Code import - branch release/SIENTIAPDE-1645

model_manager/utils/models/train_model_result.py

@@ -0,0 +1,53 @@
+from dataclasses import dataclass
+
+import pandas as pd
+
+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 prepared 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.
+        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.
+        y_pred (pd.Series | None): The predicted target values for the testing dataset. Default is None.
+        y_train_pred (pd.Series | None): The predicted target values for the training 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.
+        equation (dict | None): The equation of the model. Default is None.
+        equation_path (str | None): The path to the equation file. 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.
+    """
+
+    params: TrainModelParams
+    train_data: pd.DataFrame
+    val_data: pd.DataFrame
+    y_pred: pd.DataFrame | None = None
+    y_train_pred: pd.DataFrame | None = None
+    mse_val: float | None = None
+    mae_val: float | None = None
+    r2_val: float | None = None
+    equation: dict | None = None
+    equation_path: str | None = None
+    run_name: str | None = None
+    experiment_name: str | None = None
+    run_id: 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