#------------------ # Data Preparation #------------------ #Read datasets #Download the data from http://www.saedsayad.com/datasets/CreditData.zip train <- read.csv("Credit_train.csv") test <- read.csv("Credit_test.csv") #Rows and Cols dim(train) dim(test) #Columns name colnames(train) colnames(test) #Show head(train) head(test) #--------------- # Decision tree #--------------- library(caret) library(rpart) library(rpart.plot) library(AUC) #train model.Dtree <- rpart(DEFAULT~., data = train, method="class") prp(model.Dtree) #lift chart pb <- NULL pb <- predict(model.Dtree, test) pb <- as.data.frame(pb) pred.Dtree <- data.frame(test$DEFAULT, pb$Y) colnames(pred.Dtree) <- c("target","score") lift.Dtree <- lift(target ~ score, data = pred.Dtree, cuts=10, class="Y") xyplot(lift.Dtree, main="Decision Tree - Lift Chart", type=c("l","g"), lwd=2 , scales=list(x=list(alternating=FALSE,tick.number = 10) ,y=list(alternating=FALSE,tick.number = 10))) #confusion matrix pc <- NULL pc <- ifelse(pb$N > pb$Y, "N", "Y") summary(as.data.frame(pc)) xtab <- table(pc, test$DEFAULT) caret::confusionMatrix(xtab, positive = "Y") #roc chart labels <- as.factor(ifelse(pred.Dtree$target=="Y", 1, 0)) predictions <- pred.Dtree$score auc(roc(predictions, labels), min = 0, max = 1) plot(roc(predictions, labels), min=0, max=1, type="l", main="Decision Tree - ROC Chart")