dragon-ml-toolbox 3.5.1__py3-none-any.whl → 3.7.0__py3-none-any.whl

{dragon_ml_toolbox-3.5.1.dist-info → dragon_ml_toolbox-3.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 3.5.1
+Version: 3.7.0
 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-3.7.0.dist-info/RECORD

@@ -0,0 +1,25 @@
+dragon_ml_toolbox-3.7.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-3.7.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=6cfpIeQ6D4Mcs10nkogQrkVyq1T7i2qXjjNHFoUMOyE,1892
+ml_tools/ETL_engineering.py,sha256=yeZsW_7zRvEcuMZbM4E2GV1dxwBoWIeJAcFFk2AK0fY,39502
+ml_tools/GUI_tools.py,sha256=3kRxok-QCN5S0q1i7yK137Bsr6c2N4M4nIvgPVAuZU0,20371
+ml_tools/MICE_imputation.py,sha256=rYqvwQDVtoAJJ0agXWoGzoZEHedWiA6QzcEKEIkiZ08,11388
+ml_tools/ML_callbacks.py,sha256=OT2zwORLcn49megBEgXsSUxDHoW0Ft0_v7hLEVF3jHM,13063
+ml_tools/ML_evaluation.py,sha256=oiDV6HItQloUUKCUpltV-2pogubWLBieGpc-VUwosAQ,10106
+ml_tools/ML_trainer.py,sha256=Pw4tLtlexoZJs_3o5I6ElQMTLjijzydXXQE834949Dw,14470
+ml_tools/ML_tutorial.py,sha256=-9tJO9ISPxEjRINVaF_Bu7tiiJ2W3zznQ4gNlZeP1HQ,12238
+ml_tools/PSO_optimization.py,sha256=c23Fd-ttqoO8IBPK5-TXZLqPi9UPHUC4HNoF02Q8wLo,24774
+ml_tools/RNN_forecast.py,sha256=IZLcPs3by0Chei7ill_Grjxs7BBUnzau0Oavi3dWiyE,1886
+ml_tools/VIF_factor.py,sha256=BeP4ig3l7b1Igwgte9z8rEwHdSZvVT7W_9mcBHGoNJw,10299
+ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ml_tools/_particle_swarm_optimization.py,sha256=b_eNNkA89Y40hj76KauivT8KLScH1B9wF2IXptOqkOw,22220
+ml_tools/_pytorch_models.py,sha256=bpWZsrSwCvHJQkR6UfoPpElsMv9AvmiNErNHC8NYB_I,10132
+ml_tools/data_exploration.py,sha256=M7bn2q5XN9zJZJGAmMMFSFFZh8LGzC2arFelrXw3N6Q,25241
+ml_tools/datasetmaster.py,sha256=S3PKHNQZ9cyAOck8xQltVLZhaD1gFLfgHFL-aRjz4JU,30077
+ml_tools/ensemble_learning.py,sha256=CDSIygnHaNe92aJ46Fofevd7q6lowTnE98yWuIV3Y6w,37462
+ml_tools/handle_excel.py,sha256=lwds7rDLlGSCWiWGI7xNg-Z7kxAepogp0lstSFa0590,12949
+ml_tools/logger.py,sha256=UkbiU9ihBhw9VKyn3rZzisdClWV94EBV6B09_D0iUU0,6026
+ml_tools/utilities.py,sha256=0w0vka0Aj9IYOHJ6crWIb6gwpQIJnPyj3v2_dnVxHrs,23138
+dragon_ml_toolbox-3.7.0.dist-info/METADATA,sha256=kvgFjd_BRwob7xycC5rbROCkq4C6FVq3J5-VdCXEPrI,3273
+dragon_ml_toolbox-3.7.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-3.7.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-3.7.0.dist-info/RECORD,,

ml_tools/ETL_engineering.py

@@ -294,7 +294,7 @@ class DataProcessor:
                 raise TypeError(f"Invalid 'transform' action for '{input_col_name}': {transform_action}")
 
         if not processed_columns:
-            _LOGGER.warning("The transformation resulted in an empty DataFrame.")
+            _LOGGER.warning("⚠️ The transformation resulted in an empty DataFrame.")
             return pl.DataFrame()
             
         return pl.DataFrame(processed_columns)
@@ -588,7 +588,7 @@ class NumberExtractor:
             if not isinstance(round_digits, int):
                 raise TypeError("round_digits must be an integer.")
             if dtype == "int":
-                _LOGGER.warning(f"'round_digits' is specified but dtype is 'int'. Rounding will be ignored.")
+                _LOGGER.warning(f"⚠️ 'round_digits' is specified but dtype is 'int'. Rounding will be ignored.")
 
