dragon-ml-toolbox 8.2.0__py3-none-any.whl → 9.0.0__py3-none-any.whl

ml_tools/ML_callbacks.py

@@ -134,7 +134,8 @@ class EarlyStopping(Callback):
         self.verbose = verbose
         
         if mode not in ['auto', 'min', 'max']:
-            raise ValueError(f"EarlyStopping mode {mode} is unknown, choose one of ('auto', 'min', 'max')")
+            _LOGGER.error(f"EarlyStopping mode {mode} is unknown, choose one of ('auto', 'min', 'max')")
+            raise ValueError()
         self.mode = mode
 
         # Determine the comparison operator based on the mode
@@ -221,7 +222,8 @@ class ModelCheckpoint(Callback):
         self.last_best_filepath = None
 
         if mode not in ['auto', 'min', 'max']:
-            raise ValueError(f"ModelCheckpoint mode {mode} is unknown.")
+            _LOGGER.error(f"ModelCheckpoint mode {mode} is unknown.")
+            raise ValueError()
         self.mode = mode
 
         if self.mode == 'min':
@@ -329,7 +331,8 @@ class LRScheduler(Callback):
         # For schedulers that need a metric (e.g., val_loss)
         if isinstance(self.scheduler, torch.optim.lr_scheduler.ReduceLROnPlateau):
             if self.monitor is None:
-                raise ValueError("LRScheduler needs a `monitor` metric for ReduceLROnPlateau.")
+                _LOGGER.error("LRScheduler needs a `monitor` metric for ReduceLROnPlateau.")
+                raise ValueError()
             
             metric_val = logs.get(self.monitor) # type: ignore
             if metric_val is not None:

ml_tools/ML_datasetmaster.py

@@ -85,11 +85,13 @@ class _BaseDatasetMaker(ABC):
                 try:
                     continuous_feature_indices = [name_to_idx[name] for name in continuous_feature_columns] # type: ignore
                 except KeyError as e:
-                    raise ValueError(f"Feature column '{e.args[0]}' not found.")
+                    _LOGGER.error(f"Feature column '{e.args[0]}' not found.")
+                    raise ValueError()
             elif all(isinstance(c, int) for c in continuous_feature_columns):
                 continuous_feature_indices = continuous_feature_columns # type: ignore
             else:
-                raise TypeError("`continuous_feature_columns` must be a list of all strings or all integers.")
+                _LOGGER.error("'continuous_feature_columns' must be a list of all strings or all integers.")
+                raise TypeError()
 
         X_train_values = X_train.values
         X_test_values = X_test.values
@@ -152,8 +154,12 @@ class _BaseDatasetMaker(ABC):
         Args:
             save_dir (str | Path): The directory where the scaler will be saved.
         """
-        if not self.scaler: raise RuntimeError("No scaler was fitted or provided.")
-        if not self.id: raise ValueError("Must set the `id` before saving scaler.")
+        if not self.scaler: 
+            _LOGGER.error("No scaler was fitted or provided.")
+            raise RuntimeError()
+        if not self.id: 
+            _LOGGER.error("Must set the `id` before saving scaler.")
+            raise ValueError()
         save_path = make_fullpath(save_dir, make=True, enforce="directory")
         sanitized_id = sanitize_filename(self.id)
         filename = f"scaler_{sanitized_id}.pth"
@@ -365,7 +371,7 @@ class VisionDatasetMaker(_BaseMaker):
             f"Image channels (bands): {img_channels or 'None'}\n"
             f"--------------------------------------"
         )
-        _LOGGER.info(report)
+        print(report)
 
     def split_data(self, val_size: float = 0.2, test_size: float = 0.0, 
                    stratify: bool = True, random_state: Optional[int] = None) -> 'VisionDatasetMaker':
@@ -375,7 +381,8 @@ class VisionDatasetMaker(_BaseMaker):
             return self
 
         if val_size + test_size >= 1.0:
-            raise ValueError("The sum of val_size and test_size must be less than 1.")
+            _LOGGER.error("The sum of val_size and test_size must be less than 1.")
+            raise ValueError()
 
