dragon-ml-toolbox 20.7.1__tar.gz → 20.9.0__tar.gz

{dragon_ml_toolbox-20.7.1/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-20.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.7.1
+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
@@ -174,6 +174,7 @@ ML_vision_transformers
 optimization_tools
 path_manager
 plot_fonts
+resampling
 schema
 serde
 SQL
@@ -206,6 +207,7 @@ optimization_tools
 path_manager
 plot_fonts
 PSO_optimization
+resampling
 schema
 serde
 SQL

{dragon_ml_toolbox-20.7.1 → dragon_ml_toolbox-20.9.0}/README.md

@@ -81,6 +81,7 @@ ML_vision_transformers
 optimization_tools
 path_manager
 plot_fonts
+resampling
 schema
 serde
 SQL
@@ -113,6 +114,7 @@ optimization_tools
 path_manager
 plot_fonts
 PSO_optimization
+resampling
 schema
 serde
 SQL

{dragon_ml_toolbox-20.7.1 → dragon_ml_toolbox-20.9.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.7.1
+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
@@ -174,6 +174,7 @@ ML_vision_transformers
 optimization_tools
 path_manager
 plot_fonts
+resampling
 schema
 serde
 SQL
@@ -206,6 +207,7 @@ optimization_tools
 path_manager
 plot_fonts
 PSO_optimization
+resampling
 schema
 serde
 SQL

{dragon_ml_toolbox-20.7.1 → dragon_ml_toolbox-20.9.0}/dragon_ml_toolbox.egg-info/SOURCES.txt

@@ -48,6 +48,7 @@ ml_tools/ML_datasetmaster/_vision_datasetmaster.py
 ml_tools/ML_evaluation/__init__.py
 ml_tools/ML_evaluation/_classification.py
 ml_tools/ML_evaluation/_feature_importance.py
+ml_tools/ML_evaluation/_helpers.py
 ml_tools/ML_evaluation/_loss.py
 ml_tools/ML_evaluation/_regression.py
 ml_tools/ML_evaluation/_sequence.py
@@ -136,6 +137,10 @@ ml_tools/path_manager/_dragonmanager.py
 ml_tools/path_manager/_path_tools.py
 ml_tools/plot_fonts/__init__.py
 ml_tools/plot_fonts/_plot_fonts.py
+ml_tools/resampling/__init__.py
+ml_tools/resampling/_base_resampler.py
+ml_tools/resampling/_multi_resampling.py
+ml_tools/resampling/_single_resampling.py
 ml_tools/schema/__init__.py
 ml_tools/schema/_feature_schema.py
 ml_tools/schema/_gui_schema.py

{dragon_ml_toolbox-20.7.1 → dragon_ml_toolbox-20.9.0}/ml_tools/ML_configuration/_metrics.py

@@ -98,10 +98,11 @@ class _BaseMultiLabelFormat:
                  cmap: str = "BuGn",
                  ROC_PR_line: str='darkorange',
                  calibration_bins: Union[int, Literal['auto']]='auto', 
-                 font_size: int = 25,
-                 xtick_size: int=20,
-                 ytick_size: int=20,
-                 legend_size: int=23) -> None:
+                 font_size: int = 26,
+                 xtick_size: int=22,
+                 ytick_size: int=22,
+                 legend_size: int=26,
+                 cm_font_size: int=26) -> None:
         """
         Initializes the formatting configuration for multi-label classification metrics.
 
@@ -127,6 +128,8 @@ class _BaseMultiLabelFormat:
             
             legend_size (int): Font size for plot legends.
             
+            cm_font_size (int): Font size for the confusion matrix.
+            
         <br>
         
         ### [Matplotlib Colormaps](https://matplotlib.org/stable/users/explain/colors/colormaps.html)
@@ -142,6 +145,7 @@ class _BaseMultiLabelFormat:
         self.xtick_size = xtick_size
         self.ytick_size = ytick_size
         self.legend_size = legend_size
+        self.cm_font_size = cm_font_size
         
     def __repr__(self) -> str:
         parts = [
@@ -151,7 +155,8 @@ class _BaseMultiLabelFormat:
             f"font_size={self.font_size}",
             f"xtick_size={self.xtick_size}",
             f"ytick_size={self.ytick_size}",
-            f"legend_size={self.legend_size}"
+            f"legend_size={self.legend_size}",
+            f"cm_font_size={self.cm_font_size}"
         ]
         return f"{self.__class__.__name__}({', '.join(parts)})"
 
