copd-model-e / training /src /processing /utils /comorb_processing.py
IamGrooooot's picture
Model E: Unsupervised PCA + clustering risk stratification
53a6def
raw
history blame contribute delete
682 Bytes
"""
Comorbidities processing utilities
"""
import pandas as pd
def diagnosis_mapping_lists(excel_file, sheet_name, diagnosis_names):
"""
Create mapping between diagnoses and comorbidities
--------
:param excel_file: str filename for diagnosis mapping
:param sheet_name: str sheet name for diagnosis mapping
:param diagnosis_names: str list of diagnoses
:return: dictionary of diagnosis names and values
"""
df_diag = pd.read_excel(excel_file, sheet_name, skiprows=range(0, 1))
df_lists = df_diag.T.values.tolist()
diag_lists = [[s.strip() for s in x if pd.notna(s)] for x in df_lists]
return dict(zip(diagnosis_names, diag_lists))