         self.regex_pattern = regex_pattern
         self.dtype = dtype

ml_tools/GUI_tools.py

@@ -148,7 +148,7 @@ class ConfigManager:
         """
         path = Path(file_path)
         if path.exists() and not force_overwrite:
-            _LOGGER.warning(f"Configuration file already exists at {path}. Aborting.")
+            _LOGGER.warning(f"⚠️ Configuration file already exists at {path}. Aborting.")
             return
 
         config = configparser.ConfigParser()
@@ -206,7 +206,7 @@ class ConfigManager:
 
         with open(path, 'w') as configfile:
             config.write(configfile)
-        _LOGGER.info(f"Successfully generated config template at: '{path}'")
+        _LOGGER.info(f"📝 Successfully generated config template at: '{path}'")
 
 
 # --- GUI Factory ---
@@ -482,13 +482,12 @@ def update_target_fields(window: sg.Window, results_dict: Dict[str, Any]):
 
     Args:
         window (sg.Window): The application's window object.
-        results_dict (dict): A dictionary where keys are target names (without the
-                             'TARGET_' prefix) and values are the predicted results.
+        results_dict (dict): A dictionary where keys are target key names (including 'TARGET_' prefix if necessary) and values are the predicted results.
     """
     for target_name, result in results_dict.items():
         # Format numbers to 2 decimal places, leave other types as-is
         display_value = f"{result:.2f}" if isinstance(result, (int, float)) else result
-        window[f'TARGET_{target_name}'].update(display_value)
+        window[target_name].update(display_value)
 
 
 def info():

ml_tools/MICE_imputation.py

@@ -128,7 +128,7 @@ def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_name
             plt.savefig(save_path, bbox_inches='tight', format="svg")
             plt.close()
             
-        _LOGGER.info(f"{dataset_file_dir} completed.")
+        _LOGGER.info(f"✅ {dataset_file_dir} process completed.")
 
 
 # Imputed distributions
@@ -213,7 +213,7 @@ def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_di
             fig = kernel.plot_imputed_distributions(variables=[feature])
             _process_figure(fig, feature)
 
-    _LOGGER.info(f"{local_dir_name} completed.")
+    _LOGGER.info(f"✅ {local_dir_name} completed.")
 
 
 def run_mice_pipeline(df_path_or_dir: Union[str,Path], target_columns: list[str], 

ml_tools/ML_callbacks.py

@@ -178,7 +178,6 @@ class EarlyStopping(Callback):
                 self.stopped_epoch = epoch
                 self.trainer.stop_training = True # type: ignore
                 if self.verbose > 0:
-                    print("")
                     _LOGGER.info(f"Epoch {epoch+1}: early stopping after {self.wait} epochs with no improvement.")
 
 
@@ -256,7 +255,6 @@ class ModelCheckpoint(Callback):
             new_filepath = self.save_dir / filename
             
             if self.verbose > 0:
-                print("")
                 _LOGGER.info(f"Epoch {epoch}: {self.monitor} improved from {old_best_str} to {current:.4f}, saving model to {new_filepath}")
             
             # Save the new best model
@@ -276,7 +274,6 @@ class ModelCheckpoint(Callback):
         filepath = self.save_dir / filename
         
         if self.verbose > 0:
-            print("")
             _LOGGER.info(f'Epoch {epoch}: saving model to {filepath}')
         torch.save(self.trainer.model.state_dict(), filepath) # type: ignore
 
@@ -325,7 +322,6 @@ class LRScheduler(Callback):
             if metric_val is not None:
                 self.scheduler.step(metric_val)
             else:
-                print("")
                 _LOGGER.warning(f"LRScheduler could not find metric '{self.monitor}' in logs.")
         
