dragon-ml-toolbox 5.3.0__tar.gz → 6.0.0__tar.gz

{dragon_ml_toolbox-5.3.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-6.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 5.3.0
+Version: 6.0.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -141,19 +141,22 @@ pip install "dragon-ml-toolbox[pytorch]"
 ```bash
 custom_logger
 data_exploration
-ensemble_learning
+ensemble_evaluation
 ensemble_inference
+ensemble_learning
 ETL_engineering
-ML_datasetmaster
-ML_models
 ML_callbacks
+ML_datasetmaster
 ML_evaluation
-ML_trainer
 ML_inference
+ML_models
+ML_optimization
+ML_trainer
+optimization_tools
 path_manager
 PSO_optimization
-SQL
 RNN_forecast
+SQL
 utilities
 ```
 

{dragon_ml_toolbox-5.3.0 → dragon_ml_toolbox-6.0.0}/README.md

@@ -60,19 +60,22 @@ pip install "dragon-ml-toolbox[pytorch]"
 ```bash
 custom_logger
 data_exploration
-ensemble_learning
+ensemble_evaluation
 ensemble_inference
+ensemble_learning
 ETL_engineering
-ML_datasetmaster
-ML_models
 ML_callbacks
+ML_datasetmaster
 ML_evaluation
-ML_trainer
 ML_inference
+ML_models
+ML_optimization
+ML_trainer
+optimization_tools
 path_manager
 PSO_optimization
-SQL
 RNN_forecast
+SQL
 utilities
 ```
 

{dragon_ml_toolbox-5.3.0 → dragon_ml_toolbox-6.0.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 5.3.0
+Version: 6.0.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -141,19 +141,22 @@ pip install "dragon-ml-toolbox[pytorch]"
 ```bash
 custom_logger
 data_exploration
-ensemble_learning
+ensemble_evaluation
 ensemble_inference
+ensemble_learning
 ETL_engineering
-ML_datasetmaster
-ML_models
 ML_callbacks
+ML_datasetmaster
 ML_evaluation
-ML_trainer
 ML_inference
+ML_models
+ML_optimization
+ML_trainer
+optimization_tools
 path_manager
 PSO_optimization
-SQL
 RNN_forecast
+SQL
 utilities
 ```
 

{dragon_ml_toolbox-5.3.0 → dragon_ml_toolbox-6.0.0}/dragon_ml_toolbox.egg-info/SOURCES.txt

@@ -26,6 +26,7 @@ ml_tools/_logger.py
 ml_tools/_script_info.py
 ml_tools/custom_logger.py
 ml_tools/data_exploration.py
+ml_tools/ensemble_evaluation.py
 ml_tools/ensemble_inference.py
 ml_tools/ensemble_learning.py
 ml_tools/handle_excel.py

{dragon_ml_toolbox-5.3.0 → dragon_ml_toolbox-6.0.0}/ml_tools/ML_callbacks.py

@@ -2,7 +2,7 @@ import numpy as np
 import torch
 from tqdm.auto import tqdm
 from .path_manager import make_fullpath
-from .keys import LogKeys
+from .keys import PyTorchLogKeys
 from ._logger import _LOGGER
 from typing import Optional
 from ._script_info import _script_info
@@ -96,14 +96,14 @@ class TqdmProgressBar(Callback):
     def on_batch_end(self, batch, logs=None):
         self.batch_bar.update(1) # type: ignore
         if logs:
-            self.batch_bar.set_postfix(loss=f"{logs.get(LogKeys.BATCH_LOSS, 0):.4f}") # type: ignore
+            self.batch_bar.set_postfix(loss=f"{logs.get(PyTorchLogKeys.BATCH_LOSS, 0):.4f}") # type: ignore
 
     def on_epoch_end(self, epoch, logs=None):
         self.batch_bar.close() # type: ignore
         self.epoch_bar.update(1) # type: ignore
         if logs:
-            train_loss_str = f"{logs.get(LogKeys.TRAIN_LOSS, 0):.4f}"
-            val_loss_str = f"{logs.get(LogKeys.VAL_LOSS, 0):.4f}"
+            train_loss_str = f"{logs.get(PyTorchLogKeys.TRAIN_LOSS, 0):.4f}"
+            val_loss_str = f"{logs.get(PyTorchLogKeys.VAL_LOSS, 0):.4f}"
             self.epoch_bar.set_postfix_str(f"Train Loss: {train_loss_str}, Val Loss: {val_loss_str}") # type: ignore
 
