#------------------
# Data Preparation
#------------------

#Read datasets
#Download the data from http://www.saedsayad.com/datasets/BikeRental.zip
train <- read.csv("bike_rental_train.csv")
test <- read.csv("bike_rental_test.csv")

#Rows and Cols
dim(train)
dim(test)

#Columns name
colnames(train)
colnames(test)

#Show  
head(train)
head(test)


#Rows and Cols
dim(train)
dim(test)

#Columns name
colnames(train)
colnames(test)

#Show  
head(train)
head(test)

#Scatter plot
pairs(~temp+humidity+windspeed+bike_rent_count, data=train, main="Scatterplot - train", col="darkgreen")
pairs(~temp+humidity+windspeed+bike_rent_count, data=test, main="Scatterplot - test", col="brown")


#----------------------------
# Multiple Linear Regression
#----------------------------

#Train
model.MLR <- lm(bike_rent_count ~., data=train)
summary(model.MLR)

#Residual plot
res.MLR = resid(model.MLR)
plot(train$temp, res.MLR, ylab="Residuals", xlab="Temperature", main="Residual Plot") 
abline(0, 0)

#Q-Q plot
stdres.MLR = rstandard(model.MLR)
qqnorm(stdres.MLR, ylab="Standardized Residuals", xlab="Normal Scores", main="QQ Plot") 
qqline(stdres.MLR)

#Test
predictions <- predict(model.MLR, newdata=test)
errors <- test$bike_rent_count - predictions 
rmse <- sqrt(mean((errors^2)))

#Erros histogram
hist(errors, main="bike_rent_count", sub="(Actual-Predicted)", xlab="Error", breaks=10, col="darkred")