dragon-ml-toolbox 20.8.0__py3-none-any.whl → 20.9.0__py3-none-any.whl

{dragon_ml_toolbox-20.8.0.dist-info → dragon_ml_toolbox-20.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.8.0
+Version: 20.9.0
 Summary: Complete pipelines and helper tools for data science and machine learning projects.
 Author-email: Karl Luigi Loza Vidaurre <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-20.8.0.dist-info → dragon_ml_toolbox-20.9.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-20.8.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-20.8.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
+dragon_ml_toolbox-20.9.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-20.9.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
 ml_tools/ETL_cleaning/__init__.py,sha256=gLRHF-qzwpqKTvbbn9chIQELeUDh_XGpBRX28j-5IqI,545
@@ -34,15 +34,16 @@ ml_tools/ML_configuration/_metrics.py,sha256=KJM7HQeoEmJUUUrxNa4wYf2N9NawGPJoy7A
 ml_tools/ML_configuration/_models.py,sha256=lvuuqvD6DWUzOa3i06NZfrdfOi9bu2e26T_QO6BGMSw,7629
 ml_tools/ML_configuration/_training.py,sha256=_M_TwouHFNbGrZQtQNAvyG_poSVpmN99cbyUonZsHhk,8969
 ml_tools/ML_datasetmaster/__init__.py,sha256=UltQzuXnlXVCkD-aeA5TW4IcMVLnQf1_aglawg4WyrI,580
-ml_tools/ML_datasetmaster/_base_datasetmaster.py,sha256=lmqo9CN09xMu-YKYtKEnC2ZEzkxcZFJ0rS1B7K2-PKY,14691
+ml_tools/ML_datasetmaster/_base_datasetmaster.py,sha256=IgyVzRY3mlKDyBDklawvPF9SMjZFu8T2red6M-3MlQ4,16074
 ml_tools/ML_datasetmaster/_datasetmaster.py,sha256=Oy2UE3YJpKTaFwQF5TkQLgLB54-BFw_5b8wIPTxZIKU,19157
 ml_tools/ML_datasetmaster/_sequence_datasetmaster.py,sha256=cW3fuILZWs-7Yuo4T2fgGfTC4vwho3Gp4ohIKJYS7O0,18452
 ml_tools/ML_datasetmaster/_vision_datasetmaster.py,sha256=kvSqXYeNBN1JSRfSEEXYeIcsqy9HsJAl_EwFWClqlsw,67025
 ml_tools/ML_evaluation/__init__.py,sha256=e3c8JNP0tt4Kxc7QSQpGcOgrxf8JAucH4UkJvJxUL2E,1122
-ml_tools/ML_evaluation/_classification.py,sha256=Te5ckLfBCUyb3QO9vZ_mlJF5wS5LoajXC54k1Fkct-U,33938
+ml_tools/ML_evaluation/_classification.py,sha256=0URqIhNEgWedy-SYRmIJ2ejLKqatiuOU7qelJ6Cv3OE,33939
 ml_tools/ML_evaluation/_feature_importance.py,sha256=mTwi3LKom_axu6UFKunELj30APDdhG9GQC2w7I9mYhI,17137
+ml_tools/ML_evaluation/_helpers.py,sha256=kE1TSYIOAAcYI1EjdudyTfFeU47Wrl0E9eNL1EOwbKg,1217