         # For all other schedulers
@@ -335,7 +331,6 @@ class LRScheduler(Callback):
         # Log the change if the LR was updated
         current_lr = self.trainer.optimizer.param_groups[0]['lr'] # type: ignore
         if current_lr != self.previous_lr:
-            print("")
             _LOGGER.info(f"Epoch {epoch}: Learning rate changed to {current_lr:.6f}")
             self.previous_lr = current_lr
             

ml_tools/ML_evaluation.py

@@ -65,7 +65,7 @@ def plot_losses(history: dict, save_dir: Optional[Union[str, Path]] = None):
         save_dir_path = make_fullpath(save_dir, make=True)
         save_path = save_dir_path / "loss_plot.svg"
         plt.savefig(save_path)
-        _LOGGER.info(f"Loss plot saved as '{save_path.name}'")
+        _LOGGER.info(f"📉 Loss plot saved as '{save_path.name}'")
     else:
         plt.show()
     plt.close(fig)
@@ -92,7 +92,7 @@ def classification_metrics(y_true: np.ndarray, y_pred: np.ndarray, y_prob: Optio
         # Save text report
         report_path = save_dir_path / "classification_report.txt"
         report_path.write_text(report, encoding="utf-8")
-        _LOGGER.info(f"Classification report saved as '{report_path.name}'")
+        _LOGGER.info(f"📝 Classification report saved as '{report_path.name}'")
 
         # Save Confusion Matrix
         fig_cm, ax_cm = plt.subplots(figsize=(6, 6), dpi=100)
@@ -100,7 +100,7 @@ def classification_metrics(y_true: np.ndarray, y_pred: np.ndarray, y_prob: Optio
         ax_cm.set_title("Confusion Matrix")
         cm_path = save_dir_path / "confusion_matrix.svg"
         plt.savefig(cm_path)
-        _LOGGER.info(f"Confusion matrix saved as '{cm_path.name}'")
+        _LOGGER.info(f"❇️ Confusion matrix saved as '{cm_path.name}'")
         plt.close(fig_cm)
 
         # Save ROC Curve
@@ -117,7 +117,7 @@ def classification_metrics(y_true: np.ndarray, y_pred: np.ndarray, y_prob: Optio
             ax_roc.grid(True)
             roc_path = save_dir_path / "roc_curve.svg"
             plt.savefig(roc_path)
-            _LOGGER.info(f"ROC curve saved as '{roc_path.name}'")
+            _LOGGER.info(f"📈 ROC curve saved as '{roc_path.name}'")
             plt.close(fig_roc)
     else:
         # Show plots if not saving
@@ -162,7 +162,7 @@ def regression_metrics(y_true: np.ndarray, y_pred: np.ndarray, save_dir: Optiona
         # Save text report
         report_path = save_dir_path / "regression_report.txt"
         report_path.write_text(report_string)
-        _LOGGER.info(f"Regression report saved as '{report_path.name}'")
+        _LOGGER.info(f"📝 Regression report saved as '{report_path.name}'")
 
         # Save residual plot
         residuals = y_true - y_pred
@@ -176,7 +176,7 @@ def regression_metrics(y_true: np.ndarray, y_pred: np.ndarray, save_dir: Optiona
         plt.tight_layout()
         res_path = save_dir_path / "residual_plot.svg"
         plt.savefig(res_path)
-        _LOGGER.info(f"Residual plot saved as '{res_path.name}'")
+        _LOGGER.info(f"📈 Residual plot saved as '{res_path.name}'")
         plt.close(fig_res)
 
         # Save true vs predicted plot
@@ -190,7 +190,7 @@ def regression_metrics(y_true: np.ndarray, y_pred: np.ndarray, save_dir: Optiona
         plt.tight_layout()
         tvp_path = save_dir_path / "true_vs_predicted_plot.svg"
         plt.savefig(tvp_path)
-        _LOGGER.info(f"True vs. Predicted plot saved as '{tvp_path.name}'")
+        _LOGGER.info(f"📉 True vs. Predicted plot saved as '{tvp_path.name}'")
         plt.close(fig_tvp)
 
 
@@ -227,7 +227,7 @@ def shap_summary_plot(model, background_data: torch.Tensor, instances_to_explain
         plt.title("SHAP Feature Importance")
         plt.tight_layout()
         plt.savefig(bar_path)
-        _LOGGER.info(f"SHAP bar plot saved as '{bar_path.name}'")
+        _LOGGER.info(f"📊 SHAP bar plot saved as '{bar_path.name}'")
         plt.close()
 
         # Save Dot Plot
@@ -236,7 +236,7 @@ def shap_summary_plot(model, background_data: torch.Tensor, instances_to_explain
         plt.title("SHAP Feature Importance")
         plt.tight_layout()
         plt.savefig(dot_path)
-        _LOGGER.info(f"SHAP dot plot saved as '{dot_path.name}'")
+        _LOGGER.info(f"📊 SHAP dot plot saved as '{dot_path.name}'")
         plt.close()
 