         indices = list(range(len(self.full_dataset)))
         labels_for_split = self.labels if stratify else None
@@ -409,7 +416,8 @@ class VisionDatasetMaker(_BaseMaker):
                              extra_train_transforms: Optional[List] = None) -> 'VisionDatasetMaker':
         """Configures and applies the image transformations (augmentations)."""
         if not self._is_split:
-            raise RuntimeError("Transforms must be configured AFTER splitting data. Call .split_data() first.")
+            _LOGGER.error("Transforms must be configured AFTER splitting data. Call .split_data() first.")
+            raise RuntimeError()
 
         base_train_transforms = [transforms.RandomResizedCrop(crop_size), transforms.RandomHorizontalFlip()]
         if extra_train_transforms:
@@ -432,9 +440,10 @@ class VisionDatasetMaker(_BaseMaker):
     def get_datasets(self) -> Tuple[Dataset, ...]:
         """Returns the final train, validation, and optional test datasets."""
         if not self._is_split:
-            raise RuntimeError("Data has not been split. Call .split_data() first.")
+            _LOGGER.error("Data has not been split. Call .split_data() first.")
+            raise RuntimeError()
         if not self._are_transforms_configured:
-            _LOGGER.warning("⚠️ Transforms have not been configured. Using default ToTensor only.")
+            _LOGGER.warning("Transforms have not been configured. Using default ToTensor only.")
 
         if self._test_dataset:
             return self._train_dataset, self._val_dataset, self._test_dataset
@@ -468,7 +477,8 @@ class SequenceMaker(_BaseMaker):
             self.time_axis = numpy.arange(len(data))
             self.sequence = data.astype(numpy.float32)
         else:
-            raise TypeError("Data must be a pandas DataFrame/Series or a numpy array.")
+            _LOGGER.error("Data must be a pandas DataFrame/Series or a numpy array.")
+            raise TypeError()
             
         self.train_sequence = None
         self.test_sequence = None
@@ -483,10 +493,11 @@ class SequenceMaker(_BaseMaker):
         splitting to prevent data leakage from the test set.
         """
         if not self._is_split:
-            raise RuntimeError("Data must be split BEFORE normalizing. Call .split_data() first.")
+            _LOGGER.error("Data must be split BEFORE normalizing. Call .split_data() first.")
+            raise RuntimeError()
 
         if self.scaler:
-            _LOGGER.warning("⚠️ Data has already been normalized.")
+            _LOGGER.warning("Data has already been normalized.")
             return self
 
         # 1. PytorchScaler requires a Dataset to fit. Create a temporary one.
@@ -511,13 +522,13 @@ class SequenceMaker(_BaseMaker):
         self.test_sequence = self.scaler.transform(test_tensor).numpy().flatten()
 
         self._is_normalized = True
-        _LOGGER.info("✅ Sequence data normalized using PytorchScaler.")
+        _LOGGER.info("Sequence data normalized using PytorchScaler.")
         return self
 
     def split_data(self, test_size: float = 0.2) -> 'SequenceMaker':
         """Splits the sequence into training and testing portions."""
         if self._is_split:
-            _LOGGER.warning("⚠️ Data has already been split.")
+            _LOGGER.warning("Data has already been split.")
             return self
 
         split_idx = int(len(self.sequence) * (1 - test_size))
@@ -538,7 +549,8 @@ class SequenceMaker(_BaseMaker):
         "sequence-to-sequence": Label vectors are of the same size as the feature vectors instead of a single future prediction.
         """
         if not self._is_split:
-            raise RuntimeError("Cannot generate windows before splitting data. Call .split_data() first.")
+            _LOGGER.error("Cannot generate windows before splitting data. Call .split_data() first.")
+            raise RuntimeError()
 
         self._train_dataset = self._create_windowed_dataset(self.train_sequence, sequence_to_sequence) # type: ignore
         self._test_dataset = self._create_windowed_dataset(self.test_sequence, sequence_to_sequence) # type: ignore
@@ -550,7 +562,8 @@ class SequenceMaker(_BaseMaker):
     def _create_windowed_dataset(self, data: numpy.ndarray, use_sequence_labels: bool) -> Dataset:
         """Efficiently creates windowed features and labels using numpy."""
         if len(data) <= self.sequence_length:
-            raise ValueError("Data length must be greater than the sequence_length to create at least one window.")
+            _LOGGER.error("Data length must be greater than the sequence_length to create at least one window.")
+            raise ValueError()
             
