Question

Data mining-->

1. Please Perform Principal Component Analysis and K-Means Clustering on the Give dataset Below. [50 Points]

   Dataset Link : https://dataminingcsc6740.s3-us-west-2.amazonaws.com/datasets/homework_2.csv

   10 Points for Data Preprocessing.

   15 Points for PCA Algorithm along with plots and Results Explaination.

   15 Points for K-Means Algorithm with plots and Results Explination.

   10 Points for Comparing the results between PCA and K-Means and whats your infer- ence from your ouputs of the algorithms.

   Hints:
   As per the data preprocessing step convert all the variables in the dataset into Numerical

   values as the algorithms only work with Numerical values
   Then Apply both algorithms one after the other then plot the output clusters Compare the output clusters in both the steps.

Answer 1

In data mining, I have used R language platform as an IDE

The code is here with k means clustering and principal component analysis(PCA)

#load dataset

library(ggplot2)

library(ggthemes)

library(GGally)

library(dplyr)

library(Metrics)

homework_2 <- read.csv("C:/Users/CST2019/Downloads/homework_2.csv", sep=";")

# structure of dataset

str(homework_2)

#required libraries

require(dplyr)

# pre processing and convet categorical values to numeric values

homework_2$default<-as.numeric(homework_2$default)

str(homework_2)

homework_2$housing<-as.numeric(homework_2$housing)

str(homework_2)

homework_2$loan<-as.numeric(homework_2$loan)

str(homework_2)

homework_2$poutcome<-as.numeric(homework_2$poutcome)

str(homework_2)

homework_2$y<-as.numeric(homework_2$y)

str(homework_2)

homework_2$month<-as.numeric(homework_2$month)

str(homework_2)

homework_2$contact<-as.numeric(homework_2$contact)

str(homework_2)

homework_2$job<-as.numeric(homework_2$job)

str(homework_2)

homework_2$marital<-as.numeric(homework_2$marital)

str(homework_2)

homework_2$education<-as.numeric(homework_2$education)

str(homework_2)

#over all summary

summary(homework_2)

str(homework_2)

#plots

hist(homework_2$age)

hist(homework_2$marital)

hist(homework_2$education)

hist(homework_2$default)

hist(homework_2$balance)

hist(homework_2$housing)

hist(homework_2$loan)

#k means clustering

kmeans(homework_2, 3)

cor<-cor(homework_2)

library(corrplot)

#CORRELARTION MATRIX

corrplot(cor,method="number")

library(caTools)

sample = sample.split(homework_2,SplitRatio = 0.70) # splits the data in the ratio mentioned in SplitRatio. After splitting marks these rows as logical TRUE and the the remaining are marked as logical FALSE

train1 =subset(homework_2,sample ==TRUE) # creates a training dataset named train1 with rows which are marked as TRUE

test1=subset(homework_2, sample==FALSE)

summary(train1)

summary(test1)

#PCA algorithm

prin_comp <- prcomp(train1, scale. = T)

names(prin_comp)

prin_comp$center

prin_comp$scale

prin_comp$rotation

biplot(prin_comp, scale = 0)

std_dev <- prin_comp$sdev

std_dev

#compute variance

pr_var <- std_dev^2

pr_var

#check variance of first 10 components

pr_var[1:10]

#proportion of variance explained

prop_varex <- pr_var/sum(pr_var)

prop_varex[1:20]

#add a training set with principal components

train.data <- data.frame(pdays = train1$pdays, prin_comp$x)

#we are interested in first 10 PCAs

train.data <- train.data[,1:10]

#run a decision tree

install.packages("rpart")

library(rpart)

rpart.model <- rpart(pdays ~ . , data = train.data, method = "anova")

rpart.model

#transform test into PCA

test.data <- predict(prin_comp, newdata = test1)

test.data <- as.data.frame(test.data)

#select the first 10 components

test.data <- test.data[,1:10]

#make prediction on test data

rpart.prediction <- predict(rpart.model, test.data)