Analyzing and Visualizing Data - Residency Individual Project

install.packages("randomForest") library(randomForest) setwd("C:/Users/ialsmadi/Desktop/University_of_Cumberlands/Lectures") getwd() Credits <- read.csv("Credit_Card.csv", header = TRUE) prop.table(Credits$default.payment.next.month) summary(Credits$default.payment.next.month) str(Credits) # delete ID colum Credits$ID <- NULL # Split into Train and Validation sets # Training Set : Validation Set = 70 : 30 (random) set.seed(100) train <- sample(nrow(Credits), 0.7*nrow(Credits), replace = FALSE) TrainSet <- Credits[train,] ValidSet <- Credits[-train,] summary(TrainSet) summary(ValidSet) target <- Credits$default.payment.next.month # Create a Random Forest model with default parameters model1 <- randomForest(as.factor(target) ~ ., data = TrainSet, importance = TRUE) model1 model2 <- cforest(as.factor(target) ~ ., data = TrainSet, importance = TRUE) model2