@@ -520,10 +525,11 @@ class FormatMultiLabelBinaryClassificationMetrics(_BaseMultiLabelFormat):
                  cmap: str = "BuGn",
                  ROC_PR_line: str='darkorange',
                  calibration_bins: Union[int, Literal['auto']]='auto', 
-                 font_size: int = 25,
-                 xtick_size: int=20,
-                 ytick_size: int=20,
-                 legend_size: int=23
+                 font_size: int = 26,
+                 xtick_size: int=22,
+                 ytick_size: int=22,
+                 legend_size: int=26,
+                 cm_font_size: int=26
                  ) -> None:
         super().__init__(cmap=cmap,
                          ROC_PR_line=ROC_PR_line, 
@@ -531,7 +537,8 @@ class FormatMultiLabelBinaryClassificationMetrics(_BaseMultiLabelFormat):
                          font_size=font_size,
                          xtick_size=xtick_size,
                          ytick_size=ytick_size,
-                         legend_size=legend_size)
+                         legend_size=legend_size,
+                         cm_font_size=cm_font_size)
 
 
 # Segmentation

{dragon_ml_toolbox-20.7.1 → dragon_ml_toolbox-20.9.0}/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.")

{dragon_ml_toolbox-20.7.1 → dragon_ml_toolbox-20.9.0}/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
@@ -481,6 +491,10 @@ def multi_label_classification_metrics(
     ytick_size = format_config.ytick_size
     legend_size = format_config.legend_size
     base_font_size = format_config.font_size
+    
+    # config font size for heatmap
+    cm_font_size = format_config.cm_font_size
+    cm_tick_size = cm_font_size - 4
 
     # --- Calculate and Save Overall Metrics (using y_pred) ---
     h_loss = hamming_loss(y_true, y_pred)
@@ -488,7 +502,7 @@ def multi_label_classification_metrics(
     j_score_macro = jaccard_score(y_true, y_pred, average='macro')
 
     overall_report = (
-        f"Overall Multi-Label Metrics:\n" # No threshold to report here
+        f"Overall Multi-Label Metrics:\n"
         f"--------------------------------------------------\n"
         f"Hamming Loss: {h_loss:.4f}\n"
         f"Jaccard Score (micro): {j_score_micro:.4f}\n"
@@ -499,9 +513,65 @@ def multi_label_classification_metrics(
     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
+        full_report_dict = classification_report(y_true, y_pred, target_names=target_names, output_dict=True)
+        report_df = pd.DataFrame(full_report_dict)
+        
+        # Cleanup
+        # Remove 'accuracy' column if it exists 
+        report_df = report_df.drop(columns=['accuracy'], errors='ignore')
+        
+        # Remove 'support' row explicitly
+        if 'support' in report_df.index:
+            report_df = report_df.drop(index='support')
+            
+        # Transpose: Rows = Classes/Averages, Cols = Metrics
+        plot_df = report_df.T
+        
+        # Dynamic Height
+        fig_height = max(5.0, len(plot_df.index) * 0.5 + 4.0)
+        fig_width = 8.0 
+
+        fig_heat, ax_heat = plt.subplots(figsize=(fig_width, fig_height), dpi=_EvaluationConfig.DPI)
+
+        # Plot
+        sns.heatmap(plot_df, 
+                    annot=True, 
+                    cmap=format_config.cmap, 
+                    fmt='.2f',
+                    vmin=0.0,
+                    vmax=1.0,
+                    cbar_kws={'shrink': 0.9})
+        
+        ax_heat.set_title("Classification Report Heatmap", pad=_EvaluationConfig.LABEL_PADDING, fontsize=cm_font_size)
+        
+        # manually increase the font size of the elements
+        for text in ax_heat.texts:
+            text.set_fontsize(cm_tick_size)
+
+        cbar = ax_heat.collections[0].colorbar
+        cbar.ax.tick_params(labelsize=cm_tick_size - 4) # type: ignore
+
+        ax_heat.tick_params(axis='x', labelsize=cm_tick_size, pad=_EvaluationConfig.LABEL_PADDING)
+        ax_heat.tick_params(axis='y', labelsize=cm_tick_size, pad=_EvaluationConfig.LABEL_PADDING, rotation=0)
+
+        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(fig_heat)
+
+    except Exception as e:
+        _LOGGER.error(f"Could not generate multi-label classification report heatmap: {e}")
+
     # --- Per-Label Metrics and Plots ---
     for i, name in enumerate(target_names):
-        print(f"  -> Evaluating label: '{name}'")
+        # strip whitespace from name
+        name = name.strip()
+        
+        # print(f"  -> Evaluating label: '{name}'")
         true_i = y_true[:, i]
         pred_i = y_pred[:, i] # Use passed-in y_pred
         prob_i = y_prob[:, i] # Use passed-in y_prob
@@ -537,7 +607,7 @@ def multi_label_classification_metrics(
         ax_cm.tick_params(axis='y', labelsize=ytick_size)
         
