dragon-ml-toolbox 5.3.0__py3-none-any.whl → 5.3.1__py3-none-any.whl

{dragon_ml_toolbox-5.3.0.dist-info → dragon_ml_toolbox-5.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 5.3.0
+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

{dragon_ml_toolbox-5.3.0.dist-info → dragon_ml_toolbox-5.3.1.dist-info}/RECORD

@@ -1,15 +1,15 @@
-dragon_ml_toolbox-5.3.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-5.3.0.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=oFHg-OytOzPYTzBR_wIRHhP71cMn3aupDeT59ABsXlQ,11576
-ml_tools/ML_callbacks.py,sha256=eOCSc-1_e5vC2dQN1ydHGKDLeJ3DqB-eLRLuXp2DpFM,13257
+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=4dVqe6JF1Ukmk1sAcY8E5EG1oB1_oy2HXE5OT-pZwCs,10273
+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=zGKpWW4SL1-3iiHglDP-dkuADL73T0kxs3Dc-Lyishs,9671
-ml_tools/ML_trainer.py,sha256=t58Ka6ryaYm0Fi5xje-e-fkmz9DwDLIeJLbh04n_gDg,15034
+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
@@ -26,7 +26,7 @@ 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=T5xbxzBr14odUj7KncSeg-tJzqjmSDLOOmxEaGYLLi4,18447
-dragon_ml_toolbox-5.3.0.dist-info/METADATA,sha256=Lu_JBMfkCPssLk-a2v4b-oZu86cFK1OIB4HtHspVRIk,6643
-dragon_ml_toolbox-5.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-5.3.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-5.3.0.dist-info/RECORD,,
+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/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
@@ -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():

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_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):