dragon-ml-toolbox 5.2.2__py3-none-any.whl → 5.3.1__py3-none-any.whl

{dragon_ml_toolbox-5.2.2.dist-info → dragon_ml_toolbox-5.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 5.2.2
+Version: 5.3.1
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -18,7 +18,7 @@ Requires-Dist: numpy; extra == "base"
 Requires-Dist: polars; extra == "base"
 Requires-Dist: joblib; extra == "base"
 Provides-Extra: ml
-Requires-Dist: numpy; extra == "ml"
+Requires-Dist: numpy>=2.0; extra == "ml"
 Requires-Dist: pandas; extra == "ml"
 Requires-Dist: polars; extra == "ml"
 Requires-Dist: joblib; extra == "ml"

{dragon_ml_toolbox-5.2.2.dist-info → dragon_ml_toolbox-5.3.1.dist-info}/RECORD

@@ -1,15 +1,15 @@
-dragon_ml_toolbox-5.2.2.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-5.2.2.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+dragon_ml_toolbox-5.3.1.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-5.3.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
 ml_tools/ETL_engineering.py,sha256=4wwZXi9_U7xfCY70jGBaKniOeZ0m75ppxWpQBd_DmLc,39369
 ml_tools/GUI_tools.py,sha256=n4ZZ5kEjwK5rkOCFJE41HeLFfjhpJVLUSzk9Kd9Kr_0,45410
-ml_tools/MICE_imputation.py,sha256=b6ZTs8RedXFifOpuMCzr68xM16mCBVh1Ua6kcGfiVtg,11462
-ml_tools/ML_callbacks.py,sha256=xiJ6NnoVwF_TVak6sYzwWFk4CI3vRJGjxvGI1Yq6euw,13332
-ml_tools/ML_datasetmaster.py,sha256=IzT2v1o71PgYCFi9RXccBnmH-t-ExzX8sn9cCD2gz-Y,33603
-ml_tools/ML_evaluation.py,sha256=4dVqe6JF1Ukmk1sAcY8E5EG1oB1_oy2HXE5OT-pZwCs,10273
+ml_tools/MICE_imputation.py,sha256=oFHg-OytOzPYTzBR_wIRHhP71cMn3aupDeT59ABsXlQ,11576
+ml_tools/ML_callbacks.py,sha256=hOGWYM6ndaH0ibaHgM14j74MtWFalToY-oTnB2jsQ4A,13268
+ml_tools/ML_datasetmaster.py,sha256=bbKCNA_b_uDIfxP9YIYKZm-VSfUSD15LvegFxpE9DIQ,34315
+ml_tools/ML_evaluation.py,sha256=LX6UkUC80y43lYKBkw03CptZ3PJGkZXfmZZHL-2kd1s,11590
 ml_tools/ML_inference.py,sha256=Fh-X2UQn3AznWBjf-7iPSxwE-EzkGQm1VEIRUAkURmE,5336
 ml_tools/ML_models.py,sha256=SJhKHGAN2VTBqzcHUOpFWuVZ2Y7U1M4P_axG_LNYWcI,6460
-ml_tools/ML_optimization.py,sha256=2L9BSUzgLOEwBU84TN1qDh1KAOJ4R6C6NYSe7jmE4RI,9656
