from dataclasses import dataclass

import pandas as pd
from sientia.linear_models import LinearRegressionModel
from sientia.preprocessing import DataPreprocessor

from model_manager.utils.models.train_model_params import TrainModelParams


@dataclass
class TrainModelResult:
    """
    A data container for storing the results of a machine learning training process.

    This dataclass encapsulates all outputs from the training pipeline, including
    the trained model, datasets, evaluation metrics, and paths to generated artifacts.
    It is used to pass results between activities in the training workflow.

    Attributes:
        params (TrainModelParams): The parameters used to train the model.
        process_data (DataPreprocessor): The data preprocessor object used to process the input data.
        x_train (pd.DataFrame): The training dataset features.
        x_test (pd.DataFrame): The testing dataset features.
        y_train (pd.DataFrame): The training dataset target values.
        y_test (pd.DataFrame): The testing dataset target values.
        regr (LinearRegressionModel): The trained linear regression model.
        scaler_dict (dict): A dictionary containing the scalers used to scale the features and target values.
        y_pred (pd.Series | None): The predicted target values for the testing dataset. Default is None.
        mse_val (float | None): The Mean Squared Error (MSE) of the predictions. Default is None.
        mae_val (float | None): The Mean Absolute Error (MAE) of the predictions. Default is None.
        r2_val (float | None): The R-squared (R²) value of the predictions. Default is None.
        run_name (str | None): The name of the MLFlow run. Default is None.
        report_path (str | None): The path to the generated HTML report file. Default is None.
        train_data_path (str | None): The path to the training dataset CSV file. Default is None.
        test_data_path (str | None): The path to the testing dataset CSV file. Default is None.
        run_dir (str | None): The path to the run directory containing all artifacts. Default is None.
    """

    params: TrainModelParams
    process_data: DataPreprocessor
    x_train: pd.DataFrame
    x_test: pd.DataFrame
    y_train: pd.DataFrame
    y_test: pd.DataFrame
    regr: LinearRegressionModel
    scaler_dict: dict
    y_pred: pd.Series | None = None
    mse_val: float | None = None
    mae_val: float | None = None
    r2_val: float | None = None
    run_name: str | None = None
    report_path: str | None = None
    train_data_path: str | None = None
    test_data_path: str | None = None
    run_dir: str | None = None