from pathlib import Path

import pandas as pd

from src.modeling import HousePriceModel, train_model


def sample_training_frame() -> pd.DataFrame:
    return pd.DataFrame(
        {
            "OverallQual": [5, 6, 7, 8, 9, 4, 6, 7],
            "GrLivArea": [1200, 1500, 1800, 2100, 2400, 900, 1600, 2000],
            "GarageCars": [1, 2, 2, 3, 3, 1, 2, 2],
            "TotalBsmtSF": [800, 900, 1100, 1300, 1500, 600, 950, 1250],
            "FullBath": [1, 2, 2, 2, 3, 1, 2, 2],
            "YearBuilt": [1960, 1975, 1990, 2001, 2010, 1950, 1982, 1998],
            "Neighborhood": ["NAmes", "CollgCr", "Somerst", "NridgHt", "NoRidge", "OldTown", "NAmes", "Gilbert"],
            "HouseStyle": ["1Story", "1Story", "2Story", "2Story", "2Story", "1Story", "1Story", "2Story"],
            "SalePrice": [135000, 165000, 210000, 260000, 320000, 110000, 175000, 235000],
        }
    )


def test_train_model_persists_artifacts_and_reports_metrics(tmp_path: Path) -> None:
    artifact_path = tmp_path / "house_price_model.joblib"

    trained = train_model(sample_training_frame(), artifact_path=artifact_path)

    assert artifact_path.exists()
    assert trained.metrics["rmse"] >= 0
    assert trained.metrics["r2"] <= 1
    assert "OverallQual" in trained.feature_names
    assert "SalePrice" not in trained.feature_names


def test_house_price_model_predicts_positive_value(tmp_path: Path) -> None:
    artifact_path = tmp_path / "house_price_model.joblib"
    trained = train_model(sample_training_frame(), artifact_path=artifact_path)
    model = HousePriceModel.load(artifact_path)

    prediction = model.predict(
        {
            "OverallQual": 7,
            "GrLivArea": 1850,
            "GarageCars": 2,
            "TotalBsmtSF": 1050,
            "FullBath": 2,
            "YearBuilt": 1995,
            "Neighborhood": "Somerst",
            "HouseStyle": "2Story",
        }
    )

    assert prediction > 0
    assert model.metrics == trained.metrics