         if not use_sequence_labels:
             features = data[:-1]
@@ -578,7 +591,8 @@ class SequenceMaker(_BaseMaker):
     def denormalize(self, data: Union[torch.Tensor, numpy.ndarray]) -> numpy.ndarray:
         """Applies inverse transformation using the stored PytorchScaler."""
         if self.scaler is None:
-            raise RuntimeError("Data was not normalized. Cannot denormalize.")
+            _LOGGER.error("Data was not normalized. Cannot denormalize.")
+            raise RuntimeError()
 
         # Ensure data is a torch.Tensor
         if isinstance(data, numpy.ndarray):
@@ -597,7 +611,8 @@ class SequenceMaker(_BaseMaker):
     def plot(self, predictions: Optional[numpy.ndarray] = None):
         """Plots the original training and testing data, with optional predictions."""
         if not self._is_split:
-            raise RuntimeError("Cannot plot before splitting data. Call .split_data() first.")
+            _LOGGER.error("Cannot plot before splitting data. Call .split_data() first.")
+            raise RuntimeError()
         
         plt.figure(figsize=(15, 6))
         plt.title("Time Series Data")
@@ -618,7 +633,8 @@ class SequenceMaker(_BaseMaker):
     def get_datasets(self) -> Tuple[Dataset, Dataset]:
         """Returns the final train and test datasets."""
         if not self._are_windows_generated:
-            raise RuntimeError("Windows have not been generated. Call .generate_windows() first.")
+            _LOGGER.error("Windows have not been generated. Call .generate_windows() first.")
+            raise RuntimeError()
         return self._train_dataset, self._test_dataset
 
 
@@ -637,7 +653,8 @@ class ResizeAspectFill:
 
     def __call__(self, image: Image.Image) -> Image.Image:
         if not isinstance(image, Image.Image):
-            raise TypeError(f"Expected PIL.Image.Image, got {type(image).__name__}")
+            _LOGGER.error(f"Expected PIL.Image.Image, got {type(image).__name__}")
+            raise TypeError()
 
         w, h = image.size
         if w == h:

ml_tools/ML_evaluation.py

@@ -110,7 +110,7 @@ def classification_metrics(save_dir: Union[str, Path], y_true: np.ndarray, y_pre
         _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}")
+        _LOGGER.error(f"Could not generate classification report heatmap: {e}")
 
     # Save Confusion Matrix
     fig_cm, ax_cm = plt.subplots(figsize=(6, 6), dpi=100)
@@ -172,7 +172,7 @@ def classification_metrics(save_dir: Union[str, Path], y_true: np.ndarray, y_pre
             
             cal_path = save_dir_path / "calibration_plot.svg"
             plt.savefig(cal_path)
-            _LOGGER.info(f"✅ Calibration plot saved as '{cal_path.name}'")
+            _LOGGER.info(f"📈 Calibration plot saved as '{cal_path.name}'")
             plt.close(fig_cal)
 
 
@@ -277,7 +277,7 @@ def shap_summary_plot(model,
     
     # --- 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.")
+        _LOGGER.error("Input data for SHAP contains NaN values. Aborting explanation.")
         return
     
     print("\n--- SHAP Value Explanation ---")
@@ -364,7 +364,7 @@ def plot_attention_importance(weights: List[torch.Tensor], feature_names: Option
         save_dir (str | Path): Directory to save the plot and summary CSV.
     """
     if not weights:
-        _LOGGER.warning("⚠️ Attention weights list is empty. Skipping importance plot.")
+        _LOGGER.error("Attention weights list is empty. Skipping importance plot.")
         return
 
