#output_dir = (r'C:\Users\theism\Documents\Dimagi\Data\person_phone_aadhar-ap-anantapur2\test')
#case_data_regex = re.compile(r'cases_\d\d\d.csv')
# ------------- don't edit below here -----------------------------
gen_func.start_logging(output_dir)
logging.info('Starting scripts to analyze aadhar data...')
# combine all csv into one dataframe
case_df = gen_func.csv_files_to_df(target_dir, case_data_regex, case_date_cols,
cols_to_use)
# clean case data and start to get age distribution information
output_dict = {}
case_clean_df, output_dict = case_func.clean_case_data(case_df, output_dict)
case_clean_df = case_func.add_age_info(case_clean_df)
location_column_names = ['doc_id', 'district_name']
case_clean_df = gen_func.add_locations(case_clean_df, 'owner_id',
location_column_names)
case_clean_df = case_clean_df.loc[(
case_clean_df['state_name'].isin(real_state_list))]
logging.info(case_clean_df['sex'].value_counts())
logging.info(case_clean_df['age_bracket'].value_counts())
clean_case_age_dist = case_clean_df.groupby(['age_bracket',
'sex']).count()['caseid']
logging.info(clean_case_age_dist)
#case_clean_df = case_clean_df[(case_clean_df['district_name'] == 'WestGodavari')]
logging.info('------ FEMALE 15-49 -----------------')
target_clean_df = case_clean_df[(case_clean_df['sex'] == 'F') &
phone_output_dict = {'location': location_name}
# combine all csv into one dataframe
case_df = gen_func.csv_files_to_df(os.path.join(target_dir, folder),
case_data_regex, case_date_cols)
if user_case:
case_df['phone_number'] = np.nan
case_df['phone_number'] = case_df.apply(
lambda row: row['aww_phone_number']
if (row['aww_phone_number'] != '---') & (row[
'aww_phone_number'] != np.nan) else row['ls_phone_number'],
axis=1)
# clean case data
case_clean_df, phone_output_dict = case_func.clean_case_data(
case_df, phone_output_dict, awc_test=False)
# truncate data based on open date if so desired
if use_opened_cutoff:
logging.info('Removing any cases opened before %s' %
opened_cutoff_date)
case_clean_df = case_clean_df[
case_clean_df['opened_date'] >= opened_cutoff_date]
# if the case type is for a user, rather than belonging to a user
if user_case:
case_clean_df = gen_func.add_usertype_from_id(
case_df, 'commcare_location_id')
logging.info(
'User distribution by type for open, non-test user cases:')
logging.info(case_clean_df['location_type'].value_counts())