File size: 1,957 Bytes
cf23d85 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | from pathlib import Path
import argparse, json
import joblib
import pandas as pd
ROOT = Path(__file__).resolve().parents[1]
MODELS = ROOT / "models"
def load_artifacts():
metadata = json.loads((MODELS/"model_metadata.json").read_text(encoding="utf-8"))
model = joblib.load(MODELS/"risk_probability_model.joblib")
return metadata, model
def predict_cancellation(features: dict) -> dict:
metadata, model = load_artifacts()
required = metadata["feature_columns"]
missing = [c for c in required if c not in features]
extra = [c for c in features if c not in required]
if missing:
raise ValueError(f"Missing required features: {missing}")
row = pd.DataFrame([{c: features.get(c) for c in required}])
# The saved risk model is a full sklearn Pipeline:
# preprocessing + trained classifier. Pass raw model features directly.
probability = float(model.predict_proba(row)[:, 1][0])
threshold = float(metadata["risk_threshold"])
prediction = int(probability >= threshold)
level = "LOW" if probability < 0.35 else ("MEDIUM" if probability < 0.65 else "HIGH")
return {
"target": metadata["target"],
"cancel_probability": round(probability, 6),
"threshold": round(threshold, 6),
"prediction": prediction,
"prediction_label": "CANCEL_RISK" if prediction else "NOT_CANCEL_RISK",
"risk_level": level,
"ignored_extra_fields": extra,
"model_name": metadata["risk_probability_model"],
"synthetic_training_data_warning": metadata["synthetic_training_data"],
}
def main():
parser = argparse.ArgumentParser()
parser.add_argument("json_file")
args = parser.parse_args()
payload = json.loads(Path(args.json_file).read_text(encoding="utf-8"))
print(json.dumps(
predict_cancellation(payload.get("features", payload)),
ensure_ascii=False, indent=2
))
if __name__ == "__main__":
main()
|