-ml_tools/ML_trainer.py,sha256=t58Ka6ryaYm0Fi5xje-e-fkmz9DwDLIeJLbh04n_gDg,15034
+ml_tools/ML_optimization.py,sha256=zGKpWW4SL1-3iiHglDP-dkuADL73T0kxs3Dc-Lyishs,9671
+ml_tools/ML_trainer.py,sha256=ENOxTq07kWYn7ZolMfXYLSy-cLZOdty0dRmutA84SV4,15146
 ml_tools/PSO_optimization.py,sha256=stH2Ux1sftQgX5EwLc85kHcoT4Rmz6zv7sH2yzf4Zrw,22710
 ml_tools/RNN_forecast.py,sha256=2CyjBLSYYc3xLHxwLXUmP5Qv8AmV1OB_EndETNX1IBk,1956
 ml_tools/SQL.py,sha256=9zzS6AFEJM9aj6nE31hDe8S9TqLonk-J1amwZoiHNbk,10468
@@ -18,15 +18,15 @@ ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
 ml_tools/_logger.py,sha256=TpgYguxO-CWYqqgLW0tqFjtwZ58PE_W2OCfWNGZr0n0,1175
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/custom_logger.py,sha256=njM_0XPbQ1S-x5LeSQAaTo2if-XVOR_pQSGg4EDeiTU,4603
-ml_tools/data_exploration.py,sha256=qc_Oolxco2x9IhlYu5zPIuVBGiBw65HnypuGm8cQOOM,23677
+ml_tools/data_exploration.py,sha256=P4f8OpRa7Q4i-11nkppxXw5Lx2lwlpn20GwWBbN_xbM,23901
 ml_tools/ensemble_inference.py,sha256=0SNX3YAz5bpvtwYmqEwqyWeIJP2Pb-v-bemENRSO7qg,9426
 ml_tools/ensemble_learning.py,sha256=Zi1oy6G2FWnTI5hBwjlexwF3JKALFS2FN6F8HAlVi_s,35391
 ml_tools/handle_excel.py,sha256=J9iwIqMZemoxK49J5osSwp9Ge0h9YTKyYGbOm53hcno,13007
 ml_tools/keys.py,sha256=kK9UF-hek2VcPGFILCKl5geoN6flmMOu7IzhdEA6z5Y,1068
 ml_tools/optimization_tools.py,sha256=MuT4OG7_r1QqLUti-yYix7QeCpglezD0oe9BDCq0QXk,5086
 ml_tools/path_manager.py,sha256=Z8e7w3MPqQaN8xmTnKuXZS6CIW59BFwwqGhGc00sdp4,13692
-ml_tools/utilities.py,sha256=mz-M351DzxWxnYVcLX-7ZQ6c-RGoCV9g4VTS9Qif2Es,18348
-dragon_ml_toolbox-5.2.2.dist-info/METADATA,sha256=1xc1_iWoGsLxwEFcyLRRSJCJJNdQZNsVHCSykfaVKGQ,6638
-dragon_ml_toolbox-5.2.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-5.2.2.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-5.2.2.dist-info/RECORD,,
+ml_tools/utilities.py,sha256=T5xbxzBr14odUj7KncSeg-tJzqjmSDLOOmxEaGYLLi4,18447
+dragon_ml_toolbox-5.3.1.dist-info/METADATA,sha256=XMn0E2Bh_6X97SScFy08jxJvo_KYeS5yuApaHTDPeqY,6643
+dragon_ml_toolbox-5.3.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-5.3.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-5.3.1.dist-info/RECORD,,