 ml_tools/ML_evaluation/_loss.py,sha256=1a4O25i3Ya_3naNZNL7ELLUL46BY86g1scA7d7q2UFM,3625
-ml_tools/ML_evaluation/_regression.py,sha256=hnT2B2_6AnQ7aA7uk-X2lZL9G5JFGCduDXyZbr1gFCA,11037
+ml_tools/ML_evaluation/_regression.py,sha256=UZA7_fg85ZKJQWszioWDtmkplSiXeHJk2fBYR5bRXHY,11225
 ml_tools/ML_evaluation/_sequence.py,sha256=gUk9Uvmy7MrXkfrriMnfypkgJU5XERHdqekTa2gBaOM,8004
 ml_tools/ML_evaluation/_vision.py,sha256=abBHQ6Z2GunHNusL3wcLgfI1FVNA6hBUBTq1eOA8FSA,11489
 ml_tools/ML_evaluation_captum/_ML_evaluation_captum.py,sha256=6g3ymSxJGHXxwIN7WCD2Zi9zxKWEv-Qskd2cCGQQJ5Y,18439
@@ -118,7 +119,7 @@ ml_tools/ensemble_learning/_ensemble_learning.py,sha256=MHDZBR20_nStlSSeThFI3bSu
 ml_tools/excel_handler/__init__.py,sha256=AaWM3n_dqBhJLTs3OEA57ex5YykKXNOwVCyHlVsdnqI,530
 ml_tools/excel_handler/_excel_handler.py,sha256=TODudmeQgDSdxUKzLfAzizs--VL-g8WxDOfQ4sgxxLs,13965
 ml_tools/keys/__init__.py,sha256=-0c2pmrhyfROc-oQpEjJGLBMhSagA3CyFijQaaqZRqU,399
-ml_tools/keys/_keys.py,sha256=jBhw99SRTlBkb9EFMDLZA86_kaHT4YLxkljDYRCTarE,9389
+ml_tools/keys/_keys.py,sha256=56hlyPl2VUMsq7cFFLBypWHr-JU6ehWGwZG38l6IjI0,9389
 ml_tools/math_utilities/__init__.py,sha256=K7Obkkc4rPKj4EbRZf1BsXHfiCg7FXYv_aN9Yc2Z_Vg,400
 ml_tools/math_utilities/_math_utilities.py,sha256=BYHIVcM9tuKIhVrkgLLiM5QalJ39zx7dXYy_M9aGgiM,9012
 ml_tools/optimization_tools/__init__.py,sha256=KD8JXpfGuPndO4AHnjJGu6uV1GRwhOfboD0KZV45kzw,658
@@ -142,7 +143,7 @@ ml_tools/utilities/__init__.py,sha256=h4lE3SQstg-opcQj6QSKhu-HkqSbmHExsWoM9vC5D9
 ml_tools/utilities/_translate.py,sha256=U8hRPa3PmTpIf9n9yR3gBGmp_hkcsjQLwjAHSHc0WHs,10325
 ml_tools/utilities/_utility_save_load.py,sha256=EFvFaTaHahDQWdJWZr-j7cHqRbG_Xrpc96228JhV-bs,16773
 ml_tools/utilities/_utility_tools.py,sha256=bN0J9d1S0W5wNzNntBWqDsJcEAK7-1OgQg3X2fwXns0,6918
-dragon_ml_toolbox-20.8.0.dist-info/METADATA,sha256=EVzUhpCzHarcTicuqc_t4prSuJdXGuCppSX7wnIv1JY,7888
-dragon_ml_toolbox-20.8.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-20.8.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-20.8.0.dist-info/RECORD,,
+dragon_ml_toolbox-20.9.0.dist-info/METADATA,sha256=ehKhp6BpCkHcZnWpcoZU53rn4T0yI0Dboq3eH2vx8LU,7888
+dragon_ml_toolbox-20.9.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-20.9.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-20.9.0.dist-info/RECORD,,