         # Save Summary Data to CSV
@@ -249,7 +249,7 @@ def shap_summary_plot(model, background_data: torch.Tensor, instances_to_explain
             '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}'")
+        _LOGGER.info(f"📝 SHAP summary data saved as '{summary_path.name}'")
     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")

ml_tools/ML_trainer.py

@@ -72,10 +72,10 @@ class MyTrainer:
         """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 = "cpu"
         elif device_lower == "mps" and not torch.backends.mps.is_available():
-            _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 = "cpu"
         return torch.device(device)
 

ml_tools/PSO_optimization.py

@@ -22,7 +22,6 @@ import torch
 from tqdm import trange
 import matplotlib.pyplot as plt
 import seaborn as sns
-from collections import defaultdict
 from .logger import _LOGGER
 
 
@@ -307,7 +306,7 @@ def run_pso(lower_boundaries: list[float],
     else:
         device = torch.device("cpu")
     
-    _LOGGER.info(f"Using device: '{device}'")
+    _LOGGER.info(f"👾 Using device: '{device}'")
     
     # set local deep copies to prevent in place list modification
     local_lower_boundaries = deepcopy(lower_boundaries)
@@ -511,13 +510,13 @@ def _pso(func: ObjectiveFunction,
         return best_position, best_score
 
 
-def plot_optimal_feature_distributions(results_dir: Union[str, Path], save_dir: Union[str, Path], color_by_target: bool = True):
+def plot_optimal_feature_distributions(results_dir: Union[str, Path], save_dir: Union[str, Path]):
     """
     Analyzes optimization results and plots the distribution of optimal values for each feature.
 
-    This function can operate in two modes based on the `color_by_target` parameter:
-    1.  Aggregates all values for a feature into a single group and plots one overall distribution (histogram + KDE).
-    2.  Color-coded: Plots a separate, color-coded Kernel Density Estimate (KDE) for each source target, allowing for direct comparison on a single chart.
+    For features with more than two unique values, this function generates a color-coded 
+    Kernel Density Estimate (KDE) plot. For binary or constant features, it generates a bar plot
+    showing relative frequency.
 
     Parameters
     ----------
@@ -525,76 +524,69 @@ def plot_optimal_feature_distributions(results_dir: Union[str, Path], save_dir:
         The path to the directory containing the optimization result CSV files.
     save_dir : str or Path
         The directory where the output plots will be saved.
-    color_by_target : bool, optional
-        If True, generates comparative plots with distributions colored by their source target.
     """
-    mode = "Comparative (color-coded)" if color_by_target else "Aggregate"
-    _LOGGER.info(f"Starting analysis in '{mode}' mode from results in: '{results_dir}'")
-    
-    # Check results_dir
+    # Check results_dir and create output path
     results_path = make_fullpath(results_dir)
-    # make output path
     output_path = make_fullpath(save_dir, make=True)
     
     all_csvs = list_csv_paths(results_path)
-
     if not all_csvs:
-        _LOGGER.warning("No data found. No plots will be generated.")
+        _LOGGER.warning("⚠️ No data found. No plots will be generated.")
         return
 
-    # --- MODE 1: Color-coded plots by target ---
-    if color_by_target:
-        data_to_plot = []
-        for df, df_name in yield_dataframes_from_dir(results_path):
-            # Assumes last col is target, rest are features
-            melted_df = df.iloc[:, :-1].melt(var_name='feature', value_name='value')
-            # Sanitize target name for cleaner legend labels
-            melted_df['target'] = df_name.replace("Optimization_", "")
-            data_to_plot.append(melted_df)
-        
-        long_df = pd.concat(data_to_plot, ignore_index=True)
-        features = long_df['feature'].unique()
-        _LOGGER.info(f"Found data for {len(features)} features across {len(long_df['target'].unique())} targets. Generating plots...")
-
-        for feature_name in features:
-            plt.figure(figsize=(12, 7))
-            feature_df = long_df[long_df['feature'] == feature_name]
+    # --- Data Loading and Preparation ---
+    _LOGGER.info(f"📁 Starting analysis from results in: '{results_dir}'")
+    data_to_plot = []
+    for df, df_name in yield_dataframes_from_dir(results_path):
+        melted_df = df.iloc[:, :-1].melt(var_name='feature', value_name='value')
+        melted_df['target'] = df_name.replace("Optimization_", "")
+        data_to_plot.append(melted_df)
+    
+    long_df = pd.concat(data_to_plot, ignore_index=True)
+    features = long_df['feature'].unique()
+    _LOGGER.info(f"📂 Found data for {len(features)} features across {len(long_df['target'].unique())} targets. Generating plots...")
+
+    # --- Plotting Loop ---
+    for feature_name in features:
+        plt.figure(figsize=(12, 7))
+        feature_df = long_df[long_df['feature'] == feature_name]
+
+        # Check if the feature is binary or constant
+        if feature_df['value'].nunique() <= 2:
+            # PLOT 1: For discrete values, calculate percentages and use a true bar plot.
+            # This ensures the X-axis is clean (e.g., just 0 and 1).
+            norm_df = (feature_df.groupby('target')['value']
+                       .value_counts(normalize=True)
+                       .mul(100)
+                       .rename('percent')
+                       .reset_index())
             