     def on_train_end(self, logs=None):
@@ -124,7 +124,7 @@ class EarlyStopping(Callback):
                     inferred from the name of the monitored quantity.
         verbose (int): Verbosity mode.
     """
-    def __init__(self, monitor: str=LogKeys.VAL_LOSS, min_delta=0.0, patience=3, mode: Literal['auto', 'min', 'max']='auto', verbose: int=1):
+    def __init__(self, monitor: str=PyTorchLogKeys.VAL_LOSS, min_delta: float=0.0, patience: int=5, mode: Literal['auto', 'min', 'max']='auto', verbose: int=1):
         super().__init__()
         self.monitor = monitor
         self.patience = patience
@@ -201,8 +201,8 @@ class ModelCheckpoint(Callback):
         mode (str): One of {'auto', 'min', 'max'}.
         verbose (int): Verbosity mode.
     """
-    def __init__(self, save_dir: Union[str,Path], monitor: str = LogKeys.VAL_LOSS,
-                 save_best_only: bool = False, mode: Literal['auto', 'min', 'max']= 'auto', verbose: int = 1):
+    def __init__(self, save_dir: Union[str,Path], monitor: str = PyTorchLogKeys.VAL_LOSS,
+                 save_best_only: bool = True, mode: Literal['auto', 'min', 'max']= 'auto', verbose: int = 0):
         super().__init__()
         self.save_dir = make_fullpath(save_dir, make=True, enforce="directory")
         if not self.save_dir.is_dir():

