DATA CLUSTERING EXAMPLE

library("randomForest")

## Warning: package 'randomForest' was built under R version 3.5.1

## randomForest 4.6-14

## Type rfNews() to see new features/changes/bug fixes.

library(Metrics)

## Warning: package 'Metrics' was built under R version 3.5.1

mydata <- read.csv(paste("stock_data.csv", sep=""))
View(mydata)

Checking for dimensions of the data

dim(mydata)

## [1] 3000  101

Specifying Outcome variable as factor variable

mydata$Y<-as.factor(mydata$Y)

Dividing the data set into train and test

train<-mydata[1:2000,]
test<-mydata[2001:3000,]

Applying Random Forest

m_rf<-randomForest(Y~.,data=train)
prd<-predict(object=m_rf,test[,-101])
table(prd)

## prd
##  -1   1 
## 875 125

Checking Accuracy

auc(prd,test$Y)

## [1] 0.4622857

Accuracy we get hers is 47% approximately. We create 5 clusters based on values of independent variables using k-means clustering and reapply random forest.

combing test and train

all<-rbind(train,test)

Creating 5 clusters using k means clustering

Cluster <- kmeans(all[,-101], 5)

Adding clusters as independent variable to the dataset.

all$cluster<-as.factor(Cluster$cluster)

Dividing the dataset into train and test

train<- all[1:2000,]
test<- all[2001:3000,]

Applying Random Forest

m_rf1<-randomForest(Y~.,data=train)
prd2<-predict(object=m_rf1,test[,-101])
table(prd2)

## prd2
##  -1   1 
## 180 820

Checking Acccuracy

auc(prd2,test$Y)

## [1] 0.4788618