-            sns.kdeplot(data=feature_df, x='value', hue='target', fill=True, alpha=0.1)
+            ax = sns.barplot(data=norm_df, x='value', y='percent', hue='target')
             
-            plt.title(f"Comparative Distribution for '{feature_name}'", fontsize=16)
-            plt.xlabel("Feature Value", fontsize=12)
-            plt.ylabel("Density", fontsize=12)
-            plt.grid(axis='y', alpha=0.5, linestyle='--')
-            plt.legend(title='Target')
-
-            sanitized_feature_name = sanitize_filename(feature_name)
-            plot_filename = output_path / f"Comparative_{sanitized_feature_name}.svg"
-            plt.savefig(plot_filename, bbox_inches='tight')
-            plt.close()
-
-    # --- MODE 2: Aggregate plot ---
-    else:
-        feature_distributions = defaultdict(list)
-        for df, _ in yield_dataframes_from_dir(results_path):
-            feature_columns = df.iloc[:, :-1]
-            for feature_name in feature_columns:
-                feature_distributions[feature_name].extend(df[feature_name].tolist())
+            plt.title(f"Optimal Value Distribution for '{feature_name}'", fontsize=16)
+            plt.ylabel("Frequency (%)", fontsize=12)
+            ax.set_ylim(0, 100) # Set Y-axis from 0 to 100
+
+        else:
+            # PLOT 2: KDE plot for continuous values.
+            ax = sns.kdeplot(data=feature_df, x='value', hue='target',
+                             fill=True, alpha=0.1, warn_singular=False)
+
+            plt.title(f"Optimal Value Distribution for '{feature_name}'", fontsize=16)
+            plt.ylabel("Density", fontsize=12) # Y-axis is "Density" for KDE plots
+
+        # --- Common settings for both plot types ---
+        plt.xlabel("Feature Value", fontsize=12)
+        plt.grid(axis='y', alpha=0.5, linestyle='--')
         
-        _LOGGER.info(f"Found data for {len(feature_distributions)} features. Generating plots...")
-        for feature_name, values in feature_distributions.items():
-            plt.figure(figsize=(12, 7))
-            sns.histplot(x=values, kde=True, bins='auto', stat="density")
-            
-            plt.title(f"Aggregate Distribution for '{feature_name}'", fontsize=16)
-            plt.xlabel("Feature Value", fontsize=12)
-            plt.ylabel("Density", fontsize=12)
-            plt.grid(axis='y', alpha=0.5, linestyle='--')
-
-            sanitized_feature_name = sanitize_filename(feature_name)
-            plot_filename = output_path / f"Aggregate_{sanitized_feature_name}.svg"
-            plt.savefig(plot_filename, bbox_inches='tight')
-            plt.close()
+        legend = ax.get_legend()
+        if legend:
+            legend.set_title('Target')
+
+        sanitized_feature_name = sanitize_filename(feature_name)
+        plot_filename = output_path / f"Distribution_{sanitized_feature_name}.svg"
+        plt.savefig(plot_filename, bbox_inches='tight')
+        plt.close()
 
     _LOGGER.info(f"✅ All plots saved successfully to: '{output_path}'")
 

ml_tools/VIF_factor.py

@@ -168,12 +168,12 @@ def drop_vif_based(df: pd.DataFrame, vif_df: pd.DataFrame, threshold: float = 10
     