ml_tools/MICE_imputation.py

@@ -29,6 +29,8 @@ def apply_mice(df: pd.DataFrame, df_name: str, binary_columns: Optional[list[str
         random_state=random_state
     )
     
+    _LOGGER.info("➡️ MICE imputation running...")
+    
     # Perform MICE with n iterations per dataset
     kernel.mice(iterations)
     
@@ -61,6 +63,8 @@ def apply_mice(df: pd.DataFrame, df_name: str, binary_columns: Optional[list[str
         assert all(imputed_df.index == df.index), f"❌ Index mismatch in dataset {subname}" # type: ignore
     # print("✅ All imputed datasets match the original DataFrame indexes.")
     
+    _LOGGER.info("✅ MICE imputation complete.")
+    
     return kernel, imputed_datasets, imputed_dataset_names
 
 

ml_tools/ML_callbacks.py

@@ -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=LogKeys.VAL_LOSS, min_delta: float=0.0, patience: int=5, mode: Literal['auto', 'min', 'max']='auto', verbose: int=0):
         super().__init__()
         self.monitor = monitor
         self.patience = patience
@@ -148,13 +148,13 @@ class EarlyStopping(Callback):
             else: # Default to min mode for loss or other metrics
                 self.monitor_op = np.less
         
-        self.best = np.Inf if self.monitor_op == np.less else -np.Inf # type: ignore
+        self.best = np.inf if self.monitor_op == np.less else -np.inf
 
     def on_train_begin(self, logs=None):
         # Reset state at the beginning of training
         self.wait = 0
         self.stopped_epoch = 0
-        self.best = np.Inf if self.monitor_op == np.less else -np.Inf # type: ignore
+        self.best = np.inf if self.monitor_op == np.less else -np.inf
                     
     def on_epoch_end(self, epoch, logs=None):
         current = logs.get(self.monitor) # type: ignore
@@ -202,7 +202,7 @@ class ModelCheckpoint(Callback):
         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):
+                 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():
@@ -228,11 +228,11 @@ class ModelCheckpoint(Callback):
         else:
             self.monitor_op = np.less if 'loss' in self.monitor else np.greater
         
-        self.best = np.Inf if self.monitor_op == np.less else -np.Inf # type: ignore
+        self.best = np.inf if self.monitor_op == np.less else -np.inf
 
     def on_train_begin(self, logs=None):
         """Reset state when training starts."""
-        self.best = np.Inf if self.monitor_op == np.less else -np.Inf # type: ignore
+        self.best = np.inf if self.monitor_op == np.less else -np.inf
         self.saved_checkpoints = []
         self.last_best_filepath = None
 
@@ -251,7 +251,7 @@ class ModelCheckpoint(Callback):
             return
 
         if self.monitor_op(current, self.best):
-            old_best_str = f"{self.best:.4f}" if self.best not in [np.Inf, -np.Inf] else "inf" # type: ignore
+            old_best_str = f"{self.best:.4f}" if self.best not in [np.inf, -np.inf] else "inf"
             
             # Create a descriptive filename
             filename = f"epoch_{epoch}-{self.monitor}_{current:.4f}.pth"

ml_tools/ML_datasetmaster.py

@@ -128,17 +128,18 @@ class DatasetMaker(_BaseMaker):
     - Automated (single call):
     ```python
     maker = DatasetMaker(df, label_col='target')
-    maker.process() # uses simplified arguments
+    maker.auto_process() # uses simplified arguments
     train_ds, test_ds = maker.get_datasets()
     ```
     """
-    def __init__(self, pandas_df: pandas.DataFrame, label_col: str):
+    def __init__(self, pandas_df: pandas.DataFrame, label_col: str, kind: Literal["regression", "classification"]):
         super().__init__()
         if not isinstance(pandas_df, pandas.DataFrame):
             raise TypeError("Input must be a pandas.DataFrame.")
         if label_col not in pandas_df.columns:
             raise ValueError(f"Label column '{label_col}' not found in DataFrame.")
-
+        
+        self.kind = kind
         self.labels = pandas_df[label_col]
         self.features = pandas_df.drop(columns=label_col)
         self.labels_map = None
@@ -277,7 +278,7 @@ class DatasetMaker(_BaseMaker):
         _LOGGER.info(f"Balancing complete. New training set size: {len(self.features_train)} samples.")
         return self
 
-    def process(self, test_size: float = 0.2, cat_method: Literal["one-hot", "embed"] = "one-hot", normalize_method: Literal["standard", "minmax"] = "standard", 
+    def auto_process(self, test_size: float = 0.2, cat_method: Literal["one-hot", "embed"] = "one-hot", normalize_method: Literal["standard", "minmax"] = "standard", 
                 balance: bool = False, random_state: Optional[int] = None) -> 'DatasetMaker':
         """Runs a standard, fully automated preprocessing pipeline."""
         _LOGGER.info("--- 🤖 Running Automated Processing Pipeline ---")
@@ -334,8 +335,10 @@ class DatasetMaker(_BaseMaker):
         if not self._is_split:
             raise RuntimeError("Data has not been split yet. Call .split_data() or .process() first.")
         