dragon_ml_toolbox-6.0.0/ml_tools/ML_evaluation.py

@@ -0,0 +1,350 @@
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.calibration import CalibrationDisplay
+from sklearn.metrics import (
+    classification_report, 
+    ConfusionMatrixDisplay, 
+    roc_curve, 
+    roc_auc_score, 
+    mean_squared_error,
+    mean_absolute_error,
+    r2_score, 
+    median_absolute_error,
+    precision_recall_curve,
+    average_precision_score
+)
+import torch
+import shap
+from pathlib import Path
+from .path_manager import make_fullpath
+from ._logger import _LOGGER
+from typing import Union, Optional
+from ._script_info import _script_info
+
+
+__all__ = [
+    "plot_losses", 
+    "classification_metrics", 
+    "regression_metrics",
+    "shap_summary_plot"
+]
+
+
+def plot_losses(history: dict, save_dir: Union[str, Path]):
+    """
+    Plots training & validation loss curves from a history object.
+
+    Args:
+        history (dict): A dictionary containing 'train_loss' and 'val_loss'.
+        save_dir (str | Path): Directory to save the plot image.
+    """
+    train_loss = history.get('train_loss', [])
+    val_loss = history.get('val_loss', [])
+    
+    if not train_loss and not val_loss:
+        print("Warning: Loss history is empty or incomplete. Cannot plot.")
+        return
+
+    fig, ax = plt.subplots(figsize=(10, 5), dpi=100)
+    
+    # Plot training loss only if data for it exists
+    if train_loss:
+        epochs = range(1, len(train_loss) + 1)
+        ax.plot(epochs, train_loss, 'o-', label='Training Loss')
+    
+    # Plot validation loss only if data for it exists
+    if val_loss:
+        epochs = range(1, len(val_loss) + 1)
+        ax.plot(epochs, val_loss, 'o-', label='Validation Loss')
+    
+    ax.set_title('Training and Validation Loss')
+    ax.set_xlabel('Epochs')
+    ax.set_ylabel('Loss')
+    ax.legend()
+    ax.grid(True)
+    plt.tight_layout()
+    
+    save_dir_path = make_fullpath(save_dir, make=True, enforce="directory")
+    save_path = save_dir_path / "loss_plot.svg"
+    plt.savefig(save_path)
+    _LOGGER.info(f"📉 Loss plot saved as '{save_path.name}'")
+
+    plt.close(fig)
+
+
+def classification_metrics(save_dir: Union[str, Path], y_true: np.ndarray, y_pred: np.ndarray, y_prob: Optional[np.ndarray] = None, 
+                           cmap: str = "Blues"):
+    """
+    Saves classification metrics and plots.
+
+    Args:
+        y_true (np.ndarray): Ground truth labels.
+        y_pred (np.ndarray): Predicted labels.
+        y_prob (np.ndarray, optional): Predicted probabilities for ROC curve.
+        cmap (str): Colormap for the confusion matrix.
+        save_dir (str | Path): Directory to save plots.
+    """
+    print("--- Classification Report ---")
+    # Generate report as both text and dictionary
+    report_text: str = classification_report(y_true, y_pred) # type: ignore
+    report_dict: dict = classification_report(y_true, y_pred, output_dict=True) # type: ignore
+    print(report_text)
+    
+    save_dir_path = make_fullpath(save_dir, make=True, enforce="directory")
+    # Save text report
+    report_path = save_dir_path / "classification_report.txt"
+    report_path.write_text(report_text, encoding="utf-8")
+    _LOGGER.info(f"📝 Classification report saved as '{report_path.name}'")
+
+    # --- Save Classification Report Heatmap ---
+    try:
+        plt.figure(figsize=(8, 6), dpi=100)
+        sns.heatmap(pd.DataFrame(report_dict).iloc[:-1, :].T, annot=True, cmap='viridis', fmt='.2f')
+        plt.title("Classification Report")
+        plt.tight_layout()
+        heatmap_path = save_dir_path / "classification_report_heatmap.svg"
+        plt.savefig(heatmap_path)
+        _LOGGER.info(f"📊 Report heatmap saved as '{heatmap_path.name}'")
+        plt.close()
+    except Exception as e:
+        _LOGGER.error(f"❌ Could not generate classification report heatmap: {e}")
+
+    # Save Confusion Matrix
+    fig_cm, ax_cm = plt.subplots(figsize=(6, 6), dpi=100)
+    ConfusionMatrixDisplay.from_predictions(y_true, y_pred, cmap=cmap, ax=ax_cm)
+    ax_cm.set_title("Confusion Matrix")
+    cm_path = save_dir_path / "confusion_matrix.svg"
+    plt.savefig(cm_path)
+    _LOGGER.info(f"❇️ Confusion matrix saved as '{cm_path.name}'")
+    plt.close(fig_cm)
+
+    # Plotting logic for ROC and PR Curves
+    if y_prob is not None and y_prob.ndim > 1 and y_prob.shape[1] >= 2:
+        # Use probabilities of the positive class
+        y_score = y_prob[:, 1]
+        
+        # --- Save ROC Curve ---
+        fpr, tpr, _ = roc_curve(y_true, y_score)
+        auc = roc_auc_score(y_true, y_score)