     # --- Step 1: Aggregate data ---

ml_tools/ML_evaluation_multi.py

@@ -19,7 +19,7 @@ from sklearn.metrics import (
     jaccard_score
 )
 from pathlib import Path
-from typing import Union, List, Optional
+from typing import Union, List
 
 from .path_manager import make_fullpath, sanitize_filename
 from ._logger import _LOGGER
@@ -52,11 +52,14 @@ def multi_target_regression_metrics(
         save_dir (str | Path): Directory to save plots and the report.
     """
     if y_true.ndim != 2 or y_pred.ndim != 2:
-        raise ValueError("y_true and y_pred must be 2D arrays for multi-target regression.")
+        _LOGGER.error("y_true and y_pred must be 2D arrays for multi-target regression.")
+        raise ValueError()
     if y_true.shape != y_pred.shape:
-        raise ValueError("Shapes of y_true and y_pred must match.")
+        _LOGGER.error("Shapes of y_true and y_pred must match.")
+        raise ValueError()
     if y_true.shape[1] != len(target_names):
-        raise ValueError("Number of target names must match the number of columns in y_true.")
+        _LOGGER.error("Number of target names must match the number of columns in y_true.")
+        raise ValueError()
 
     save_dir_path = make_fullpath(save_dir, make=True, enforce="directory")
     metrics_summary = []
@@ -64,7 +67,7 @@ def multi_target_regression_metrics(
     _LOGGER.info("--- Multi-Target Regression Evaluation ---")
 
     for i, name in enumerate(target_names):
-        _LOGGER.info(f"  -> Evaluating target: '{name}'")
+        print(f"  -> Evaluating target: '{name}'")
         true_i = y_true[:, i]
         pred_i = y_pred[:, i]
         sanitized_name = sanitize_filename(name)
@@ -113,7 +116,7 @@ def multi_target_regression_metrics(
     summary_df = pd.DataFrame(metrics_summary)
     report_path = save_dir_path / "regression_report_multi.csv"
     summary_df.to_csv(report_path, index=False)
-    _LOGGER.info(f"✅ Full regression report saved to '{report_path.name}'")
+    _LOGGER.info(f"Full regression report saved to '{report_path.name}'")
 
 
 def multi_label_classification_metrics(
@@ -139,11 +142,14 @@ def multi_label_classification_metrics(
                            binary predictions for metrics like the confusion matrix.
     """
     if y_true.ndim != 2 or y_prob.ndim != 2:
-        raise ValueError("y_true and y_prob must be 2D arrays for multi-label classification.")
+        _LOGGER.error("y_true and y_prob must be 2D arrays for multi-label classification.")
+        raise ValueError()
     if y_true.shape != y_prob.shape:
-        raise ValueError("Shapes of y_true and y_prob must match.")
+        _LOGGER.error("Shapes of y_true and y_prob must match.")
+        raise ValueError()
     if y_true.shape[1] != len(target_names):
-        raise ValueError("Number of target names must match the number of columns in y_true.")
+        _LOGGER.error("Number of target names must match the number of columns in y_true.")
+        raise ValueError()
 
     save_dir_path = make_fullpath(save_dir, make=True, enforce="directory")
     
@@ -165,13 +171,13 @@ def multi_label_classification_metrics(
         f"Jaccard Score (macro): {j_score_macro:.4f}\n"
         f"--------------------------------------------------\n"
     )
-    _LOGGER.info(overall_report)
+    print(overall_report)
     overall_report_path = save_dir_path / "classification_report_overall.txt"
     overall_report_path.write_text(overall_report)
 
     # --- Per-Label Metrics and Plots ---
     for i, name in enumerate(target_names):
-        _LOGGER.info(f"  -> Evaluating label: '{name}'")
+        print(f"  -> Evaluating label: '{name}'")
         true_i = y_true[:, i]
         pred_i = y_pred[:, i]
         prob_i = y_prob[:, i]
@@ -215,7 +221,7 @@ def multi_label_classification_metrics(
         plt.savefig(pr_path)
         plt.close(fig_pr)
 
-    _LOGGER.info(f"✅ All individual label reports and plots saved to '{save_dir_path.name}'")
+    _LOGGER.info(f"All individual label reports and plots saved to '{save_dir_path.name}'")
 
 
 def multi_target_shap_summary_plot(
@@ -242,10 +248,10 @@ def multi_target_shap_summary_plot(
     instances_to_explain_np = instances_to_explain.numpy() if isinstance(instances_to_explain, torch.Tensor) else instances_to_explain
 
