For Exercises $1$ to $4,$ work with the adult$\_$ch$6\_$training and adult$\_$ch$6\_$test data sets.

Use either Python to solve each problem. Import required packages as shown below

$1.$ # import required packages

$2.$ import os

$3.$ import graphviz

$4.$ import pandas as pd

$5.$ import numpy as np

$6.$ import statsmodels.tools.tools as stattools

$7.$ from sklearn.tree import DecisionTreeClassifier, export$\_$graphviz

$8.$

$9.$ # read the csv adult$\_$ch$6\_$training data using the pandas package

$10.$ adult$\_$tr $=$ pd$.$read$\_$csv$("/$Users$/$markmaxwell$/$Desktop$/$Website Data Sets$/$adult$\_$ch$6\_$training

$")$

$11.$

$12.$ # read the csv adult$\_$ch$6\_$test data using the pandas package

$13.$ adult$\_$test $=$ pd$.$read$\_$csv$("/$Users$/$markmaxwell$/$Desktop$/$Website Data Sets$/$adult$\_$ch$6\_$test"$)$

$1.$

Create a CART model using the training data set that predicts income using marital status and capital

gains and losses. Visualize the decision tree $($that is$,$ provide the decision tree output$).$ Describe the first

few splits in the decision tree.

$2.$

Develop a CART model using the test data set that utilizes the same target and predictor variables.

Visualize the decision tree. Compare the decision trees. Does the test data result match the training

data result?

$3.$

Use the training data set to build a C$5\mathrm{.}0$ model to predict income using marital status and capital

gains and losses. Specify a minimum of $75$ cases per terminal node. Visualize the decision tree.

Describe the first few splits in the decision tree.

$4.$ How does your C$5\mathrm{.}0$ model compare to the CART model? Describe the similarities and differences.