+        fig_roc, ax_roc = plt.subplots(figsize=(6, 6), dpi=100)
+        ax_roc.plot(fpr, tpr, label=f'AUC = {auc:.2f}')
+        ax_roc.plot([0, 1], [0, 1], 'k--')
+        ax_roc.set_title('Receiver Operating Characteristic (ROC) Curve')
+        ax_roc.set_xlabel('False Positive Rate')
+        ax_roc.set_ylabel('True Positive Rate')
+        ax_roc.legend(loc='lower right')
+        ax_roc.grid(True)
+        roc_path = save_dir_path / "roc_curve.svg"
+        plt.savefig(roc_path)
+        _LOGGER.info(f"📈 ROC curve saved as '{roc_path.name}'")
+        plt.close(fig_roc)
+
+        # --- Save Precision-Recall Curve ---
+        precision, recall, _ = precision_recall_curve(y_true, y_score)
+        ap_score = average_precision_score(y_true, y_score)
+        fig_pr, ax_pr = plt.subplots(figsize=(6, 6), dpi=100)
+        ax_pr.plot(recall, precision, label=f'AP = {ap_score:.2f}')
+        ax_pr.set_title('Precision-Recall Curve')
+        ax_pr.set_xlabel('Recall')
+        ax_pr.set_ylabel('Precision')
+        ax_pr.legend(loc='lower left')
+        ax_pr.grid(True)
+        pr_path = save_dir_path / "pr_curve.svg"
+        plt.savefig(pr_path)
+        _LOGGER.info(f"📈 PR curve saved as '{pr_path.name}'")
+        plt.close(fig_pr)
+        
+        # --- Save Calibration Plot ---
+        if y_prob.ndim > 1 and y_prob.shape[1] >= 2:
+            y_score = y_prob[:, 1] # Use probabilities of the positive class
+            
+            fig_cal, ax_cal = plt.subplots(figsize=(8, 8), dpi=100)
+            CalibrationDisplay.from_predictions(y_true, y_score, n_bins=15, ax=ax_cal)
+            
+            ax_cal.set_title('Calibration Plot (Reliability Curve)')
+            ax_cal.set_xlabel('Mean Predicted Probability')
+            ax_cal.set_ylabel('Fraction of Positives')
+            ax_cal.grid(True)
+            plt.tight_layout()
+            
+            cal_path = save_dir_path / "calibration_plot.svg"
+            plt.savefig(cal_path)
+            _LOGGER.info(f"✅ Calibration plot saved as '{cal_path.name}'")
+            plt.close(fig_cal)
+
+
+def regression_metrics(y_true: np.ndarray, y_pred: np.ndarray, save_dir: Union[str, Path]):
+    """
+    Saves regression metrics and plots.
+
+    Args:
+        y_true (np.ndarray): Ground truth values.
+        y_pred (np.ndarray): Predicted values.
+        save_dir (str | Path): Directory to save plots and report.
+    """
+    rmse = np.sqrt(mean_squared_error(y_true, y_pred))
+    mae = mean_absolute_error(y_true, y_pred)
+    r2 = r2_score(y_true, y_pred)
+    medae = median_absolute_error(y_true, y_pred)
+    
+    report_lines = [
+        "--- Regression Report ---",
+        f"  Root Mean Squared Error (RMSE): {rmse:.4f}",
+        f"  Mean Absolute Error (MAE):      {mae:.4f}",
+        f"  Median Absolute Error (MedAE):  {medae:.4f}",
+        f"  Coefficient of Determination (R²): {r2:.4f}"
+    ]
+    report_string = "\n".join(report_lines)
+    print(report_string)
+
+    save_dir_path = make_fullpath(save_dir, make=True, enforce="directory")
+    # Save text report
+    report_path = save_dir_path / "regression_report.txt"
+    report_path.write_text(report_string)
+    _LOGGER.info(f"📝 Regression report saved as '{report_path.name}'")
+
+    # Save residual plot
+    residuals = y_true - y_pred
+    fig_res, ax_res = plt.subplots(figsize=(8, 6), dpi=100)
+    ax_res.scatter(y_pred, residuals, alpha=0.6)
+    ax_res.axhline(0, color='red', linestyle='--')
+    ax_res.set_xlabel("Predicted Values")
+    ax_res.set_ylabel("Residuals")
+    ax_res.set_title("Residual Plot")
+    ax_res.grid(True)
+    plt.tight_layout()
+    res_path = save_dir_path / "residual_plot.svg"
+    plt.savefig(res_path)
+    _LOGGER.info(f"📈 Residual plot saved as '{res_path.name}'")
+    plt.close(fig_res)
+
+    # Save true vs predicted plot
+    fig_tvp, ax_tvp = plt.subplots(figsize=(8, 6), dpi=100)
+    ax_tvp.scatter(y_true, y_pred, alpha=0.6)
+    ax_tvp.plot([y_true.min(), y_true.max()], [y_true.min(), y_true.max()], 'k--', lw=2)
+    ax_tvp.set_xlabel('True Values')
+    ax_tvp.set_ylabel('Predictions')
+    ax_tvp.set_title('True vs. Predicted Values')
+    ax_tvp.grid(True)
+    plt.tight_layout()
+    tvp_path = save_dir_path / "true_vs_predicted_plot.svg"
+    plt.savefig(tvp_path)
+    _LOGGER.info(f"📉 True vs. Predicted plot saved as '{tvp_path.name}'")
+    plt.close(fig_tvp)
+    
+    # Save Histogram of Residuals
+    fig_hist, ax_hist = plt.subplots(figsize=(8, 6), dpi=100)
+    sns.histplot(residuals, kde=True, ax=ax_hist)
+    ax_hist.set_xlabel("Residual Value")