     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.")
+        _LOGGER.error("Input data for SHAP contains NaN values. Aborting explanation.")
         return
 
-    _LOGGER.info("\n--- Multi-Target SHAP Value Explanation ---")
+    _LOGGER.info("--- Multi-Target SHAP Value Explanation ---")
     model.eval()
     model.cpu()
 
@@ -262,7 +268,7 @@ def multi_target_shap_summary_plot(
     # 3. Create the KernelExplainer.
     explainer = shap.KernelExplainer(prediction_wrapper, background_summary)
 
-    _LOGGER.info("Calculating SHAP values with KernelExplainer...")
+    print("Calculating SHAP values with KernelExplainer...")
     # For multi-output models, shap_values is a list of arrays.
     shap_values_list = explainer.shap_values(instances_to_explain_np, l1_reg="aic")
 
@@ -271,7 +277,7 @@ def multi_target_shap_summary_plot(
 
     # 4. Iterate through each target's SHAP values and generate plots.
     for i, target_name in enumerate(target_names):
-        _LOGGER.info(f"  -> Generating SHAP plots for target: '{target_name}'")
+        print(f"  -> Generating SHAP plots for target: '{target_name}'")
         shap_values_for_target = shap_values_list[i]
         sanitized_target_name = sanitize_filename(target_name)
 
@@ -292,5 +298,8 @@ def multi_target_shap_summary_plot(
         plt.close()
 
     plt.ion()
-    _LOGGER.info(f"✅ All SHAP plots saved to '{save_dir_path.name}'")
+    _LOGGER.info(f"All SHAP plots saved to '{save_dir_path.name}'")
 
+
+def info():
+    _script_info(__all__)

ml_tools/ML_inference.py

@@ -59,20 +59,20 @@ class _BaseInferenceHandler(ABC):
             self.model.load_state_dict(torch.load(model_p, map_location=self.device))
             self.model.to(self.device)
             self.model.eval()  # Set the model to evaluation mode
-            _LOGGER.info(f"✅ Model state loaded from '{model_p.name}' and set to evaluation mode.")
+            _LOGGER.info(f"Model state loaded from '{model_p.name}' and set to evaluation mode.")
         except Exception as e:
-            _LOGGER.error(f"❌ Failed to load model state from '{model_p}': {e}")
+            _LOGGER.error(f"Failed to load model state from '{model_p}': {e}")
             raise
 
     def _validate_device(self, device: str) -> torch.device:
         """Validates the selected device and returns a torch.device object."""
         device_lower = device.lower()
         if "cuda" in device_lower and not torch.cuda.is_available():
-            _LOGGER.warning("⚠️ CUDA not available, switching to CPU.")
+            _LOGGER.warning("CUDA not available, switching to CPU.")
             device_lower = "cpu"
         elif device_lower == "mps" and not torch.backends.mps.is_available():
             # Your M-series Mac will appreciate this check!
-            _LOGGER.warning("⚠️ Apple Metal Performance Shaders (MPS) not available, switching to CPU.")
+            _LOGGER.warning("Apple Metal Performance Shaders (MPS) not available, switching to CPU.")
             device_lower = "cpu"
         return torch.device(device_lower)
 
@@ -144,7 +144,8 @@ class PyTorchInferenceHandler(_BaseInferenceHandler):
             A dictionary containing the raw output tensors from the model.
         """
         if features.ndim != 2:
-            raise ValueError("Input for batch prediction must be a 2D array or tensor.")
+            _LOGGER.error("Input for batch prediction must be a 2D array or tensor.")
+            raise ValueError()
 
         input_tensor = self._preprocess_input(features)
 
@@ -176,7 +177,8 @@ class PyTorchInferenceHandler(_BaseInferenceHandler):
             features = features.reshape(1, -1) # Reshape to a batch of one
 
         if features.shape[0] != 1:
-            raise ValueError("The predict() method is for a single sample. Use predict_batch() for multiple samples.")
+            _LOGGER.error("The 'predict()' method is for a single sample. Use 'predict_batch()' for multiple samples.")
+            raise ValueError()
 
         batch_results = self.predict_batch(features)
 