     # Identify features to drop
     to_drop = vif_df[vif_df["VIF"] > threshold]["feature"].tolist()
-    _LOGGER.info(f"\tDropping {len(to_drop)} column(s) with VIF > {threshold}: {to_drop}")
+    _LOGGER.info(f"🗑️ Dropping {len(to_drop)} column(s) with VIF > {threshold}: {to_drop}")
     
     result_df = df.drop(columns=to_drop)
     
     if result_df.empty:
-        _LOGGER.warning(f"\t⚠️ All columns were dropped.")
+        _LOGGER.warning(f"⚠️ All columns were dropped.")
 
     return result_df, to_drop
 

ml_tools/data_exploration.py

@@ -15,7 +15,7 @@ import re
 # Keep track of all available tools, show using `info()`
 __all__ = [
     "summarize_dataframe",
-    "drop_zero_only_columns",
+    "drop_constant_columns",
     "drop_rows_with_missing_data",
     "split_features_targets", 
     "show_null_columns",
@@ -62,44 +62,50 @@ def summarize_dataframe(df: pd.DataFrame, round_digits: int = 2):
     return summary
 
 
-def drop_zero_only_columns(df: pd.DataFrame, verbose: bool=True) -> pd.DataFrame:
+def drop_constant_columns(df: pd.DataFrame, verbose: bool = True) -> pd.DataFrame:
     """
-    Removes columns from a pandas DataFrame that contain only zeros and null/NaN values.
+    Removes columns from a pandas DataFrame that contain only a single unique 
+    value or are entirely null/NaN.
 
-    This utility is useful for cleaning data after dummification steps that may result in empty columns.
+    This utility is useful for cleaning data by removing constant features that 
+    have no predictive value.
 
     Args:
         df (pd.DataFrame): 
             The pandas DataFrame to clean.
+        verbose (bool): 
+            If True, prints the names of the columns that were dropped. 
+            Defaults to True.
 
     Returns:
         pd.DataFrame: 
-            A new DataFrame with the empty columns removed.
+            A new DataFrame with the constant columns removed.
     """
     if not isinstance(df, pd.DataFrame):
         raise TypeError("Input must be a pandas DataFrame.")
-    
+
     original_columns = set(df.columns)
-    
     cols_to_keep = []
+
     for col_name in df.columns:
         column = df[col_name]
         
-        # Keep any column that is not numeric by default
-        if not is_numeric_dtype(column):
+        # We can apply this logic to all columns or only focus on numeric ones.
+        # if not is_numeric_dtype(column):
+        #     cols_to_keep.append(col_name)
+        #     continue
+        
+        # Keep a column if it has more than one unique value (nunique ignores NaNs by default)
+        if column.nunique(dropna=True) > 1:
             cols_to_keep.append(col_name)
-            continue
 
-        # For numeric columns, check if there's at least one non-zero value.
-        if (column.fillna(0) != 0).any():
-            cols_to_keep.append(col_name)
-    
-    dropped_columns = original_columns - set(cols_to_keep)      
-    if dropped_columns and verbose:
-        print(f"Dropped {len(dropped_columns)} columns:")
-        for dropped_column in dropped_columns:
-            print(f"    {dropped_column}")
-    
+    dropped_columns = original_columns - set(cols_to_keep)
+    if verbose:
+        print(f"🧹 Dropped {len(dropped_columns)} constant columns.")
+        if dropped_columns:
+            for dropped_column in dropped_columns:
+                print(f"    {dropped_column}")
+
     return df[cols_to_keep]
 
 

ml_tools/datasetmaster.py

@@ -13,7 +13,7 @@ from torchvision.datasets import ImageFolder
 from torchvision import transforms
 import matplotlib.pyplot as plt
 from pathlib import Path
-from .utilities import _script_info
+from .utilities import _script_info, make_fullpath
 from .logger import _LOGGER
 
 
@@ -204,7 +204,7 @@ class DatasetMaker(_BaseMaker):
         if not self._is_split:
             raise RuntimeError("Continuous features must be normalized AFTER splitting data. Call .split_data() first.")
         if self._is_normalized:
-            _LOGGER.warning("Data has already been normalized.")
+            _LOGGER.warning("⚠️ Data has already been normalized.")
             return self
 
