gr$attr_importance,
ChiSquared = chi$attr_importance,
row.names = rownames(ig))
print(res)
## InformationGain GainRatio ChiSquared
## Sepal.Length 0.4521286 0.4196464 0.6288067
## Sepal.Width 0.2672750 0.2472972 0.4922162
## Petal.Length 0.9402853 0.8584937 0.9346311
## Petal.Width 0.9554360 0.8713692 0.9432359
# Plot
barplot(ig$attr_importance[order(ig$attr_importance, decreasing = TRUE)],
main = 'Information Gain (iris)', las = 3)
library(arules)
data(iris)
vec <- iris$Sepal.Length
summary(vec)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.300 5.100 5.800 5.843 6.400 7.900
# 4 discretization methods
int_cut <- discretize(vec, method = 'interval', categories = 3)
freq_cut <- discretize(vec, method = 'frequency', categories = 3)
clust_cut <- discretize(vec, method = 'cluster', categories = 3)
fixed_cut <- discretize(vec, method = 'fixed', breaks = c(4.3, 5.5, 6.5, 7.9))
# Show results
table(int_cut)
## int_cut
## [4.3,5.5) [5.5,6.7) [6.7,7.9]
## 52 70 28
table(freq_cut)
## freq_cut
## [4.3,5.4) [5.4,6.3) [6.3,7.9]
## 46 53 51
table(clust_cut)
## clust_cut
## [4.3,5.42) [5.42,6.39) [6.39,7.9]
## 52 56 42
table(fixed_cut)
## fixed_cut
## [4.3,5.5) [5.5,6.5) [6.5,7.9]
## 52 63 35
# Plots
plot(int_cut, main='interval')
plot(freq_cut, main='frequency')
plot(clust_cut, main='cluster')
plot(fixed_cut, main='fixed')
library(Boruta)
library(mlbench)
data("Ozone")
ozone_clean <- na.omit(Ozone)
set.seed(42)
boruta_res <- Boruta(V4 ~ ., data = ozone_clean, ntree = 500, doTrace = 0)
print(boruta_res)
## Boruta performed 21 iterations in 0.94034 secs.
## 9 attributes confirmed important: V1, V10, V11, V12, V13 and 4 more;
## 3 attributes confirmed unimportant: V2, V3, V6;
plot(boruta_res, xlab = "", xaxt = "n")
axis(side = 1, las = 2, at = 1:ncol(boruta_res$ImpHistory),
labels = colnames(boruta_res$ImpHistory), cex.axis = 0.7)
