#------------------ # 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) #----- # LDA #----- library(caret) library(AUC) library(MASS) #remove all records with missing values train <- na.omit(train) test <- na.omit(test) #train model.LDA <- lda(DEFAULT~., data=train) model.LDA #variables importance model.LDA$scaling #test pc <- predict(model.LDA, test) summary(pc$class) xtab <- table(pc$class, test$DEFAULT) caret::confusionMatrix(xtab, positive = "Y") #lift chart pb <- NULL pb <- pc$posterior pb <- as.data.frame(pb) pred.LDA <- data.frame(test$DEFAULT, pb$Y) colnames(pred.LDA) <- c("target","score") lift.LDA <- lift(target ~ score, data = pred.LDA, cuts=10, class="Y") xyplot(lift.LDA, main="LDA - Lift Chart", type=c("l","g"), lwd=2 , scales=list(x=list(alternating=FALSE,tick.number = 10) ,y=list(alternating=FALSE,tick.number = 10))) #roc chart labels <- as.factor(ifelse(pred.LDA$target=="Y", 1, 0)) predictions <- pred.LDA$score auc(roc(predictions, labels), min = 0, max = 1) plot(roc(predictions, labels), min=0, max=1, type="l", main="LDA - ROC Chart")