def japan_hospitalizations(params): data_df = load_utils.default_read_function(params) data_df['deaths_cumulative'] = data_df['deaths_cumulative'].replace( to_replace='-', value=0).astype('int32') data_df = region_utils.join_region_codes(data_df, params) data_df = region_utils.aggregate_and_append(data_df, params) return data_df
def default_load_function(params): df = load_utils.default_read_function(params) df = region_utils.join_region_codes(df, params) load_params = params['load'] if 'regions' in load_params: if 'aggregate_by' in load_params['regions']: df = region_utils.aggregate_and_append(df, params) df = load_utils.compute_cumulative_from_new(df, params) return df
def scotland_hospitalizations(data_path, params): df = pd.read_excel(data_path, 'Table 2 - Hospital Care', skiprows=4) df = df.rename(columns={ df.columns[1]: 'icu_current', df.columns[4]: 'hospitalized_current', }) df = date_utils.parse_date(df, params) df = region_utils.join_region_codes(df, params) return df
def scotland_hospitalizations(params): data_path = path_utils.most_recent_data(params)['path'] df = pd.read_excel(data_path, 'Table 2 - Hospital Care', skiprows=4) df = df.rename(columns={ df.columns[1]: "icu_current", df.columns[4]: "hospitalized_current", }) df = date_utils.parse_date(df, params) df = region_utils.join_region_codes(df, params) return df
def default_load_function(data_path, params): df = load_utils.default_read_function(data_path, params) df = region_utils.join_region_codes(df, params) duplicates = df[df[['region_code', 'date']].duplicated(keep=False)] if duplicates.shape[0] != 0: logging.warning( 'Dropping the following duplicate data for %s data source:\n%s', params['config_key'], duplicates[['region_code', 'date']]) df = df.drop_duplicates(subset=['region_code', 'date'], keep='first') load_params = params['load'] if 'regions' in load_params: if 'aggregate_by' in load_params['regions']: df = region_utils.aggregate_and_append(df, params) df = load_utils.compute_cumulative_from_new(df, params) return df