Decision Tree

Assignment 26

#install.packages("C50")
#install.packages("tree")

library(C50)

## Warning: package 'C50' was built under R version 3.5.1

library(tree)

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

mydata <- read.csv("C:\\Users\\RISHI RAHUL\\Desktop\\DS\\10 Decision Trees\\Assignment\\Fraud_check.csv")

colnames(mydata)

## [1] "Undergrad"       "Marital.Status"  "Taxable.Income"  "City.Population"
## [5] "Work.Experience" "Urban"

TIRisky <- NULL
TIRisky <- ifelse(mydata$Taxable.Income<=30000,1,0)
mydata[,"TIRisky"] <- TIRisky

mydata$Undergrad <- as.factor(mydata$Undergrad)
mydata$Marital.Status <- as.factor(mydata$Marital.Status)
mydata$Urban <- as.factor(mydata$Urban)
mydata$TIRisky <- as.factor(mydata$TIRisky)




fraud_risky <- mydata[mydata$TIRisky == "1",] 
fraud_not_risky <- mydata[mydata$TIRisky == "0",]

data_train <- rbind(fraud_risky[1:93,], fraud_not_risky[1:357,])
data_test <- rbind(fraud_risky[94:124,], fraud_not_risky[357:476,])

trained_model <- C5.0(data_train[,-c(7)], data_train$TIRisky)
plot(trained_model)

mean(data_train$TIRisky == predict(trained_model, data_train))

## [1] 1

pred_test <- predict(trained_model, newdata = data_test)

mean(pred_test == data_test$TIRisky)

## [1] 1

#install.packages("gmodels")
library(gmodels)

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

CrossTable(data_test$TIRisky, pred_test)

## 
##  
##    Cell Contents
## |-------------------------|
## |                       N |
## | Chi-square contribution |
## |           N / Row Total |
## |           N / Col Total |
## |         N / Table Total |
## |-------------------------|
## 
##  
## Total Observations in Table:  151 
## 
##  
##                   | pred_test 
## data_test$TIRisky |         0 |         1 | Row Total | 
## ------------------|-----------|-----------|-----------|
##                 0 |       120 |         0 |       120 | 
##                   |     6.364 |    24.636 |           | 
##                   |     1.000 |     0.000 |     0.795 | 
##                   |     1.000 |     0.000 |           | 
##                   |     0.795 |     0.000 |           | 
## ------------------|-----------|-----------|-----------|
##                 1 |         0 |        31 |        31 | 
##                   |    24.636 |    95.364 |           | 
##                   |     0.000 |     1.000 |     0.205 | 
##                   |     0.000 |     1.000 |           | 
##                   |     0.000 |     0.205 |           | 
## ------------------|-----------|-----------|-----------|
##      Column Total |       120 |        31 |       151 | 
##                   |     0.795 |     0.205 |           | 
## ------------------|-----------|-----------|-----------|
## 
##