#Discretization library(funModeling) d_bins=discretize_get_bins(data=Leedata5, input=c("flgs_number","srate","drate","rate","max","state_number","mean","min","stddev","seq"), n_bins=5) # Checking `d_bins` object: d_bins # Now it can be applied on the same data frame or in a new one Leedata_discretized=discretize_df(data=Leedata5, data_bins=d_bins, stringsAsFactors=T) View(Leedata_discretized) sapply(Leedata_discretized, class) LeeTrain <- createDataPartition(Leedata_discretized$category, p=0.8, list=FALSE, times = 1) Leetraining <- Leedata_discretized[ LeeTrain, ] Leetesting <- Leedata_discretized[ -LeeTrain, ] #Random Forest library("randomForest") Leemod_RF <- train(category ~ ., data=Leetraining, method="rf") Leepred_RF = predict(Leemod_RF, newdata=Leetesting) confusionMatrix(Leepred_RF,Leetesting$category) #SVM library("kernlab") Leemod_SVM <- train(category ~ ., data=Leetraining, method="svmLinear") Leepred_SVM = predict(Leemod_SVM, newdata=Leetesting) confusionMatrix(Leepred_SVM,Leetesting$category)