#Extract data for regression mode

Clean_Data<-read.csv("http://ucanalytics.com/blogs/wp-content/uploads/2016/09/Regression-Clean-Data.csv")
numeric<-c("Dist_Taxi", "Dist_Market", "Dist_Hospital", "Carpet","Builtup", "Rainfall")
categoric <- c("Parking", "City_Category")
Target<-c("House_Price")

# Prepare train and test data for regression models

set.seed(42)
train <-sample(nrow(Clean_Data), 0.7*nrow(Clean_Data))
test<-setdiff(seq_len(nrow(Clean_Data)), train)

# 1st regression model with all the variables

Org_Reg<-lm(House_Price~.,data = Clean_Data[train,c(Target,numeric,categoric)])
summary(Org_Reg)
Estimate <- predict(Org_Reg, type="response", newdata=Clean_Data[test, c(numeric,categoric,Target)])
Observed <- subset(Clean_Data[test,c(numeric,categoric,Target)],select = Target)
format(cor(Estimate, Observed$House_Price)^2, digits=4)

# 2nd Regression model with principal components

require(FactoMineR)
Data_for_PCA<-Clean_Data[,numeric]
pca1<-PCA(Data_for_PCA)
PCA_data<-as.data.frame(cbind(Clean_Data[train,c(Target,categoric)],pca1$ind$coord[train,]))
Step_PCA_Reg<-step(lm(House_Price~.,data = PCA_data))
summary(Step_PCA_Reg)
PCA_Estimate <- predict(Step_PCA_Reg, type="response", newdata=cbind(Clean_Data[test,c(Target,categoric)],pca1$ind$coord[test,]))
format(cor(PCA_Estimate, Observed$House_Price)^2, digits=4)

# 3rd regression model with dominant variables

numeric_new<-c("Dist_Hospital", "Carpet")
New_Reg<-lm(House_Price~.,data = Clean_Data[train,c(Target,numeric_new,categoric)])
options(scipen=999)
summary(New_Reg)
New_Estimate <- predict(New_Reg, type="response", newdata=Clean_Data[test, c(numeric,categoric,Target)])
Observed <- subset(Clean_Data[test,c(numeric,categoric,Target)],select = Target)
format(cor(New_Estimate, Observed$House_Price)^2, digits=4)