ml_tools/ML_datasetmaster/_base_datasetmaster.py

@@ -133,7 +133,7 @@ class _BaseDatasetMaker(ABC):
 
         # Get continuous feature indices *from the schema*
         if schema.continuous_feature_names:
-            if verbose >= 2:
+            if verbose >= 3:
                 _LOGGER.info("Getting continuous feature indices from schema.")
             try:
                 # Convert columns to a standard list for .index()
@@ -189,7 +189,7 @@ class _BaseDatasetMaker(ABC):
         # ------------------------------------------------------------------
 
         if self.target_scaler is None:
-            if verbose >= 2:
+            if verbose >= 3:
                 _LOGGER.info("Fitting a new DragonScaler on training targets.")
             # Convert to float tensor for calculation
             y_train_tensor = torch.tensor(y_train_arr, dtype=torch.float32)
@@ -202,6 +202,9 @@ class _BaseDatasetMaker(ABC):
             y_val_tensor = self.target_scaler.transform(torch.tensor(y_val_arr, dtype=torch.float32))
             y_test_tensor = self.target_scaler.transform(torch.tensor(y_test_arr, dtype=torch.float32))
             return y_train_tensor.numpy(), y_val_tensor.numpy(), y_test_tensor.numpy()
+        
+        if verbose >= 2:
+            _LOGGER.info("Target scaling transformation complete.")
 
         return y_train_arr, y_val_arr, y_test_arr
     
@@ -214,6 +217,9 @@ class _BaseDatasetMaker(ABC):
 
     @property
     def train_dataset(self) -> Dataset:
+        """  
+        Returns the training dataset.
+        """
         if self._train_ds is None: 
             _LOGGER.error("Train Dataset not yet created.")
             raise RuntimeError()
@@ -221,6 +227,9 @@ class _BaseDatasetMaker(ABC):
     
     @property
     def validation_dataset(self) -> Dataset:
+        """  
+        Returns the validation dataset.
+        """
         if self._val_ds is None: 
             _LOGGER.error("Validation Dataset not yet created.")
             raise RuntimeError()
@@ -228,6 +237,9 @@ class _BaseDatasetMaker(ABC):
 
     @property
     def test_dataset(self) -> Dataset:
+        """
+        Returns the test dataset.
+        """
         if self._test_ds is None: 
             _LOGGER.error("Test Dataset not yet created.")
             raise RuntimeError()
@@ -235,30 +247,50 @@ class _BaseDatasetMaker(ABC):
 
     @property
     def feature_names(self) -> list[str]:
+        """
+        Returns a list with the feature names.
+        """
         return self._feature_names
     
     @property
     def target_names(self) -> list[str]:
+        """
+        Returns a list with the target names.
+        """
         return self._target_names
     
     @property
     def number_of_features(self) -> int:
+        """  
+        Returns the number of features.
+        """
         return len(self._feature_names)
     
     @property
     def number_of_targets(self) -> int:
+        """  
+        Returns the number of targets.
+        """
         return len(self._target_names)
 
     @property
     def id(self) -> Optional[str]:
+        """  
+        Returns the dataset ID if set, otherwise None.
+        """
         return self._id
 
     @id.setter
     def id(self, dataset_id: str):
-        if not isinstance(dataset_id, str): raise ValueError("ID must be a string.")
+        if not isinstance(dataset_id, str): 
+            _LOGGER.error("Dataset ID must be a string.")
+            raise ValueError()
         self._id = dataset_id
 
     def dataframes_info(self) -> None:
+        """  
+        Prints the shapes of the dataframes after the split.
+        """
         print("--- DataFrame Shapes After Split ---")
         print(f"  X_train shape: {self._X_train_shape}, y_train shape: {self._y_train_shape}")
         print(f"  X_val shape:   {self._X_val_shape}, y_val shape:   {self._y_val_shape}")
@@ -266,12 +298,26 @@ class _BaseDatasetMaker(ABC):
         print("------------------------------------")
     
     def save_feature_names(self, directory: Union[str, Path], verbose: bool=True) -> None:
+        """  
+        Saves the feature names to a text file.
+        
+        Args:
+            directory (str | Path): Directory to save the feature names.
+            verbose (bool): Whether to print log messages.
+        """
         save_list_strings(list_strings=self._feature_names,
                           directory=directory,
                           filename=DatasetKeys.FEATURE_NAMES,
                           verbose=verbose)
         