-        self._train_dataset = _PytorchDataset(self.features_train, self.labels_train) # type: ignore
-        self._test_dataset = _PytorchDataset(self.features_test, self.labels_test) # type: ignore
+        label_dtype = torch.float32 if self.kind == "regression" else torch.int64
+        
+        self._train_dataset = _PytorchDataset(self.features_train, self.labels_train, labels_dtype=label_dtype) # type: ignore
+        self._test_dataset = _PytorchDataset(self.features_test, self.labels_test, labels_dtype=label_dtype)  # type: ignore
         
         return self._train_dataset, self._test_dataset
     
@@ -382,12 +385,13 @@ class SimpleDatasetMaker:
 
     Args:
         pandas_df (pandas.DataFrame): The pre-processed input DataFrame with numerical data.
+        kind (Literal["regression", "classification"]): The type of ML task. This determines the data type of the labels.
         test_size (float): The proportion of the dataset to allocate to the
                            test split.
         random_state (int): The seed for the random number generator for
                             reproducibility.
     """
-    def __init__(self, pandas_df: pandas.DataFrame, test_size: float = 0.2, random_state: int = 42):
+    def __init__(self, pandas_df: pandas.DataFrame, kind: Literal["regression", "classification"], test_size: float = 0.2, random_state: int = 42):
         """
         Attributes:
             `train_dataset` -> PyTorch Dataset
@@ -398,9 +402,11 @@ class SimpleDatasetMaker:
             
         The ID can be manually set to any string if needed, it is `None` by default.
         """
-        
+        # Validation
         if not isinstance(pandas_df, pandas.DataFrame):
-            raise TypeError("Input must be a pandas.DataFrame.")        
+            raise TypeError("Input must be a pandas.DataFrame.")
+        if kind not in ["regression", "classification"]:
+            raise ValueError("`kind` must be 'regression' or 'classification'.")
 
         # 1. Identify features and target
         features = pandas_df.iloc[:, :-1]
@@ -422,9 +428,11 @@ class SimpleDatasetMaker:
         self._y_train_shape = y_train.shape
         self._y_test_shape = y_test.shape
 
-        # 3. Convert to PyTorch Datasets
-        self._train_ds = _PytorchDataset(X_train.values, y_train.values)
-        self._test_ds = _PytorchDataset(X_test.values, y_test.values)
+        # 3. Convert to PyTorch Datasets with the correct label dtype
+        label_dtype = torch.float32 if kind == "regression" else torch.int64
+        
+        self._train_ds = _PytorchDataset(X_train.values, y_train.values, labels_dtype=label_dtype)
+        self._test_ds = _PytorchDataset(X_test.values, y_test.values, labels_dtype=label_dtype)
 
     @property
     def train_dataset(self) -> Dataset:

ml_tools/ML_evaluation.py

@@ -195,7 +195,7 @@ def regression_metrics(y_true: np.ndarray, y_pred: np.ndarray, save_dir: Optiona
         plt.close(fig_tvp)
 
 
-def shap_summary_plot(model, background_data: torch.Tensor, instances_to_explain: torch.Tensor, 
+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.
@@ -207,24 +207,54 @@ def shap_summary_plot(model, background_data: torch.Tensor, 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 ---")
-    print("Calculating SHAP values... ")
     
     model.eval()
     model.cpu()
     
-    explainer = shap.DeepExplainer(model, background_data)
-    shap_values = explainer.shap_values(instances_to_explain)
-
-    shap_values_for_plot = shap_values[1] if isinstance(shap_values, list) else shap_values
-    if isinstance(shap_values, list):
-        _LOGGER.info("Using SHAP values for the positive class (class 1) for plots.")
+    # 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_for_plot, instances_to_explain, feature_names=feature_names, plot_type="bar", show=False)
+        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)
@@ -233,7 +263,7 @@ def shap_summary_plot(model, background_data: torch.Tensor, instances_to_explain
 
         # Save Dot Plot
         dot_path = save_dir_path / "shap_dot_plot.svg"
-        shap.summary_plot(shap_values_for_plot, instances_to_explain, feature_names=feature_names, plot_type="dot", show=False)
+        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)
@@ -242,18 +272,25 @@ def shap_summary_plot(model, background_data: torch.Tensor, instances_to_explain
 
