fair-splits-without-sex.py

# add data splits to the collection we just created
year_begin = 2014
year_end = 2016 # exclusive
states = ['CA', 'NY']


for year in range(year_begin, year_end):
   for state in states:
       tru.add_data_split(f'{year}-{state}',
         pre_data = data[year][state]['data_preprocessed'].\
            drop('Sex', axis = 1), # drop sex from pre-data
         post_data = data[year][state]['data_postprocessed'].\
            drop(['Sex_Female','Sex_Male'], axis = 1), # drop sex from post-data
         label_data = data[year][state]['label'],
         extra_data_df = data[year][state]['extra_data'].\
            reset_index(drop=True).\
               join(data[year][state]['data_preprocessed']['Sex'].reset_index(drop=True)), # add sex to extra data
         split_type = "all")