@@ -216,7 +218,8 @@ class PyTorchInferenceHandler(_BaseInferenceHandler):
         `target_id` must be implemented.
         """
         if self.target_id is None:
-            raise AttributeError(f"'target_id' has not been implemented.")
+            _LOGGER.error(f"'target_id' has not been implemented.")
+            raise AttributeError()
         
         if self.task == "regression":
             result = self.predict_numpy(features)[PyTorchInferenceKeys.PREDICTIONS]
@@ -252,7 +255,8 @@ class PyTorchInferenceHandlerMulti(_BaseInferenceHandler):
         super().__init__(model, state_dict, device, scaler)
 
         if task not in ["multi_target_regression", "multi_label_classification"]:
-            raise ValueError("`task` must be 'multi_target_regression' or 'multi_label_classification'.")
+            _LOGGER.error("`task` must be 'multi_target_regression' or 'multi_label_classification'.")
+            raise ValueError()
         self.task = task
         self.target_ids = target_ids
 
@@ -272,7 +276,8 @@ class PyTorchInferenceHandlerMulti(_BaseInferenceHandler):
             A dictionary containing the raw output tensors from the model.
         """
         if features.ndim != 2:
-            raise ValueError("Input for batch prediction must be a 2D array or tensor.")
+            _LOGGER.error("Input for batch prediction must be a 2D array or tensor.")
+            raise ValueError()
 
         input_tensor = self._preprocess_input(features)
 
@@ -309,7 +314,8 @@ class PyTorchInferenceHandlerMulti(_BaseInferenceHandler):
             features = features.reshape(1, -1)
 
         if features.shape[0] != 1:
-            raise ValueError("The predict() method is for a single sample. Use predict_batch() for multiple samples.")
+            _LOGGER.error("The 'predict()' method is for a single sample. 'Use predict_batch()' for multiple samples.")
+            raise ValueError()
 
         batch_results = self.predict_batch(features, classification_threshold)
 
@@ -348,7 +354,8 @@ class PyTorchInferenceHandlerMulti(_BaseInferenceHandler):
         `target_ids` must be implemented.
         """
         if self.target_ids is None:
-            raise AttributeError(f"'target_id' has not been implemented.")
+            _LOGGER.error(f"'target_id' has not been implemented.")
+            raise AttributeError()
         
         if self.task == "multi_target_regression":
             result = self.predict_numpy(features)[PyTorchInferenceKeys.PREDICTIONS].flatten().tolist()
@@ -398,18 +405,18 @@ def multi_inference_regression(handlers: list[PyTorchInferenceHandler],
     
     # Validate that the input is a 2D tensor.
     if feature_vector.ndim != 2:
-        raise ValueError("Input feature_vector must be a 1D or 2D array/tensor.")
+        _LOGGER.error("Input feature_vector must be a 1D or 2D array/tensor.")
+        raise ValueError()
     
     results: dict[str,Any] = dict()
     for handler in handlers:
         # validation
         if handler.target_id is None:
-            raise AttributeError("All inference handlers must have a 'target_id' attribute.")
+            _LOGGER.error("All inference handlers must have a 'target_id' attribute.")
+            raise AttributeError()
         if handler.task != "regression":
-            raise ValueError(
-                f"Invalid task type: The handler for target_id '{handler.target_id}' "
-                f"is for '{handler.task}', but only 'regression' tasks are supported."
-            )
+            _LOGGER.error(f"Invalid task type: The handler for target_id '{handler.target_id}' is for '{handler.task}', but only 'regression' tasks are supported.")
+            raise ValueError()
             
         # inference
         if output == "numpy":
@@ -476,7 +483,8 @@ def multi_inference_classification(
         feature_vector = feature_vector.reshape(1, -1)
     
     if feature_vector.ndim != 2:
-        raise ValueError("Input feature_vector must be a 1D or 2D array/tensor.")
+        _LOGGER.error("Input feature_vector must be a 1D or 2D array/tensor.")
+        raise ValueError()
 
