Created
March 6, 2024 08:51
-
-
Save mlondschien/2fa324f27e49a0c8bdecdb7ab9c61402 to your computer and use it in GitHub Desktop.
concept_dicts.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
from pathlib import Path | |
import copy | |
import pandas as pd | |
from datetime import datetime | |
import numpy as np | |
json_path = Path(__file__).parent | |
data_path = Path(__file__).parents[4] / "data" / "picdb" / "V1.1.0" | |
d_icd_diagnoses = pd.read_csv(data_path / "D_ICD_DIAGNOSES.csv") | |
d_items = pd.read_csv(data_path / "D_ITEMS.csv") | |
d_labitems = pd.read_csv(data_path / "D_LABITEMS.csv") | |
for concept_dict_path in json_path.glob("*.json"): | |
with concept_dict_path.open() as f: | |
concept_dict = json.load(f) | |
for concept_name, concept in concept_dict.items(): | |
if concept.get("class") == "rec_cncpt": | |
continue | |
concept["sources"]["picdb"] = [] | |
d_items_ = d_items[lambda x: x["LABEL"].str.lower().str.replace("-", "").isin([concept["description"].lower().replace("-", ""), concept_name])] | |
if len(d_items_) > 0: | |
if not d_items_["UNITNAME"].nunique() == 1: | |
breakpoint() | |
if isinstance(concept["unit"], str): | |
if not (d_items_["UNITNAME"].iloc[0].lower() == concept["unit"].lower()): | |
breakpoint() | |
else: | |
if not d_items_["UNITNAME"].iloc[0].lower() in [x.lower() for x in concept["unit"]]: | |
breakpoint() | |
concept["sources"]["picdb"] += d_items_.groupby(["LINKSTO"]).agg({"ITEMID": list}).reset_index().assign(sub_var="itemid").rename(columns={"LINKSTO": "table", "ITEMID": "ids"}).to_dict("records") | |
d_labitems_ = d_labitems[lambda x: x["LABEL"].str.lower().str.replace("-", "").isin([concept["description"].lower().replace("-", ""), concept_name])] | |
if len(d_labitems_) > 0: | |
source_dict = [{"table": "labevents", "ids": d_labitems_["ITEMID"].tolist(), "sub_var": "itemid"}] | |
concept["sources"]["picdb"] += source_dict | |
# unitnames = labevents[lambda x: x["ITEMID"].isin(d_labitems_["ITEMID"])]["VALUEUOM"].dropna().unique() | |
# if not len(unitnames) == 1: | |
# breakpoint() | |
# if isinstance(concept["unit"], str): | |
# if not (unitnames[0].lower() == concept["unit"].lower()): | |
# breakpoint() | |
# else: | |
# if not unitnames[0].lower() in [x.lower() for x in concept["unit"]]: | |
# breakpoint() | |
concept_dict[concept_name] = concept | |
with concept_dict_path.open("w") as f: | |
json.dump(concept_dict, f, indent=4) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment