import pandas as pd
import numpy as np

IHME_COD_FILEPATH = "./IHME_GBD_2019_COD_CAUSE_ICD_CODE_MAP_Y2020M10D15.XLSX"
IHME_NONFATAL_FILEPATH = "./IHME_GBD_2019_NONFATAL_CAUSE_ICD_CODE_MAP_Y2020M10D15.XLSX"
ICD10CM_ORDER_FILEPATH = "./icd10-2019_categories_only.psv"

#READ in ICD10CM codes

icd10_codes = {}

with open(ICD10CM_ORDER_FILEPATH,"r") as icd_fh:
    for idx,line in enumerate(icd_fh.readlines()):
        code, descr = line.split("|")
        code = code.strip()
        descr = descr.strip()
        icd10_codes[code] = (idx,descr)



cod = pd.read_excel(IHME_COD_FILEPATH,header=1)
print(cod.columns)
itt = 0
for row in cod.itertuples():
    cause = row[1]
    codes = row[2]

    codes = "" if type(codes) is float else codes #normalize codes to string...
    codes = [x.strip().replace('.','').split('-') for x in codes.split(",")]


    print(cause)
    #print(codes)
    
    for rng in codes:
        begin = rng[0]
        end = rng[1] if len(rng) > 1 else rng[0]

        print(rng, icd10_codes.get(begin,None),icd10_codes.get(end,None))


    itt += 1
    if itt > 5:
        break



cod = pd.read_excel(IHME_NONFATAL_FILEPATH,header=1)
print(cod.columns)
itt = 0
for row in cod.itertuples():
    print(row)

    cause = row[2]
    codes = row[3]

    codes = "" if type(codes) is float else codes #normalize codes to string...
    codes = [x.strip().replace('.','').split('-') for x in codes.split(",")]
    print(cause)
    print(codes)


    for rng in codes:
        begin = rng[0]
        end = rng[1] if len(rng) > 1 else rng[0]

        print(rng, icd10_codes.get(begin,None),icd10_codes.get(end,None))

    
    itt += 1
    if itt > 5:
        break