training/src/reduction/post_proc_reduction.py

import json
import pandas as pd


single_inhaler = ['saba_inhaler_per_year', 'laba_inhaler_per_year',
                  'lama_inhaler_per_year', 'sama_inhaler_per_year',
                  'ics_inhaler_per_year', 'mcs_inhaler_per_year']
double_inhaler = ['laba_ics_inhaler_per_year', 'saba_sama_inhaler_per_year']
triple_inhaler = 'lama_laba_ics_inhaler_per_year'
adm_cols = ['copd_per_year', 'resp_per_year']


def main():

    # Load in config items
    with open('../../../config.json') as json_config_file:
        config = json.load(json_config_file)
    data_path = config['model_data_path']

    # Read in original data before scaling
    df = pd.read_pickle(data_path + 'merged_full.pkl')

    # Create new reduced columns
    df['single_inhaler'] = df[single_inhaler].sum(axis=1)
    df['double_inhaler'] = df[double_inhaler].sum(axis=1)
    df['triple_inhaler'] = df[triple_inhaler]
    df['copd_resp_per_year'] = df[adm_cols].sum(axis=1)

    # Drop original columns
    cols2drop = single_inhaler + double_inhaler + [triple_inhaler] + adm_cols
    df = df.drop(cols2drop, axis=1)

    # Save data
    df.to_pickle(data_path + 'merged.pkl')


main()