         # Save Summary Data to CSV
         summary_path = save_dir_path / "shap_summary.csv"
-        mean_abs_shap = np.abs(shap_values_for_plot).mean(axis=0)
+        # 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_for_plot, instances_to_explain, feature_names=feature_names, plot_type="dot")
+        shap.summary_plot(shap_values, instances_to_explain_np, feature_names=feature_names, plot_type="dot")
 
 
 def info():

ml_tools/ML_optimization.py

@@ -49,6 +49,7 @@ def create_pytorch_problem(
             selected search algorithm's constructor (e.g., stdev_init=0.5 for CMAES).
 
     Returns:
+        Tuple:
         A tuple containing the configured evotorch.Problem and evotorch.Searcher.
     """
     lower_bounds, upper_bounds = bounds

ml_tools/ML_trainer.py

@@ -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):

ml_tools/data_exploration.py

@@ -7,6 +7,7 @@ from typing import Union, Literal, Dict, Tuple, List, Optional
 from pathlib import Path
 from .path_manager import sanitize_filename, make_fullpath
 from ._script_info import _script_info
+from ._logger import _LOGGER
 import re
 
 
@@ -55,7 +56,7 @@ def summarize_dataframe(df: pd.DataFrame, round_digits: int = 2):
         ].round(round_digits)
         summary = summary.join(summary_numeric, how='left')
 
-    print(f"Shape: {df.shape}")
+    print(f"DataFrame Shape: {df.shape}")
     return summary
 
 
@@ -98,7 +99,7 @@ def drop_constant_columns(df: pd.DataFrame, verbose: bool = True) -> pd.DataFram
 
     dropped_columns = original_columns - set(cols_to_keep)
     if verbose:
-        print(f"🧹 Dropped {len(dropped_columns)} constant columns.")
+        _LOGGER.info(f"🧹 Dropped {len(dropped_columns)} constant columns.")
         if dropped_columns:
             for dropped_column in dropped_columns:
                 print(f"    {dropped_column}")
@@ -129,10 +130,10 @@ def drop_rows_with_missing_data(df: pd.DataFrame, targets: Optional[list[str]],
         valid_targets = _validate_columns(df_clean, targets)
         target_na = df_clean[valid_targets].isnull().all(axis=1)
         if target_na.any():
-            print(f"🧹 Dropping {target_na.sum()} rows with all target columns missing.")
+            _LOGGER.info(f"🧹 Dropping {target_na.sum()} rows with all target columns missing.")
             df_clean = df_clean[~target_na]
         else:
-            print("✅ No rows with all targets missing.")
+            _LOGGER.info("✅ No rows with all targets missing.")
     else:
         valid_targets = []
 
@@ -142,12 +143,12 @@ def drop_rows_with_missing_data(df: pd.DataFrame, targets: Optional[list[str]],
         feature_na_frac = df_clean[feature_cols].isnull().mean(axis=1)
         rows_to_drop = feature_na_frac[feature_na_frac > threshold].index
         if len(rows_to_drop) > 0:
-            print(f"🧹 Dropping {len(rows_to_drop)} rows with more than {threshold*100:.0f}% missing feature data.")
+            _LOGGER.info(f"🧹 Dropping {len(rows_to_drop)} rows with more than {threshold*100:.0f}% missing feature data.")
             df_clean = df_clean.drop(index=rows_to_drop)
         else:
-            print(f"✅ No rows exceed the {threshold*100:.0f}% missing feature data threshold.")
+            _LOGGER.info(f"✅ No rows exceed the {threshold*100:.0f}% missing feature data threshold.")
     else:
-        print("⚠️ No feature columns available to evaluate.")
+        _LOGGER.warning("⚠️ No feature columns available to evaluate.")
 