+    ax_hist.set_ylabel("Frequency")
+    ax_hist.set_title("Distribution of Residuals")
+    ax_hist.grid(True)
+    plt.tight_layout()
+    hist_path = save_dir_path / "residuals_histogram.svg"
+    plt.savefig(hist_path)
+    _LOGGER.info(f"📊 Residuals histogram saved as '{hist_path.name}'")
+    plt.close(fig_hist)
+
+
+def shap_summary_plot(model, background_data: Union[torch.Tensor,np.ndarray], instances_to_explain: Union[torch.Tensor,np.ndarray], 
+                      feature_names: Optional[list[str]]=None, save_dir: Optional[Union[str, Path]] = None):
+    """
+    Calculates SHAP values and saves summary plots and data.
+
+    Args:
+        model (nn.Module): The trained PyTorch model.
+        background_data (torch.Tensor): A sample of data for the explainer background.
+        instances_to_explain (torch.Tensor): The specific data instances to explain.
+        feature_names (list of str | None): Names of the features for plot labeling.
+        save_dir (str | Path | None): Directory to save SHAP artifacts. If None, dot plot is shown.
+    """
+    # everything to numpy
+    if isinstance(background_data, np.ndarray):
+        background_data_np = background_data
+    else:
+        background_data_np = background_data.numpy()
+        
+    if isinstance(instances_to_explain, np.ndarray):
+        instances_to_explain_np = instances_to_explain
+    else:
+        instances_to_explain_np = instances_to_explain.numpy()
+    
+    # --- Data Validation Step ---
+    if np.isnan(background_data_np).any() or np.isnan(instances_to_explain_np).any():
+        _LOGGER.error("❌ Input data for SHAP contains NaN values. Aborting explanation.")
+        return
+    
+    print("\n--- SHAP Value Explanation ---")
+    
+    model.eval()
+    model.cpu()
+    
+    # 1. Summarize the background data.
+    # Summarize the background data using k-means. 10-50 clusters is a good starting point.
+    background_summary = shap.kmeans(background_data_np, 30) 
+    
+    # 2. Define a prediction function wrapper that SHAP can use. It must take a numpy array and return a numpy array.
+    def prediction_wrapper(x_np: np.ndarray) -> np.ndarray:
+        # Convert numpy data to torch tensor
+        x_torch = torch.from_numpy(x_np).float()
+        with torch.no_grad():
+            # Get model output
+            output = model(x_torch)
+        # Return as numpy array
+        return output.cpu().numpy().flatten()
+
+    # 3. Create the KernelExplainer
+    explainer = shap.KernelExplainer(prediction_wrapper, background_summary)
+    
+    print("Calculating SHAP values with KernelExplainer...")
+    shap_values = explainer.shap_values(instances_to_explain_np, l1_reg="aic")
+    
+    if save_dir:
+        save_dir_path = make_fullpath(save_dir, make=True, enforce="directory")
+        plt.ioff()
+        
+        # Save Bar Plot
+        bar_path = save_dir_path / "shap_bar_plot.svg"
+        shap.summary_plot(shap_values, instances_to_explain_np, feature_names=feature_names, plot_type="bar", show=False)
+        plt.title("SHAP Feature Importance")
+        plt.tight_layout()
+        plt.savefig(bar_path)
+        _LOGGER.info(f"📊 SHAP bar plot saved as '{bar_path.name}'")
+        plt.close()
+
+        # Save Dot Plot
+        dot_path = save_dir_path / "shap_dot_plot.svg"
+        shap.summary_plot(shap_values, instances_to_explain_np, feature_names=feature_names, plot_type="dot", show=False)
+        plt.title("SHAP Feature Importance")
+        plt.tight_layout()
+        plt.savefig(dot_path)
+        _LOGGER.info(f"📊 SHAP dot plot saved as '{dot_path.name}'")
+        plt.close()
+
+        # Save Summary Data to CSV
+        summary_path = save_dir_path / "shap_summary.csv"
+        # Ensure the array is 1D before creating the DataFrame
+        mean_abs_shap = np.abs(shap_values).mean(axis=0).flatten()
+        
+        if feature_names is None:
+            feature_names = [f'feature_{i}' for i in range(len(mean_abs_shap))]
+            
+        summary_df = pd.DataFrame({
+            'feature': feature_names,
+            'mean_abs_shap_value': mean_abs_shap
+        }).sort_values('mean_abs_shap_value', ascending=False)
+        
+        summary_df.to_csv(summary_path, index=False)
+        
+        _LOGGER.info(f"📝 SHAP summary data saved as '{summary_path.name}'")
+        plt.ion()
+        
+    else:
+        _LOGGER.info("No save directory provided. Displaying SHAP dot plot.")
+        shap.summary_plot(shap_values, instances_to_explain_np, feature_names=feature_names, plot_type="dot")
+
+
+def info():
+    _script_info(__all__)