         # Set titles and labels with padding
-        ax_cm.set_title(f"Confusion Matrix for '{name}'", pad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size + 2)
+        ax_cm.set_title(f"Confusion Matrix - {name}", pad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size + 2)
         ax_cm.set_xlabel(ax_cm.get_xlabel(), labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size)
         ax_cm.set_ylabel(ax_cm.get_ylabel(), labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size)
         
@@ -594,7 +664,7 @@ def multi_label_classification_metrics(
         ax_roc.plot(fpr, tpr, label=f'AUC = {auc:.2f}', color=format_config.ROC_PR_line) # Use config color
         ax_roc.plot([0, 1], [0, 1], 'k--')
         
-        ax_roc.set_title(f'ROC Curve for "{name}"', pad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size + 2)
+        ax_roc.set_title(f'ROC Curve - {name}', pad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size + 2)
         ax_roc.set_xlabel('False Positive Rate', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size)
         ax_roc.set_ylabel('True Positive Rate', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size)
         
@@ -616,7 +686,7 @@ def multi_label_classification_metrics(
         ap_score = average_precision_score(true_i, prob_i)
         fig_pr, ax_pr = plt.subplots(figsize=CLASSIFICATION_PLOT_SIZE, dpi=DPI_value)
         ax_pr.plot(recall, precision, label=f'AP = {ap_score:.2f}', color=format_config.ROC_PR_line) # Use config color
-        ax_pr.set_title(f'Precision-Recall Curve for "{name}"', pad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size + 2)
+        ax_pr.set_title(f'PR Curve - {name}', pad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size + 2)
         ax_pr.set_xlabel('Recall', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size)
         ax_pr.set_ylabel('Precision', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size)
         
@@ -654,15 +724,20 @@ 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, 
                     marker='o',
                     linewidth=2, 
-                    label=f"Calibration for '{name}'", 
+                    label=f"Model Calibration", 
                     color=format_config.ROC_PR_line)
         
-        ax_cal.set_title(f'Reliability Curve for "{name}"', pad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size + 2)
+        ax_cal.set_title(f'Calibration - {name}', pad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size + 2)
         ax_cal.set_xlabel('Mean Predicted Probability', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size)
         ax_cal.set_ylabel('Fraction of Positives', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=base_font_size)
         

dragon_ml_toolbox-20.9.0/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

{dragon_ml_toolbox-20.7.1 → dragon_ml_toolbox-20.9.0}/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 = []

{dragon_ml_toolbox-20.7.1 → dragon_ml_toolbox-20.9.0}/ml_tools/data_exploration/__init__.py

@@ -2,6 +2,7 @@ from ._analysis import (
     summarize_dataframe,
     show_null_columns,
     match_and_filter_columns_by_regex,
+    check_class_balance,
 )
 
 from ._cleaning import (
@@ -28,6 +29,7 @@ from ._features import (
     split_continuous_binary,
     split_continuous_categorical_targets,
     encode_categorical_features,
+    encode_classification_target,
     reconstruct_one_hot,
     reconstruct_binary,
     reconstruct_multibinary,
@@ -44,7 +46,6 @@ from .._core import _imprimir_disponibles
 
 __all__ = [
     "summarize_dataframe",
-    "show_null_columns",
     "drop_constant_columns",
     "drop_rows_with_missing_data",
     "drop_columns_with_missing_data",
@@ -61,10 +62,13 @@ __all__ = [
     "plot_categorical_vs_target",
     "plot_correlation_heatmap", 
     "encode_categorical_features",
+    "encode_classification_target",
     "finalize_feature_schema",
     "apply_feature_schema",
     "reconstruct_from_schema",
     "match_and_filter_columns_by_regex",
+    "show_null_columns",
+    "check_class_balance",
     "standardize_percentages",
     "reconstruct_one_hot",
     "reconstruct_binary",