| """ |
| predict.py - tiny client for the feature-input fraud model. |
| Depends only on pandas, numpy, joblib (+ huggingface_hub if you use from_hub). |
| |
| model = FraudModel.from_hub("user/repo") # or FraudModel.load("fraud_model") |
| model.predict({"amount": 650, "hour": 3.2, ... all 15 features ...}) |
| """ |
| import json |
| import os |
|
|
| import joblib |
| import pandas as pd |
|
|
| RISK_LABELS = {0: "low", 1: "elevated", 2: "high", 3: "critical"} |
|
|
|
|
| class FraudModel: |
| def __init__(self, model, config): |
| self.model = model |
| self.feature_names = config["feature_names"] |
| self.thresholds = config["thresholds"] |
|
|
| @classmethod |
| def load(cls, folder="."): |
| with open(os.path.join(folder, "config.json")) as f: |
| config = json.load(f) |
| return cls(joblib.load(os.path.join(folder, "model.joblib")), config) |
|
|
| @classmethod |
| def from_hub(cls, repo_id): |
| from huggingface_hub import snapshot_download |
| return cls.load(snapshot_download(repo_id)) |
|
|
| def predict(self, features): |
| """features: dict | list of dicts | DataFrame -> dict (or list of dicts for several rows)""" |
| single = isinstance(features, dict) |
| df = pd.DataFrame([features] if single else features) |
| missing = [c for c in self.feature_names if c not in df.columns] |
| if missing: |
| raise ValueError(f"Missing features: {missing}") |
| X = df[self.feature_names].astype(float) |
| if X.isna().any().any(): |
| raise ValueError("Feature values must not be empty/NaN (use the 'no history' defaults).") |
| probs = self.model.predict_proba(X)[:, 1] |
| out = [] |
| for p in probs: |
| level = int(sum(p >= t for t in self.thresholds)) |
| out.append({"fraud_probability": round(float(p), 4), "risk_level": level, |
| "risk_label": RISK_LABELS[level]}) |
| return out[0] if single else out |
|
|
