df = demographic_data.drop(["est_age",'cons_n2mob','cons_n2pbl','cons_n2pmv'],axis=1).dropna() df # In[129]: from sklearn.preprocessing import OneHotEncoder df=OneHotEncoder().fit_transform(df) # In[134]: df=df.apply(LabelEncoder().fit_transform) # In[135]: from sklearn.feature_selection import chi2 # In[137]: X = df.drop(['transportation_issues','person_id_syn'],axis=1) y = df['transportation_issues']