{dragon_ml_toolbox-5.3.0 → dragon_ml_toolbox-6.0.0}/ml_tools/ML_trainer.py

@@ -8,16 +8,16 @@ import numpy as np
 from .ML_callbacks import Callback, History, TqdmProgressBar
 from .ML_evaluation import classification_metrics, regression_metrics, plot_losses, shap_summary_plot
 from ._script_info import _script_info
-from .keys import LogKeys
+from .keys import PyTorchLogKeys
 from ._logger import _LOGGER
 
 
 __all__ = [
-    "MyTrainer"
+    "MLTrainer"
 ]
 
 
-class MyTrainer:
+class MLTrainer:
     def __init__(self, model: nn.Module, train_dataset: Dataset, test_dataset: Dataset, 
                  kind: Literal["regression", "classification"],
                  criterion: nn.Module, optimizer: torch.optim.Optimizer, 
@@ -95,14 +95,16 @@ class MyTrainer:
             batch_size=batch_size, 
             shuffle=shuffle, 
             num_workers=loader_workers, 
-            pin_memory=(self.device.type == "cuda")
+            pin_memory=("cuda" in self.device.type),
+            drop_last=True  # Drops the last batch if incomplete, selecting a good batch size is key.
         )
+        
         self.test_loader = DataLoader(
             dataset=self.test_dataset, 
             batch_size=batch_size, 
             shuffle=False, 
             num_workers=loader_workers, 
-            pin_memory=(self.device.type == "cuda")
+            pin_memory=("cuda" in self.device.type)
         )
 
     def fit(self, epochs: int = 10, batch_size: int = 10, shuffle: bool = True):
@@ -159,8 +161,8 @@ class MyTrainer:
         for batch_idx, (features, target) in enumerate(self.train_loader): # type: ignore
             # Create a log dictionary for the batch
             batch_logs = {
-                LogKeys.BATCH_INDEX: batch_idx, 
-                LogKeys.BATCH_SIZE: features.size(0)
+                PyTorchLogKeys.BATCH_INDEX: batch_idx, 
+                PyTorchLogKeys.BATCH_SIZE: features.size(0)
             }
             self.callbacks_hook('on_batch_begin', batch_idx, logs=batch_logs)
 
@@ -178,11 +180,11 @@ class MyTrainer:
             running_loss += batch_loss * features.size(0)
 
             # Add the batch loss to the logs and call the end-of-batch hook
-            batch_logs[LogKeys.BATCH_LOSS] = batch_loss
+            batch_logs[PyTorchLogKeys.BATCH_LOSS] = batch_loss
             self.callbacks_hook('on_batch_end', batch_idx, logs=batch_logs)
 
