Scribd
Upload
200 views5 pages

Car Seats R Code

This document describes using a classification tree to predict whether car seat sales are high or low based on various attributes. It first creates a training and test dataset, fits a classification tree to the training data, and evaluates the tree's performance on the test data. It then uses cross-validation to determine the optimal tree size, prunes the tree accordingly, and evaluates the pruned tree's performance. Finally, it generates an ROC curve to evaluate the tree's predictive ability.

Uploaded by

nvnkmr9999
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
200 views5 pages

Car Seats R Code

This document describes using a classification tree to predict whether car seat sales are high or low based on various attributes. It first creates a training and test dataset, fits a classification tree to the training data, and evaluates the tree's performance on the test data. It then uses cross-validation to determine the optimal tree size, prunes the tree accordingly, and evaluates the pruned tree's performance. Finally, it generates an ROC curve to evaluate the tree's predictive ability.

Uploaded by

nvnkmr9999
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

CarSeats: Classification Tree

# Attach the library


# Loading the library

library(ISLR)

## Warning: package 'ISLR' was built under R version 3.3.3

library(tree)

## Warning: package 'tree' was built under R version 3.3.3

# Attach the data set


attach(Carseats)

# Creating the dummy variable for Sales


High=ifelse(Sales<=8,"No","Yes")
Carseats=data.frame(Carseats,High)

# Creating the Training and Test Data set


set.seed(2)
train=sample(1:400, 200)
Carseats.test=Carseats[-train,]
High.test=High[-train]

# Fitting the Classification Tree


tree.carseats=tree(High~.-Sales,Carseats,subset=train)

# Plotting the tree


plot(tree.carseats)
text(tree.carseats,pretty=0)
# Prediction for Test Data
tree.pred=predict(tree.carseats,Carseats.test,type="class")

# Confusion Matrix
table(tree.pred,High.test)

## High.test
## tree.pred No Yes
## No 86 27
## Yes 30 57

# Deciding the Optimal Size using Cross Validation


set.seed(3)
cv.carseats=cv.tree(tree.carseats,FUN=prune.misclass)
names(cv.carseats)

## [1] "size" "dev" "k" "method"

cv.carseats

## $size
## [1] 19 17 14 13 9 7 3 2 1
##
## $dev
## [1] 55 55 53 52 50 56 69 65 80
##
## $k
## [1] -Inf 0.0000000 0.6666667 1.0000000 1.7500000 2.0000000
## [7] 4.2500000 5.0000000 23.0000000
##
## $method
## [1] "misclass"
##
## attr(,"class")
## [1] "prune" "tree.sequence"

# Plotting Cross-Validation Error against Size


plot(cv.carseats$size,cv.carseats$dev,type="b")

# Pruning the Tree


prune.carseats=prune.misclass(tree.carseats,best=9)
plot(prune.carseats)
text(prune.carseats,pretty=0)

# Predition for the Test Data Set using Pruned Tree


tree.pred=predict(prune.carseats,Carseats.test,type="class")

#Confusion Matrix
table(tree.pred,High.test)

## High.test
## tree.pred No Yes
## No 94 24
## Yes 22 60
# Predition for the Test Data Set using Pruned Tree
tree.prob=predict(prune.carseats,Carseats.test,type="vector")[,2]

# ROC Plot
library(pROC)

## Warning: package 'pROC' was built under R version 3.3.3

## Type 'citation("pROC")' for a citation.

##
## Attaching package: 'pROC'

## The following objects are masked from 'package:stats':


##
## cov, smooth, var

roc(High.test,tree.prob)

##
## Call:
## roc.default(response = High.test, predictor = tree.prob)
##
## Data: tree.prob in 116 controls (High.test No) < 84 cases (High.test Yes).
## Area under the curve: 0.7788

plot(roc(High.test,tree.prob),col="blue",legacy.axes = TRUE)

You might also like