         # Use continuous features columns
@@ -232,7 +232,7 @@ class DatasetMaker(_BaseMaker):
     def split_data(self, test_size: float = 0.2, stratify: bool = False, random_state: Optional[int] = None) -> 'DatasetMaker':
         """Splits the data into training and testing sets."""
         if self._is_split:
-            _LOGGER.warning("Data has already been split.")
+            _LOGGER.warning("⚠️ Data has already been split.")
             return self
 
         if self.labels.dtype == 'object' or self.labels.dtype.name == 'category':
@@ -260,9 +260,9 @@ class DatasetMaker(_BaseMaker):
         Defaults to `SMOTETomek`.
         """
         if not self._is_split:
-            raise RuntimeError("Cannot balance data before it has been split. Call .split_data() first.")
+            raise RuntimeError("❌ Cannot balance data before it has been split. Call .split_data() first.")
         if self._is_balanced:
-            _LOGGER.warning("Training data has already been balanced.")
+            _LOGGER.warning("⚠️ Training data has already been balanced.")
             return self
 
         if resampler is None:
@@ -278,13 +278,13 @@ class DatasetMaker(_BaseMaker):
     def 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 ---")
+        _LOGGER.info("--- 🤖 Running Automated Processing Pipeline ---")
         self.process_categoricals(method=cat_method)
         self.split_data(test_size=test_size, stratify=True, random_state=random_state)
         self.normalize_continuous(method=normalize_method)
         if balance:
             self.balance_data()
-        _LOGGER.info("--- Automated Processing Complete ---")
+        _LOGGER.info("--- 🤖 Automated Processing Complete ---")
         return self
         
     def denormalize(self, data: Union[torch.Tensor, numpy.ndarray, pandas.DataFrame]) -> Union[numpy.ndarray, pandas.DataFrame]:
@@ -400,10 +400,7 @@ class VisionDatasetMaker(_BaseMaker):
         Logs a report of the types, sizes, and channels of image files
         found in the directory and its subdirectories.
         """
-        path_obj = Path(path)
-        if not path_obj.is_dir():
-            _LOGGER.error(f"Path is not a valid directory: {path_obj}")
-            return
+        path_obj = make_fullpath(path)
 
         non_image_files = set()
         img_types = set()
@@ -505,7 +502,7 @@ class VisionDatasetMaker(_BaseMaker):
         if not self._is_split:
             raise RuntimeError("Data has not been split. Call .split_data() first.")
         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
@@ -555,7 +552,7 @@ class SequenceMaker(_BaseMaker):
             raise RuntimeError("Data must be split BEFORE normalizing. Call .split_data() first.")
         
         if self.scaler:
-            _LOGGER.warning("Data has already been normalized.")
+            _LOGGER.warning("⚠️ Data has already been normalized.")
             return self
             
         if method == "standard":
@@ -579,7 +576,7 @@ class SequenceMaker(_BaseMaker):
     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))

ml_tools/ensemble_learning.py

@@ -915,7 +915,7 @@ def run_ensemble_pipeline(datasets_dir: Union[str,Path], save_dir: Union[str,Pat
     datasets_path = make_fullpath(datasets_dir)
     save_path = make_fullpath(save_dir, make=True)
     
-    _LOGGER.info("Training starting...")
+    _LOGGER.info("🏁 Training starting...")
     #Yield imputed dataset
     for dataframe, dataframe_name in yield_dataframes_from_dir(datasets_path):
         #Yield features dataframe and target dataframe
@@ -933,7 +933,7 @@ def run_ensemble_pipeline(datasets_dir: Union[str,Path], save_dir: Union[str,Pat
                                     test_features=X_test, test_target=y_test,
                                     feature_names=feature_names,target_name=target_name,
                                     debug=debug, save_dir=save_path, save_model=save_model)
-    print("")
+
     _LOGGER.info("✅ Training and evaluation complete.")
 
 

ml_tools/logger.py

@@ -10,7 +10,6 @@ import logging
 import sys
 
 
-
 __all__ = [
     "custom_logger"
 ]
@@ -85,10 +84,10 @@ def custom_logger(
         else:
             raise ValueError("Unsupported data type. Must be list, dict, DataFrame, str, or BaseException.")
 
