copd-model-e / training /src /processing /misc /process_validation_adm.py
IamGrooooot's picture
Model E: Unsupervised PCA + clustering risk stratification
53a6def
raw
history blame contribute delete
788 Bytes
from utils.adm_common import (initialize_adm_data, correct_stays,
track_copd_resp)
def main():
# Load in data
adm_file = "<YOUR_DATA_PATH>/EXAMPLE_STUDY_DATA/SMR01_Cohort3R.csv"
adm = initialize_adm_data(adm_file)
# Fill null STAY data and combine transfer admissions
adm = correct_stays(adm)
# Track COPD and respiratory events
adm = track_copd_resp(adm)
# Select relevant columns
adm_reduced = adm[['SafeHavenID', 'ADMDATE', 'copd_event', 'resp_event']]
# Track events
adm_reduced['copd_resp_event'] = adm_reduced['copd_event'] | adm_reduced['resp_event']
adm_reduced['adm_event'] = 1
# Save data
adm_reduced.to_pickle('<YOUR_DATA_PATH>/Model_E_Extracts/validation_adm_proc-og.pkl')
main()