         # Return the average loss for the entire epoch
-        return {LogKeys.TRAIN_LOSS: running_loss / len(self.train_loader.dataset)} # type: ignore
+        return {PyTorchLogKeys.TRAIN_LOSS: running_loss / len(self.train_loader.dataset)} # type: ignore
 
     def _validation_step(self):
         self.model.eval()
@@ -195,7 +197,7 @@ class MyTrainer:
                     output = output.view_as(target)
                 loss = self.criterion(output, target)
                 running_loss += loss.item() * features.size(0)
-        logs = {LogKeys.VAL_LOSS: running_loss / len(self.test_loader.dataset)} # type: ignore
+        logs = {PyTorchLogKeys.VAL_LOSS: running_loss / len(self.test_loader.dataset)} # type: ignore
         return logs
     
     def _predict_for_eval(self, dataloader: DataLoader):
@@ -230,14 +232,14 @@ class MyTrainer:
                 
                 yield y_pred_batch, y_prob_batch, y_true_batch
     
-    def evaluate(self, save_dir: Optional[Union[str,Path]], data: Optional[Union[DataLoader, Dataset]] = None):
+    def evaluate(self, save_dir: Union[str,Path], data: Optional[Union[DataLoader, Dataset]] = None):
         """
         Evaluates the model on the given data.
 
         Args:
             data (DataLoader | Dataset | None ): The data to evaluate on.
                 Can be a DataLoader or a Dataset. If None, defaults to the trainer's internal test_dataset.
-            save_dir (str | Path | None): Directory to save all reports and plots. If None, metrics are shown but not saved.
+            save_dir (str | Path): Directory to save all reports and plots.
         """
         eval_loader = None
         if isinstance(data, DataLoader):
@@ -273,14 +275,14 @@ class MyTrainer:
         y_prob = np.concatenate(all_probs) if self.kind == "classification" else None
 
         if self.kind == "classification":
-            classification_metrics(y_true, y_pred, y_prob, save_dir=save_dir)
+            classification_metrics(save_dir, y_true, y_pred, y_prob)
         else:
-            regression_metrics(y_true.flatten(), y_pred.flatten(), save_dir=save_dir)
+            regression_metrics(y_true.flatten(), y_pred.flatten(), save_dir)
 
         print("\n--- Training History ---")
         plot_losses(self.history, save_dir=save_dir)
     
-    def explain(self, explain_dataset: Optional[Dataset] = None, n_samples: int = 100, 
+    def explain(self, explain_dataset: Optional[Dataset] = None, n_samples: int = 1000, 
                 feature_names: Optional[List[str]] = None, save_dir: Optional[Union[str,Path]] = None):
         """
         Explains model predictions using SHAP and saves all artifacts.

{dragon_ml_toolbox-5.3.0 → dragon_ml_toolbox-6.0.0}/ml_tools/PSO_optimization.py

@@ -12,7 +12,7 @@ from .path_manager import sanitize_filename, make_fullpath, list_files_by_extens
 import torch
 from tqdm import trange
 from ._logger import _LOGGER
-from .keys import ModelSaveKeys
+from .keys import EnsembleKeys
 from ._script_info import _script_info
 from .SQL import DatabaseManager
 from contextlib import nullcontext
@@ -48,9 +48,9 @@ class ObjectiveFunction():
         self.is_hybrid = False if binary_features <= 0 else True
         self.use_noise = add_noise
         self._artifact = deserialize_object(trained_model_path, verbose=False, raise_on_error=True)
-        self.model = self._get_from_artifact(ModelSaveKeys.MODEL)
-        self.feature_names: Optional[list[str]] = self._get_from_artifact(ModelSaveKeys.FEATURES) # type: ignore
-        self.target_name: Optional[str] = self._get_from_artifact(ModelSaveKeys.TARGET) # type: ignore
+        self.model = self._get_from_artifact(EnsembleKeys.MODEL)
+        self.feature_names: Optional[list[str]] = self._get_from_artifact(EnsembleKeys.FEATURES) # type: ignore
+        self.target_name: Optional[str] = self._get_from_artifact(EnsembleKeys.TARGET) # type: ignore
         self.task = task
         self.check_model() # check for classification models and None values
         
@@ -126,7 +126,7 @@ class ObjectiveFunction():
         if self._artifact is None:
             raise TypeError("Load model error")
         val = self._artifact.get(key)
-        if key == ModelSaveKeys.FEATURES:
+        if key == EnsembleKeys.FEATURES:
             result = val if isinstance(val, list) and val else None
         else:
             result = val if val else None