routes/ML_GradientBoosting_HousePricePredictor.py

from fastapi import APIRouter
from pydantic import BaseModel
import joblib
import pandas as pd
from typing import Optional, Any

from .config_huggingface import build_model_url, download_artifact_if_needed

router = APIRouter(tags=["Machine Learning"])


class GradientBoostingRequest(BaseModel):
    lot_size_sqm: int = 200
    floors: int = 2
    rooms: int = 5
    crime_rate: float = 3.0
    school_rating: int = 8


MODEL_STATE: dict[str, Optional[Any]] = {
    "model": None,
    "error": None,
}

MODEL_URL = build_model_url("ML_GradientBoosting_HousePricePredictor.joblib")


def _ensure_model_loaded() -> None:
    if MODEL_STATE["model"] is not None:
        return
    try:
        model_path = download_artifact_if_needed(MODEL_URL)
        MODEL_STATE["model"] = joblib.load(model_path)
        MODEL_STATE["error"] = None
    except Exception as e:
        MODEL_STATE["error"] = str(e)
        raise


@router.post("/models/gradient_boosting", summary="Predict house price with Gradient Boosting")
def predict_gradient_boosting(data: GradientBoostingRequest):
    import traceback
    try:
        _ensure_model_loaded()
    except Exception:
        detail = "Model not loaded."
        if MODEL_STATE["error"]:
            detail = f"Model not loaded: {MODEL_STATE['error']}"
        return {"error": detail, "traceback": traceback.format_exc(), "status": 500}

    model = MODEL_STATE["model"]
    if model is None:
        return {"error": f"Model is None after loading. Error: {MODEL_STATE['error']}", "status": 500}

    input_df = pd.DataFrame(
        [[data.lot_size_sqm, data.floors, data.rooms, data.crime_rate, data.school_rating]],
        columns=["lot_size_sqm", "floors", "rooms", "crime_rate", "school_rating"],
    )

    try:
        pred = model.predict(input_df)[0]
    except Exception as e:
        return {"error": f"Prediction failed: {str(e)}", "traceback": traceback.format_exc(), "status": 500}

    price = max(round(float(pred), 2), 0.0)
    return {
        "predicted_price_thousands": price,
        "predicted_price_formatted": f"${price:.1f}k",
    }