-        _LOGGER.info(f"Log saved to: '{base_path}'")
+        _LOGGER.info(f"🗄️ Log saved to: '{base_path}'")
 
     except Exception as e:
-        _LOGGER.error(f"Log not saved: {e}")
+        _LOGGER.error(f"❌ Log not saved: {e}")
 
 
 def _log_list_to_txt(data: List[Any], path: Path) -> None:
@@ -176,7 +175,7 @@ def _get_logger(name: str = "ml_tools", level: int = logging.INFO):
         handler = logging.StreamHandler(sys.stdout)
         
         # Define the format string and the date format separately
-        log_format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+        log_format = '\n🐉%(asctime)s - %(name)s - %(levelname)s - %(message)s'
         date_format = '%Y-%m-%d %H:%M' # Format: Year-Month-Day Hour:Minute
         
         # Pass both the format and the date format to the Formatter

ml_tools/utilities.py

@@ -640,7 +640,7 @@ def train_dataset_orchestrator(list_of_dirs: list[Union[str,Path]],
                 print(f"⚠️ Failed to process file '{df_path}'. Reason: {e}")
                 continue 
 
-    print(f"{total_saved} single-target datasets were created.")
+    print(f"\n✅ {total_saved} single-target datasets were created.")
 
 
 class LogKeys:

dragon_ml_toolbox-3.5.1.dist-info/RECORD

@@ -1,25 +0,0 @@
-dragon_ml_toolbox-3.5.1.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-3.5.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=6cfpIeQ6D4Mcs10nkogQrkVyq1T7i2qXjjNHFoUMOyE,1892
-ml_tools/ETL_engineering.py,sha256=URol7s45fVIdLqnhyOU1Etbi-D7MksFg-qtNwsKiunY,39488
-ml_tools/GUI_tools.py,sha256=uFx6zIrQZzDPSTtOSHz8ptz-fxZiQz-lXHcrqwuYV_E,20385
-ml_tools/MICE_imputation.py,sha256=ed-YeQkEAeHxTNkWIHs09T4YeYNF0aqAnrUTcdIEp9E,11372
-ml_tools/ML_callbacks.py,sha256=gHZk-lyzAax6iEtG26zHuoobdAZCFJ6BmI6pWoXkOrw,13189
-ml_tools/ML_evaluation.py,sha256=3xOqVXLJDhbioKZ922yxFnSuO4VDQ-HFzZyZZ1MskVM,10054
-ml_tools/ML_trainer.py,sha256=zRs3crz_z4B285iJhmY7m4AFwnvvq4urOyl4zDuCLtA,14456
-ml_tools/ML_tutorial.py,sha256=-9tJO9ISPxEjRINVaF_Bu7tiiJ2W3zznQ4gNlZeP1HQ,12238
-ml_tools/PSO_optimization.py,sha256=RCvIFGyf28voo2mpbRKC6LfDzKslzY-aYoPwgv9F4Bg,25458
-ml_tools/RNN_forecast.py,sha256=IZLcPs3by0Chei7ill_Grjxs7BBUnzau0Oavi3dWiyE,1886
-ml_tools/VIF_factor.py,sha256=4b3HmrrolN7ZIAo16TWwLlExqj_xaa8MxbkXD1xPCys,10295
-ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ml_tools/_particle_swarm_optimization.py,sha256=b_eNNkA89Y40hj76KauivT8KLScH1B9wF2IXptOqkOw,22220
-ml_tools/_pytorch_models.py,sha256=bpWZsrSwCvHJQkR6UfoPpElsMv9AvmiNErNHC8NYB_I,10132
-ml_tools/data_exploration.py,sha256=41q0ux4rsf6ktQDzX1haYOk0iRZzmNucrHRi_rqlNLs,25013
-ml_tools/datasetmaster.py,sha256=N-uwfzWnl_qnoAqjbfS98I1pVNra5u6rhKLdWbFIReA,30122
-ml_tools/ensemble_learning.py,sha256=PPtBBLgLvaYOdY-MlcjXuxWWXf3JQavLNEysFgzjc_s,37470
-ml_tools/handle_excel.py,sha256=lwds7rDLlGSCWiWGI7xNg-Z7kxAepogp0lstSFa0590,12949
-ml_tools/logger.py,sha256=jC4Q2OqmDm8ZO9VpuZqBSWdXryqaJvLscqVJ6caNMOk,6009
-ml_tools/utilities.py,sha256=7cVWXjdxgSoIbZunuxJEOnJDSYp29liYsZexbrVDabs,23132
-dragon_ml_toolbox-3.5.1.dist-info/METADATA,sha256=F1RicIFxIpnKadElu8EU_k6P0FYKwGPRjHF2YXe9F6E,3273
-dragon_ml_toolbox-3.5.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-3.5.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-3.5.1.dist-info/RECORD,,