     return df_clean
 
@@ -207,7 +208,7 @@ def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7, sho
     cols_to_drop = missing_fraction[missing_fraction > threshold].index
 
     if len(cols_to_drop) > 0:
-        print(f"Dropping columns with more than {threshold*100:.0f}% missing data:")
+        _LOGGER.info(f"Dropping columns with more than {threshold*100:.0f}% missing data:")
         print(list(cols_to_drop))
         
         result_df = df.drop(columns=cols_to_drop)
@@ -216,7 +217,7 @@ def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7, sho
         
         return result_df
     else:
-        print(f"No columns have more than {threshold*100:.0f}% missing data.")
+        _LOGGER.info(f"No columns have more than {threshold*100:.0f}% missing data.")
         return df
 
 
@@ -311,7 +312,7 @@ def plot_correlation_heatmap(df: pd.DataFrame,
     """
     numeric_df = df.select_dtypes(include='number')
     if numeric_df.empty:
-        print("No numeric columns found. Heatmap not generated.")
+        _LOGGER.warning("⚠️ No numeric columns found. Heatmap not generated.")
         return
     
     corr = numeric_df.corr(method=method)
@@ -348,7 +349,7 @@ def plot_correlation_heatmap(df: pd.DataFrame,
         full_path = save_path / plot_title
         
         plt.savefig(full_path, bbox_inches="tight", format='svg')
-        print(f"Saved correlation heatmap: '{plot_title}'")
+        _LOGGER.info(f"Saved correlation heatmap: '{plot_title}'")
     
     plt.show()
     plt.close()
@@ -454,7 +455,7 @@ def plot_value_distributions(df: pd.DataFrame, save_dir: Union[str, Path], bin_t
     _plot_helper(dict_=dict_to_plot_std, target_dir=std_dir, ylabel="Counts")
     _plot_helper(dict_=dict_to_plot_freq, target_dir=freq_dir, ylabel="Frequency")
 
-    print(f"Saved {saved_plots} plot(s)")
+    _LOGGER.info(f"Saved {saved_plots} value distribution plots.")
 
 
 def clip_outliers_single(
@@ -479,17 +480,17 @@ def clip_outliers_single(
         None: if a problem with the dataframe column occurred.
     """
     if column not in df.columns:
-        print(f"Column '{column}' not found in DataFrame.")
+        _LOGGER.warning(f"⚠️ Column '{column}' not found in DataFrame.")
         return None
 
     if not pd.api.types.is_numeric_dtype(df[column]):
-        print(f"Column '{column}' must be numeric.")
+        _LOGGER.warning(f"⚠️ Column '{column}' must be numeric.")
         return None
 
     new_df = df.copy(deep=True)
     new_df[column] = new_df[column].clip(lower=min_val, upper=max_val)
 
-    print(f"Column '{column}' clipped to range [{min_val}, {max_val}].")
+    _LOGGER.info(f"Column '{column}' clipped to range [{min_val}, {max_val}].")
     return new_df
 
 
@@ -539,10 +540,10 @@ def clip_outliers_multi(
             skipped_columns.append((col, str(e)))
             continue
         
-    print(f"Clipped {clipped_columns} columns.")
+    _LOGGER.info(f"Clipped {clipped_columns} columns.")
 
     if skipped_columns:
-        print("\n⚠️ Skipped columns:")
+        _LOGGER.warning("⚠️ Skipped columns:")
         for col, msg in skipped_columns:
             print(f" - {col}: {msg}")
 
@@ -574,7 +575,7 @@ def match_and_filter_columns_by_regex(
     matched_columns = df.columns[mask].to_list()
     filtered_df = df.loc[:, mask]
     
-    print(f"{len(matched_columns)} column(s) match the regex pattern '{pattern}'.")
+    _LOGGER.info(f"{len(matched_columns)} columns match the regex pattern '{pattern}'.")
 
     return filtered_df, matched_columns
 
@@ -628,11 +629,11 @@ def standardize_percentages(
     for col in columns:
         # --- Robustness Checks ---
         if col not in df_copy.columns:
-            print(f"Warning: Column '{col}' not found. Skipping.")
+            _LOGGER.warning(f"⚠️ Column '{col}' not found. Skipping.")
             continue
 
         if not is_numeric_dtype(df_copy[col]):
-            print(f"Warning: Column '{col}' is not numeric. Skipping.")
+            _LOGGER.warning(f"⚠️ Column '{col}' is not numeric. Skipping.")
             continue
 
