lin_reg1.R

install.packages("rsq")
library(rsq)

train<-read.table(file.choose(),sep = ",",header = T) #Importing the train set
train[train==""] <- NA #Filling blank values with NA
names(train)
X<-train[c(6,8)] #Creating new data with two variables
names((X))

Y<-train[c(12)] #Storing the dependent variable
names((Y))

#Splitting the data
set.seed(567) 
part <- sample(2, nrow(X), replace = TRUE, prob = c(0.7, 0.3))
X_train<- X[part == 1,]
X_cv<- X[part == 2,]

Y_train<- Y[part == 1,]
Y_cv<- Y[part == 2,]

train_2<-data.frame(Y_train,X_train)

model1<-lm(Y_train~Item_MRP+Outlet_Establishment_Year,data =train_2 ) #linear model function
summary(model1)

predict_1<-predict(model1,X_cv) #Predicting the values

m<-mean((Y_cv - predict_1)^2) #Calculating mse