Final Exam Part $1$: Decision Trees

For Part $1$ of the final exam, you wil use the iris data set to construct a decision tree. You will be using the packages party and rpart to construct your decision tree.

To begin, we will import the iris data set and create training and test sets.

summary$($iris$)$

set.seed$(55)$ # for data partition

ind $<-$ sample$(2,$ nrow$($iris$),$ replace $=$ TRUE, prob $=$ c$(0\mathrm{.}8,0\mathrm{.}2))$

train $<-$ iris$[$ind $==1,]$

test $<-$ iris$[$ind $==2,]$

Using the output tree construct a decision tree with the function rpart with the output Species regressed on all of the explanatory variables $($use a period symbol for this $.).$ Perform this on the entire training set.

library$($party$)$ # for decision tree model

library$($rpart$)$

library$($rpart$.$plot$)$ # for decision tree plot drawing

Student's answer$($Top$)$

# Load the required libraries

library$($party$)$

library$($rpart$)$

library$($rpart$.$plot$)$

# Set the seed for reproducibility

set.seed$(55)$

# Create training and test sets

ind $<-$ sample$(2,$ nrow$($iris$),$ replace $=$ TRUE, prob $=$ c$(0\mathrm{.}8,0\mathrm{.}2))$

train $<-$ iris$[$ind $==1,]$

test $<-$ iris$[$ind $==2,]$

# Construct a decision tree with rpart

tree $<-$ rpart$($Species ~ $.,$ data $=$ train$)$

# Plot the decision tree

rpart.plot$($tree$)$

Grade cell: cell$-5393427620$f$5$d$754$Score: $100\mathrm{.}0/100\mathrm{.}0($Top$)$

Hidden Tests Redacted

Congratulations! All test cases in this cell passed.

The question below needs to answered

After this use the rpart function to plot he tree.