Crime Data - Clustering Using Euclidean and Complete Linkage Method.

Cluster 1 has the maximum number of Murder which to me looks like it is more vulnerable

with other Assault on second top in the list.

Custer 2 has the maximum number of Rape,Assault and murder Pop and stands second in Murder.

Cluster 3 is a little vulnerable in terms of the Murder(Less). However it still stands 2nd in

UrbanPop Crime

Cluster 4 has got the less vulnerable to all the Crime categories.

crime <- read.csv(file.choose())
install.packages("rmarkdown",repos = "http://cran.us.r-project.org")

## Installing package into 'C:/Users/tswaminathan/Documents/R/win-library/3.5'
## (as 'lib' is unspecified)

## package 'rmarkdown' successfully unpacked and MD5 sums checked
## 
## The downloaded binary packages are in
##  C:\Users\tswaminathan\AppData\Local\Temp\RtmpGufOD3\downloaded_packages

install.packages("xlsx",repos = "http://cran.us.r-project.org")

## Installing package into 'C:/Users/tswaminathan/Documents/R/win-library/3.5'
## (as 'lib' is unspecified)

## package 'xlsx' successfully unpacked and MD5 sums checked
## 
## The downloaded binary packages are in
##  C:\Users\tswaminathan\AppData\Local\Temp\RtmpGufOD3\downloaded_packages

install.packages("rjava",repos = "http://cran.us.r-project.org")

## Installing package into 'C:/Users/tswaminathan/Documents/R/win-library/3.5'
## (as 'lib' is unspecified)

## Warning: package 'rjava' is not available (for R version 3.5.1)

## Warning: Perhaps you meant 'rJava' ?

# install.packages("yaml",repos = "http://cran.us.r-project.org")
install.packages("ggplot2",repos = "http://cran.us.r-project.org")

## Installing package into 'C:/Users/tswaminathan/Documents/R/win-library/3.5'
## (as 'lib' is unspecified)

## package 'ggplot2' successfully unpacked and MD5 sums checked
## 
## The downloaded binary packages are in
##  C:\Users\tswaminathan\AppData\Local\Temp\RtmpGufOD3\downloaded_packages

library(cluster)
library(fpc)
# library(NbClust)
library(dendextend)

## 
## ---------------------
## Welcome to dendextend version 1.9.0
## Type citation('dendextend') for how to cite the package.
## 
## Type browseVignettes(package = 'dendextend') for the package vignette.
## The github page is: https://github.com/talgalili/dendextend/
## 
## Suggestions and bug-reports can be submitted at: https://github.com/talgalili/dendextend/issues
## Or contact: <tal.galili@gmail.com>
## 
##  To suppress this message use:  suppressPackageStartupMessages(library(dendextend))
## ---------------------

## 
## Attaching package: 'dendextend'

## The following object is masked from 'package:stats':
## 
##     cutree

View(crime)

# Normalizing continuous columns to bring them under same scale
normalized_data<-scale(crime[,2:5]) #excluding the ID from spreadsheet
d <- dist(normalized_data, method = "euclidean") # distance matrix
fit <- hclust(d, method="complete")

fit <- as.dendrogram(fit)
cd = color_branches(fit,k=4)
plot(cd) # display dendrogram

plot(fit, hang=-1)

## Warning in plot.window(...): "hang" is not a graphical parameter

## Warning in plot.xy(xy, type, ...): "hang" is not a graphical parameter

## Warning in axis(side = side, at = at, labels = labels, ...): "hang" is not
## a graphical parameter

## Warning in axis(side = side, at = at, labels = labels, ...): "hang" is not
## a graphical parameter

## Warning in title(...): "hang" is not a graphical parameter

# rect.hclust(fit, k=2, border="red")
groups <- cutree(fit, k=4) # cut tree into 4 clusters

table(groups)

## groups
##  1  2  3  4 
##  8 11 21 10

Crime_Rate_Categories<-as.matrix(groups) # groups or cluster numbers
final <- data.frame(crime, Crime_Rate_Categories)

final1 <- final[,c(ncol(final),1:(ncol(final)-1))]

View(final1)


# setwd("C:/Users/tswaminathan/Desktop/Other Desktop Docs Recent/R Prog Assignment/Clustering/Output")


# write.csv(final1, file="Crime_Final.csv",row.names = F)


aggregate(crime[,-1],by=list(final$Crime_Rate_Categories),mean)

##   Group.1    Murder  Assault UrbanPop     Rape
## 1       1 14.087500 252.7500 53.50000 24.53750
## 2       2 11.054545 264.0909 79.09091 32.61818
## 3       3  5.871429 134.4762 70.76190 18.58095
## 4       4  3.180000  78.7000 49.30000 11.63000