     def save_target_names(self, directory: Union[str, Path], verbose: bool=True) -> None:
+        """  
+        Saves the target names to a text file.
+        
+        Args:
+            directory (str | Path): Directory to save the target names.
+            verbose (bool): Whether to print log messages.
+        """
         save_list_strings(list_strings=self._target_names,
                           directory=directory,
                           filename=DatasetKeys.TARGET_NAMES,
@@ -281,6 +327,10 @@ class _BaseDatasetMaker(ABC):
         """
         Saves both feature and target scalers (if they exist) to a single .pth file
         using a dictionary structure.
+        
+        Args:
+            directory (str | Path): Directory to save the scaler.
+            verbose (bool): Whether to print log messages.
         """
         if self.feature_scaler is None and self.target_scaler is None:
             _LOGGER.warning("No scalers (feature or target) were fitted. Nothing to save.")

ml_tools/ML_evaluation/_classification.py

@@ -28,6 +28,8 @@ from ..path_manager import make_fullpath, sanitize_filename
 from .._core import get_logger
 from ..keys._keys import _EvaluationConfig
 
+from ._helpers import check_and_abbreviate_name
+
 
 _LOGGER = get_logger("Classification Metrics")
 
@@ -85,7 +87,8 @@ def classification_metrics(save_dir: Union[str, Path],
         try:
             sorted_items = sorted(class_map.items(), key=lambda item: item[1])
             map_labels = [item[1] for item in sorted_items]
-            map_display_labels = [item[0] for item in sorted_items]
+            # Abbreviate display labels if needed
+            map_display_labels = [check_and_abbreviate_name(item[0]) for item in sorted_items]
         except Exception as e:
             _LOGGER.warning(f"Could not parse 'class_map': {e}")
             map_labels = None
@@ -397,6 +400,10 @@ def classification_metrics(save_dir: Union[str, Path],
             # --- Step 1: Get binned data directly ---
             # calculates reliability diagram data without needing a temporary plot
             prob_true, prob_pred = calibration_curve(y_true_binary, y_score, n_bins=dynamic_bins)
+            
+            # Anchor the plot to (0,0) and (1,1) to ensure the line spans the full diagonal
+            prob_true = np.concatenate(([0.0], prob_true, [1.0]))
+            prob_pred = np.concatenate(([0.0], prob_pred, [1.0]))
 
             # --- Step 2: Plot ---
             ax_cal.plot([0, 1], [0, 1], 'k--', label='Perfectly calibrated')
@@ -467,6 +474,9 @@ def multi_label_classification_metrics(
 
     save_dir_path = make_fullpath(save_dir, make=True, enforce="directory")
     
+    # --- Pre-process target names for abbreviation ---
+    target_names = [check_and_abbreviate_name(name) for name in target_names]
+    
     # --- Parse Config or use defaults ---
     if config is None:
         # Create a default config if one wasn't provided
@@ -502,7 +512,7 @@ def multi_label_classification_metrics(
     # print(overall_report)
     overall_report_path = save_dir_path / "classification_report.txt"
     overall_report_path.write_text(overall_report)
-    
+
     # --- Save Classification Report Heatmap (Multi-label) ---
     try:
          # Generate full report as dict
@@ -566,18 +576,6 @@ def multi_label_classification_metrics(
         pred_i = y_pred[:, i] # Use passed-in y_pred
         prob_i = y_prob[:, i] # Use passed-in y_prob
         sanitized_name = sanitize_filename(name)
-        
-        # if name is too long, just take the first letter of each word. Each word might be separated by space or underscore
-        if len(name) >= _EvaluationConfig.NAME_LIMIT:
-            parts = [w for w in name.replace("_", " ").split() if w]
-            abbr = "".join(p[0].upper() for p in parts)
-            # keep only alpha numeric chars
-            abbr = "".join(ch for ch in abbr if ch.isalnum())
-            if not abbr:
-                # fallback to a sanitized, truncated version of the original name
-                abbr = sanitize_filename(name)[: _EvaluationConfig.NAME_LIMIT]
-            _LOGGER.warning(f"Using abbreviated name '{abbr}' for '{name}' plots.")
-            name = abbr
 
