training/src/processing/utils/presc_common.py

import pandas as pd
from utils.common import read_data


steroid_codes = ['0603020T0AAACAC', '0603020T0AABKBK', '0603020T0AAAXAX',
                 '0603020T0AAAGAG', '0603020T0AABHBH', '0603020T0AAACAC',
                 '0603020T0AABKBK', '0603020T0AABNBN', '0603020T0AAAGAG',
                 '0603020T0AABHBH']

antib_codes = ['0501013B0AAAAAA', '0501013B0AAABAB', '0501030I0AAABAB',
               '0501030I0AAAAAA', '0501050B0AAAAAA', '0501050B0AAADAD',
               '0501013K0AAAJAJ']

exac_meds = steroid_codes + antib_codes


def initialize_presc_data(presc_file):
    """
    Load in prescribing dataset to correct format
    --------
    :param presc_file: prescribing data file name
    :return: prescribing dataframe with correct column names and types
    """
    print('Loading prescribing data')

    # Read in data
    presc_cols = ['SafeHavenID', 'PRESC_DATE', 'PI_Approved_Name',
                  'PI_BNF_Item_Code']
    presc_types = ['int', 'object', 'str', 'str']
    df = read_data(presc_file, presc_cols, presc_types)

    # Drop any nulls or duplicates
    df = df.dropna()
    df = df.drop_duplicates()
    
    # Convert date
    df['PRESC_DATE'] = pd.to_datetime(df.PRESC_DATE)

    return df


def track_medication(df):
    """
    Track salbutamol and rescue med prescriptions
    https://openprescribing.net/bnf/
    --------
    :param df: dataframe
    :return: dataframe with tracked meds
    """
    print('Tracking medication')

    # Extract BNF codes without brand info
    df['code'] = df.PI_BNF_Item_Code.apply(lambda x: x[0:9])

    # Add flag for salbutamol - marked important by Chris
    df['SALBUTAMOL'] = (df.code == '0301011R0').astype(int)

    # Track rescue meds
    df['rescue_meds'] = df.PI_BNF_Item_Code.str.contains(
        '|'.join(exac_meds)).astype(int)

    # Track anxiety and depression medication
    ad_bnf = ('040102', '0403', '0204000R0', '0408010AE')
    ad_events = df.PI_BNF_Item_Code.str.startswith(ad_bnf).fillna(False)
    drop_dummy = (df.PI_Approved_Name != 'DUMMY') & (df.PI_Approved_Name != 'DUMMY REJECTED')
    df['anxiety_depression_presc'] = (drop_dummy & ad_events).astype(int)

    return df