starbucks_post_4.py

'''Cleaning the *Profile* dataset'''
profile = profile.dropna(axis=0, subset=['gender', 'income']);
profile_gender = profile['gender'].str.get_dummies()
profile_gender.columns = ['gender_' + col for col in profile_gender.columns];
# Separate date attributes into year, month, and day, converting to integers.
profile_date = profile['became_member_on'];

profile_year = profile_date.apply(lambda d: str(d)).str[0:4].astype('int').rename('member_year');
profile_month = profile_date.apply(lambda d: str(d)).str[4:6].astype('int').rename('member_month');
profile_day = profile_date.apply(lambda d: str(d)).str[6:8].astype('int').rename('member_day');

profile = pd.concat([profile, profile_gender, profile_year, profile_month, profile_day], axis=1);

profile = profile.drop(['became_member_on', 'gender'], axis=1);