#------------------
# 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)


#-------------------------
# Hierarchical Clustering
#-------------------------
library(ggplot2)

#Clusters
clusters <- hclust(dist(train), method='complete')
plot(clusters)

#Top 4 clusters
clusterCut <- cutree(clusters, 4)
ggplot(train, aes(temp, humidity)) + 
       geom_point(size = 1) + geom_point(col = clusterCut) + 
       scale_color_manual(values = c('black', 'red', 'green', 'blue'))