     # Initialize two dictionaries for results
     labels_results: dict[str, Any] = dict()
@@ -485,12 +493,11 @@ def multi_inference_classification(
     for handler in handlers:
         # Validation
         if handler.target_id is None:
-            raise AttributeError("All inference handlers must have a 'target_id' attribute.")
+            _LOGGER.error("All inference handlers must have a 'target_id' attribute.")
+            raise AttributeError()
         if handler.task != "classification":
-            raise ValueError(
-                f"Invalid task type: The handler for target_id '{handler.target_id}' "
-                f"is for '{handler.task}', but this function only supports 'classification'."
-            )
+            _LOGGER.error(f"Invalid task type: The handler for target_id '{handler.target_id}' is for '{handler.task}', but this function only supports 'classification'.")
+            raise ValueError()
             
         # Inference
         if output == "numpy":

ml_tools/ML_models.py

@@ -34,13 +34,17 @@ class _BaseMLP(nn.Module):
 
         # --- Validation ---
         if not isinstance(in_features, int) or in_features < 1:
-            raise ValueError("in_features must be a positive integer.")
+            _LOGGER.error("'in_features' must be a positive integer.")
+            raise ValueError()
         if not isinstance(out_targets, int) or out_targets < 1:
-            raise ValueError("out_targets must be a positive integer.")
+            _LOGGER.error("'out_targets' must be a positive integer.")
+            raise ValueError()
         if not isinstance(hidden_layers, list) or not all(isinstance(n, int) for n in hidden_layers):
-            raise TypeError("hidden_layers must be a list of integers.")
+            _LOGGER.error("'hidden_layers' must be a list of integers.")
+            raise TypeError()
         if not (0.0 <= drop_out < 1.0):
-            raise ValueError("drop_out must be a float between 0.0 and 1.0.")
+            _LOGGER.error("'drop_out' must be a float between 0.0 and 1.0.")
+            raise ValueError()
         
         # --- Save configuration ---
         self.in_features = in_features
@@ -626,10 +630,8 @@ def save_architecture(model: nn.Module, directory: Union[str, Path], verbose: bo
         AttributeError: If the model does not have a `get_config()` method.
     """
     if not hasattr(model, 'get_config'):
-        raise AttributeError(
-            f"Model '{model.__class__.__name__}' does not have a 'get_config()' method. "
-            "Please implement it to return the model's constructor arguments."
-        ) 
+        _LOGGER.error(f"Model '{model.__class__.__name__}' does not have a 'get_config()' method.")
+        raise AttributeError() 
 
     # Ensure the target directory exists
     path_dir = make_fullpath(directory, make=True, enforce="directory")
@@ -644,7 +646,7 @@ def save_architecture(model: nn.Module, directory: Union[str, Path], verbose: bo
         json.dump(config, f, indent=4)
     
     if verbose:
-        _LOGGER.info(f"✅ Architecture for '{model.__class__.__name__}' saved to '{path_dir.name}'")
+        _LOGGER.info(f"Architecture for '{model.__class__.__name__}' saved to '{path_dir.name}'")
 
 
 def load_architecture(filepath: Union[str, Path], expected_model_class: type, verbose: bool=True) -> nn.Module:
@@ -674,15 +676,13 @@ def load_architecture(filepath: Union[str, Path], expected_model_class: type, ve
     config = saved_data['config']
 
     if saved_class_name != expected_model_class.__name__:
-        raise ValueError(
-            f"Model class mismatch. File specifies '{saved_class_name}', "
-            f"but you expected '{expected_model_class.__name__}'."
-        )
+        _LOGGER.error(f"Model class mismatch. File specifies '{saved_class_name}', but '{expected_model_class.__name__}' was expected.")
+        raise ValueError()
 
     # Create an instance of the model using the provided class and config
     model = expected_model_class(**config)
     if verbose:
-        _LOGGER.info(f"✅ Successfully loaded architecture for '{saved_class_name}'")
+        _LOGGER.info(f"Successfully loaded architecture for '{saved_class_name}'")
     return model
 
 

ml_tools/ML_optimization.py

@@ -127,7 +127,8 @@ def create_pytorch_problem(
         SearcherClass = GeneticAlgorithm
         
     else:
-        raise ValueError(f"Unknown algorithm '{algorithm}'.")
+        _LOGGER.error(f"Unknown algorithm '{algorithm}'.")
+        raise ValueError()
     
