import statsmodels.tools.tools as stattools import pandas as pd import numpy as np from sklearn.tree import DecisionTreeClassifier, export_graphviz adult_tr = pd.read_csv(‘~/Desktop/Dataset_Assignment/adult_ch6_training’, usecols=[‘Marital status’,’Income’,’Cap_Gains_Losses’]) y = adult_tr[[‘Income’]] mar_np = np.array(adult_tr[‘Marital status’]) (mar_cat, mar_cat_dict) = stattools.categorical(mar_np, drop=True, dictnames = True) mar_cat_pd = pd.DataFrame(mar_cat) X = pd.concat((adult_tr[[‘Cap_Gains_Losses’]], mar_cat_pd), axis = 1) X_names = [“Cap_Gains_Losses”, “Divorced”, “Married”, “Never-married”, “Separated”, “Widowed”] […]