         # --- Save Classification Report for the label (uses y_pred) ---
         report_text = classification_report(true_i, pred_i)
@@ -726,6 +724,11 @@ def multi_label_classification_metrics(
         # Calculate calibration curve for this specific label
         prob_true, prob_pred = calibration_curve(true_i, prob_i, n_bins=dynamic_bins)
         
+        # Anchor the plot to (0,0) and (1,1)
+        prob_true = np.concatenate(([0.0], prob_true, [1.0]))
+        prob_pred = np.concatenate(([0.0], prob_pred, [1.0]))
+        
+        # Plot the calibration curve
         ax_cal.plot([0, 1], [0, 1], 'k--', label='Perfectly calibrated')
         ax_cal.plot(prob_pred, 
                     prob_true, 

ml_tools/ML_evaluation/_helpers.py

@@ -0,0 +1,41 @@
+from ..keys._keys import _EvaluationConfig
+from ..path_manager import sanitize_filename
+from .._core import get_logger
+
+
+_LOGGER = get_logger("Metrics Helper")
+
+
+def check_and_abbreviate_name(name: str) -> str:
+    """
+    Checks if a name exceeds the NAME_LIMIT. If it does, creates an abbreviation 
+    (initials of words) or truncates it if the abbreviation is empty.
+    
+    Args:
+        name (str): The original label or target name.
+        
+    Returns:
+        str: The potentially abbreviated name.
+    """
+    limit = _EvaluationConfig.NAME_LIMIT
+    
+    # Strip whitespace
+    name = name.strip()
+    
+    if len(name) <= limit:
+        return name
+        
+    # Attempt abbreviation: First letter of each word (split by space or underscore)
+    parts = [w for w in name.replace("_", " ").split() if w]
+    abbr = "".join(p[0].upper() for p in parts)
+    
+    # Keep only alphanumeric characters
+    abbr = "".join(ch for ch in abbr if ch.isalnum())
+    
+    # Fallback if abbreviation failed or is empty
+    if not abbr:
+        sanitized = sanitize_filename(name)
+        abbr = sanitized[:limit]
+        
+    _LOGGER.warning(f"Label '{name}' is too long. Abbreviating to '{abbr}'.")
+    return abbr

ml_tools/ML_evaluation/_regression.py

@@ -19,6 +19,8 @@ from ..path_manager import make_fullpath, sanitize_filename
 from .._core import get_logger
 from ..keys._keys import _EvaluationConfig
 
+from ._helpers import check_and_abbreviate_name
+
 
 _LOGGER = get_logger("Regression Metrics")
 
@@ -180,6 +182,9 @@ def multi_target_regression_metrics(
     if y_true.shape[1] != len(target_names):
         _LOGGER.error("Number of target names must match the number of columns in y_true.")
         raise ValueError()
+    
+    # --- Pre-process target names for abbreviation ---
+    target_names = [check_and_abbreviate_name(name) for name in target_names]
 
     save_dir_path = make_fullpath(save_dir, make=True, enforce="directory")
     metrics_summary = []

ml_tools/keys/_keys.py

@@ -306,7 +306,7 @@ class _EvaluationConfig:
     LOSS_PLOT_LEGEND_SIZE = 24
     # CM settings
     CM_SIZE = (9, 8)    # used for multi label binary classification confusion matrix 
-    NAME_LIMIT = 20  # max number of characters for feature/label names in plots
+    NAME_LIMIT = 15  # max number of characters for feature/label names in plots
 
 class _OneHotOtherPlaceholder:
     """Used internally by GUI_tools."""