File size: 6,837 Bytes
53a6def | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 | """
To Do:
- Refactor script to be more readable/smaller main function
"""
import json
import pandas as pd
import numpy as np
from datetime import timedelta
def read_pkl_data(dataset, data_path, path_type):
"""
Read in pickled dataset
--------
:param dataset: type of dataset to read in
:param data_path: path to generated data
:param path_type: type of path to read from
:return: dataframe
"""
print('Reading in ' + dataset)
file_path = data_path + dataset
if path_type == 'data':
file_path += '_proc.pkl'
else:
file_path += '_first_dates.pkl'
return pd.read_pickle(file_path)
def fill_eth_grp_data(df):
"""
Fill nulls in eth_grp column introduced in joining
:param df: dataframe to update
:return: Filled dataframe
"""
df['eth_grp'] = df.groupby('SafeHavenID').eth_grp.apply(
lambda x: x.ffill().bfill())
df['eth_grp'] = df['eth_grp'].fillna('Unknown')
return df
def fill_to_date_columns(df):
"""
Fill nulls in to_date columns introduced in joining
:param df: dataframe to update
:return: Filled dataframe
"""
to_date_cols = ['adm_to_date', 'copd_to_date', 'resp_to_date',
'presc_to_date', 'rescue_to_date', 'labs_to_date',
'anxiety_depression_to_date',
'anxiety_depression_presc_to_date']
df[to_date_cols] = df.groupby('SafeHavenID')[to_date_cols].apply(
lambda x: x.ffill().fillna(0))
return df
def fill_yearly_columns(df):
"""
Fill nulls in yearly columns introduced in joining
:param df: dataframe to update
:return: Filled dataframe
"""
zero_cols = ['adm_per_year', 'total_hosp_days', 'mean_los',
'copd_per_year', 'resp_per_year', 'comorb_per_year',
'salbutamol_per_year',
'saba_inhaler_per_year', 'laba_inhaler_per_year',
'lama_inhaler_per_year', 'sama_inhaler_per_year',
'ics_inhaler_per_year', 'laba_ics_inhaler_per_year',
'lama_laba_ics_inhaler_per_year', 'saba_sama_inhaler_per_year',
'mcs_inhaler_per_year', 'rescue_meds_per_year',
'presc_per_year', 'labs_per_year',
'anxiety_depression_per_year', 'anxiety_depression_presc_per_year']
df[zero_cols] = df[zero_cols].fillna(0)
return df
def fill_days_since(df, typ):
"""
Fill days_since_copd/resp/rescue
:param df: dataframe to update
:param typ: type of feature to fill ('copd', 'resp', 'rescue')
:return: Filled dataframe
"""
df['days_since_' + typ] = df.eoy - df[typ + '_date'].ffill()
return df
def process_first_dates(df):
"""
Process dataframe containing patient's first date in the health board region
--------
:param df: dataframe to process
:return: processed dataframe
"""
df = df.set_index('SafeHavenID')
entry_dataset = df.idxmin(axis=1).apply(lambda x: x.split('_')[1])
first_entry = df.min(axis=1)
df['entry_dataset'] = entry_dataset
df['first_entry'] = first_entry
df_reduced = df[['entry_dataset', 'first_entry']].reset_index()
return df_reduced
def find_closest_simd(v):
"""
Find closest SIMD vigintile for each row 'v'
--------
:param v: row of data from apply statement
:param typ: type of simd column to add
:return: simd value
"""
simd_years = [2009, 2012, 2016]
bools = [v.eoy.year >= year for year in simd_years]
if any(bools):
simd_year = str(simd_years[np.where(bools)[0][-1]])
v['simd_quintile'] = v['simd_' + simd_year + '_quintile']
v['simd_decile'] = v['simd_' + simd_year + '_decile']
v['simd_vigintile'] = v['simd_' + simd_year + '_vigintile']
else:
v['simd_quintile'] = np.nan
v['simd_decile'] = np.nan
v['simd_vigintile'] = np.nan
return v
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 data
adm = read_pkl_data('adm', data_path, 'data')
comorb = read_pkl_data('comorb', data_path, 'data')
presc = read_pkl_data('presc', data_path, 'data')
labs = read_pkl_data('labs', data_path, 'data')
demo = read_pkl_data('demo', data_path, 'data')
# Join datasets
df = adm.join(
comorb, how='left').join(
presc, how='outer').join(
labs, how='outer')
df = df.reset_index()
# Fill nulls introduced in joining
print('Filling data')
df = fill_eth_grp_data(df)
df = fill_to_date_columns(df)
df = fill_yearly_columns(df)
# Fill days_since columns
for typ in ['copd', 'resp', 'rescue', 'adm']:
df = df.groupby('SafeHavenID').apply(fill_days_since, typ)
# Reduce to single column
ds_cols = ['days_since_copd', 'days_since_resp']
df['days_since_copd_resp'] = df[ds_cols].min(axis=1)
# Read in first date data
print('Adding first dates')
adm_dates = read_pkl_data('adm', data_path, 'date')
presc_dates = read_pkl_data('presc', data_path, 'date')
labs_dates = read_pkl_data('labs', data_path, 'date')
# Merge first date data
first_dates = pd.merge(
pd.merge(adm_dates, presc_dates, how="outer", on='SafeHavenID'),
labs_dates, how="outer", on='SafeHavenID')
# Save first dates if needed
first_dates.to_pickle(data_path + 'overall_first_dates.pkl')
# Process first_years
date_data = process_first_dates(first_dates)
# Merge first dates data with dataframe
print('Merging data')
df_merged = pd.merge(df, date_data, on='SafeHavenID', how='inner')
# Add years in health board region
ggc_years = (df_merged.eoy - df_merged.first_entry) / np.timedelta64(1, 'Y')
df_merged['ggc_years'] = round(ggc_years)
# Merge demographics
df_merged = pd.merge(df_merged, demo, on='SafeHavenID')
# Calculate age relative to end of year
dt_diff = df_merged.eoy - pd.to_datetime(df_merged.obf_dob)
df_merged['age'] = dt_diff // timedelta(days=365.2425)
# Find closest SIMD
df_merged = df_merged.apply(find_closest_simd, axis=1)
# Drop additional columns
cols2drop = ['copd_date', 'resp_date', 'adm_date', 'rescue_date',
'simd_2009_quintile', 'simd_2009_decile',
'simd_2009_vigintile', 'simd_2012_quintile',
'simd_2012_decile', 'simd_2012_vigintile',
'simd_2016_quintile', 'simd_2016_decile',
'simd_2016_vigintile', 'days_since_copd',
'days_since_resp']
df_merged = df_merged.drop(cols2drop, axis=1)
# Save dataset
df_merged.to_pickle(data_path + 'merged_full.pkl')
main()
|