     # Create a factory function with all arguments pre-filled
     searcher_factory = partial(SearcherClass, problem, **searcher_kwargs)
@@ -242,7 +243,7 @@ def run_optimization(
         if verbose:
             _handle_pandas_log(pandas_logger, save_path=save_path, target_name=target_name)
         
-        _LOGGER.info(f"✅ Optimization complete. Best solution saved to '{csv_path.name}'")
+        _LOGGER.info(f"Optimization complete. Best solution saved to '{csv_path.name}'")
         return result_dict
 
     # --- MULTIPLE REPETITIONS LOGIC ---
@@ -295,7 +296,7 @@ def run_optimization(
         if pandas_logger is not None:
             _handle_pandas_log(pandas_logger, save_path=save_path, target_name=target_name)      
         
-        _LOGGER.info(f"✅ Optimal solution space complete. Results saved to '{save_path}'")
+        _LOGGER.info(f"Optimal solution space complete. Results saved to '{save_path}'")
         return None
 
 

ml_tools/ML_scaler.py

@@ -50,7 +50,7 @@ class PytorchScaler:
             PytorchScaler: A new, fitted instance of the scaler.
         """
         if not continuous_feature_indices:
-            _LOGGER.warning("⚠️ No continuous feature indices provided. Scaler will not be fitted.")
+            _LOGGER.error("No continuous feature indices provided. Scaler will not be fitted.")
             return cls()
 
         loader = DataLoader(dataset, batch_size=batch_size, shuffle=False)
@@ -72,7 +72,7 @@ class PytorchScaler:
             count += continuous_features.size(0)
 
         if count == 0:
-             _LOGGER.warning("⚠️ Dataset is empty. Scaler cannot be fitted.")
+             _LOGGER.error("Dataset is empty. Scaler cannot be fitted.")
              return cls(continuous_feature_indices=continuous_feature_indices)
 
         # Calculate mean
@@ -80,7 +80,7 @@ class PytorchScaler:
 
         # Calculate standard deviation
         if count < 2:
-            _LOGGER.warning(f"⚠️ Only one sample found. Standard deviation cannot be calculated and is set to 1.")
+            _LOGGER.warning(f"Only one sample found. Standard deviation cannot be calculated and is set to 1.")
             std = torch.ones_like(mean)
         else:
             # var = E[X^2] - (E[X])^2
@@ -101,7 +101,7 @@ class PytorchScaler:
             torch.Tensor: The transformed data tensor.
         """
         if self.mean_ is None or self.std_ is None or self.continuous_feature_indices is None:
-            _LOGGER.warning("⚠️ Scaler has not been fitted. Returning original data.")
+            _LOGGER.error("Scaler has not been fitted. Returning original data.")
             return data
 
         data_clone = data.clone()
@@ -132,7 +132,7 @@ class PytorchScaler:
             torch.Tensor: The original-scale data tensor.
         """
         if self.mean_ is None or self.std_ is None or self.continuous_feature_indices is None:
-            _LOGGER.warning("⚠️ Scaler has not been fitted. Returning original data.")
+            _LOGGER.error("Scaler has not been fitted. Returning original data.")
             return data
             
         data_clone = data.clone()
@@ -163,7 +163,7 @@ class PytorchScaler:
             'continuous_feature_indices': self.continuous_feature_indices
         }
         torch.save(state, path_obj)
-        _LOGGER.info(f"✅ PytorchScaler state saved to '{path_obj.name}'.")
+        _LOGGER.info(f"PytorchScaler state saved to '{path_obj.name}'.")
 
     @staticmethod
     def load(filepath: Union[str, Path]) -> 'PytorchScaler':
@@ -178,7 +178,7 @@ class PytorchScaler:
         """
         path_obj = make_fullpath(filepath, enforce="file")
         state = torch.load(path_obj)
-        _LOGGER.info(f"✅ PytorchScaler state loaded from '{path_obj.name}'.")
+        _LOGGER.info(f"PytorchScaler state loaded from '{path_obj.name}'.")
         return PytorchScaler(
             mean=state['mean'],
             std=state['std'],