polyguard-openenv / scripts /preprocess_mock_ehr.py
TheJackBright's picture
Deploy PolyGuard OpenEnv Space
877add7 verified
#!/usr/bin/env python3
"""Mock EHR preprocessing."""
from __future__ import annotations
import json
from pathlib import Path
def main() -> None:
root = Path(__file__).resolve().parents[1]
raw = root / "data" / "raw" / "mock_ehr"
out = root / "data" / "processed"
out.mkdir(parents=True, exist_ok=True)
records = []
for path in raw.glob("*.json"):
records.append(json.loads(path.read_text(encoding="utf-8")))
(out / "mock_ehr_processed.json").write_text(json.dumps(records, ensure_ascii=True, indent=2), encoding="utf-8")
print(f"processed_records={len(records)}")
if __name__ == "__main__":
main()