         # --- Applying the Logic ---

ml_tools/utilities.py

@@ -8,6 +8,7 @@ import joblib
 from joblib.externals.loky.process_executor import TerminatedWorkerError
 from .path_manager import sanitize_filename, make_fullpath, list_csv_paths
 from ._script_info import _script_info
+from ._logger import _LOGGER
 
 
 # Keep track of available tools
@@ -81,7 +82,7 @@ def load_dataframe(
         raise ValueError(f"❌ DataFrame '{df_name}' loaded from '{path}' is empty.")
 
     if verbose:
-        print(f"\n💾 Loaded {kind.upper()} dataset: '{df_name}' with shape: {df.shape}")
+        _LOGGER.info(f"💾 Loaded {kind.upper()} dataset: '{df_name}' with shape: {df.shape}")
     
     return df, df_name
 
@@ -166,7 +167,7 @@ def merge_dataframes(
         merged_df = merged_df.reset_index(drop=True)
     
     if verbose:
-        print(f"\n✅ Merged DataFrame shape: {merged_df.shape}")
+        _LOGGER.info(f"✅ Merged DataFrame shape: {merged_df.shape}")
 
     return merged_df
 
@@ -185,7 +186,7 @@ def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Union[str,Pa
     """
     # This check works for both pandas and polars
     if df.shape[0] == 0:
-        print(f"⚠️ Attempting to save an empty DataFrame: '{filename}'. Process Skipped.")
+        _LOGGER.warning(f"⚠️ Attempting to save an empty DataFrame: '{filename}'. Process Skipped.")
         return
     
     # Create the directory if it doesn't exist
@@ -207,7 +208,7 @@ def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Union[str,Pa
         # This error handles cases where an unsupported type is passed
         raise TypeError(f"❌ Unsupported DataFrame type: {type(df)}. Must be pandas or polars.")
     
-    print(f"\n✅ Saved dataset: '{filename}' with shape: {df.shape}")
+    _LOGGER.info(f"✅ Saved dataset: '{filename}' with shape: {df.shape}")
 
 
 def normalize_mixed_list(data: list, threshold: int = 2) -> list[float]:
@@ -382,11 +383,11 @@ def serialize_object(obj: Any, save_dir: Union[str,Path], filename: str, verbose
         if raise_on_error:
             raise Exception(message)
         else:
-            print(message)
+            _LOGGER.warning(message)
         return None
     else:
         if verbose:
-            print(f"\n✅ Object of type '{type(obj)}' saved to '{full_path}'")
+            _LOGGER.info(f"✅ Object of type '{type(obj)}' saved to '{full_path}'")
         return None
 
 
@@ -409,11 +410,11 @@ def deserialize_object(filepath: Union[str,Path], verbose: bool=True, raise_on_e
         if raise_on_error:
             raise Exception(message)
         else:
-            print(message)
+            _LOGGER.warning(message)
         return None
     else:
         if verbose:
-            print(f"\n✅ Loaded object of type '{type(obj)}'")
+            _LOGGER.info(f"✅ Loaded object of type '{type(obj)}'")
         return obj
 
 
@@ -500,10 +501,10 @@ def train_dataset_orchestrator(list_of_dirs: list[Union[str,Path]],
                     save_dataframe(df=df, save_dir=save_dir, filename=filename)
                     total_saved += 1
             except Exception as e:
-                print(f"⚠️ Failed to process file '{df_path}'. Reason: {e}")
+                _LOGGER.warning(f"⚠️ Failed to process file '{df_path}'. Reason: {e}")
                 continue 
 
-    print(f"\n✅ {total_saved} single-target datasets were created.")
+    _LOGGER.info(f"✅ {total_saved} single-target datasets were created.")
 
 
 def info():