dragon-ml-toolbox 20.3.0__tar.gz → 20.4.0__tar.gz

{dragon_ml_toolbox-20.3.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-20.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.3.0
+Version: 20.4.0
 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-20.3.0 → dragon_ml_toolbox-20.4.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.3.0
+Version: 20.4.0
 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-20.3.0 → dragon_ml_toolbox-20.4.0}/ml_tools/IO_tools/_IO_loggers.py

@@ -170,7 +170,7 @@ def _log_dict_to_json(data: dict[Any, Any], path: Path) -> None:
 
 
 def train_logger(train_config: Union[dict, Any],
-                 model_parameters: Union[dict, Any],
+                 model_parameters: Union[dict, Any, None],
                  train_history: Union[dict, None],
                  save_directory: Union[str, Path],
                  verbose: int = 3) -> None:
@@ -179,7 +179,7 @@ def train_logger(train_config: Union[dict, Any],
     
     Args:
         train_config (dict | Any): Training configuration parameters. If object, must have a `.to_log()` method returning a dict.
-        model_parameters (dict | Any): Model parameters. If object, must have a `.to_log()` method returning a dict.
+        model_parameters (dict | Any | None): Model parameters. If object, must have a `.to_log()` method returning a dict.
         train_history (dict | None): Training history log.
         save_directory (str | Path): Directory to save the log file.
     """
@@ -201,23 +201,27 @@ def train_logger(train_config: Union[dict, Any],
         
         train_config_dict = train_config
         
-    # model_parameters should be a dict or a custom object with the ".to_log()" method
-    if not isinstance(model_parameters, dict):
-        if hasattr(model_parameters, "to_log") and callable(getattr(model_parameters, "to_log")):
-            model_parameters_dict: dict = model_parameters.to_log()
-            if not isinstance(model_parameters_dict, dict):
-                _LOGGER.error("'model_parameters.to_log()' did not return a dictionary.")
+    # model_parameters should be a dict or a custom object with the ".to_log()" method or None
+    model_parameters_dict = {}
+
+    if model_parameters is not None:
+        if not isinstance(model_parameters, dict):
+            if hasattr(model_parameters, "to_log") and callable(getattr(model_parameters, "to_log")):
+                params_result: dict = model_parameters.to_log()
+                if not isinstance(params_result, dict):
+                    _LOGGER.error("'model_parameters.to_log()' did not return a dictionary.")
+                    raise ValueError()
+                model_parameters_dict = params_result
+            else:
+                _LOGGER.error("'model_parameters' must be a dict, None, or an object with a 'to_log()' method.")
                 raise ValueError()
         else:
-            _LOGGER.error("'model_parameters' must be a dict or an object with a 'to_log()' method.")
-            raise ValueError()
-    else:
-        # check for empty dict
-        if not model_parameters:
-            _LOGGER.error("'model_parameters' dictionary is empty.")
-            raise ValueError()
-        
-        model_parameters_dict = model_parameters
+            # check for empty dict
+            if not model_parameters:
+                _LOGGER.error("'model_parameters' dictionary is empty.")
+                raise ValueError()
+            
+            model_parameters_dict = model_parameters
     
     # make base dictionary
     data: dict = train_config_dict | model_parameters_dict

{dragon_ml_toolbox-20.3.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ML_evaluation/_classification.py

@@ -329,7 +329,11 @@ def classification_metrics(save_dir: Union[str, Path],
             fig_roc, ax_roc = plt.subplots(figsize=CLASSIFICATION_PLOT_SIZE, dpi=DPI_value)
             ax_roc.plot(fpr, tpr, label=f'AUC = {auc:.2f}', color=format_config.ROC_PR_line)
             ax_roc.plot([0, 1], [0, 1], 'k--')
-            ax_roc.set_title(f'Receiver Operating Characteristic{plot_title}', pad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size + 2)
+            # use "ROC" if extra title, else use "Receiver Operating Characteristic" title
+            if plot_title.strip():
+                ax_roc.set_title(f'ROC{plot_title}', pad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size + 2)
+            else:
+                ax_roc.set_title(f'Receiver Operating Characteristic', pad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size + 2)
             ax_roc.set_xlabel('False Positive Rate', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size)
             ax_roc.set_ylabel('True Positive Rate', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size)
             
@@ -351,7 +355,11 @@ def classification_metrics(save_dir: Union[str, Path],
             ap_score = average_precision_score(y_true_binary, y_score)
             fig_pr, ax_pr = plt.subplots(figsize=CLASSIFICATION_PLOT_SIZE, dpi=DPI_value)
             ax_pr.plot(recall, precision, label=f'Avg Precision = {ap_score:.2f}', color=format_config.ROC_PR_line)
-            ax_pr.set_title(f'Precision-Recall Curve{plot_title}', pad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size + 2)
+            # Use "PR Curve" if extra title, else use "Precision-Recall Curve" title
+            if plot_title.strip():
+                ax_pr.set_title(f'PR Curve{plot_title}', pad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size + 2)
+            else:
+                ax_pr.set_title(f'Precision-Recall Curve', pad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size + 2)
             ax_pr.set_xlabel('Recall', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size)
             ax_pr.set_ylabel('Precision', labelpad=_EvaluationConfig.LABEL_PADDING, fontsize=format_config.font_size)
             

{dragon_ml_toolbox-20.3.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ML_optimization/_multi_dragon.py

@@ -313,14 +313,15 @@ class DragonParetoOptimizer:
         return pareto_df
     
     def save_solutions(self, 
+                       csv_if_exists: Literal['fail', 'replace', 'append'] = 'replace',
                        save_to_sql: bool = False,
                        sql_table_name: Optional[str] = None,
                        sql_if_exists: Literal['fail', 'replace', 'append'] = 'replace') -> None:
         """
-        Saves the current Pareto front to a CSV file, with optional integer rounding 
-        for specific continuous columns. Optionally saves to a SQL database.
+        Saves the current Pareto front to a CSV file. Optionally saves to a SQL database.
 
         Args:
+            csv_if_exists (str): Behavior if CSV file exists ('fail', 'replace', 'append').
             save_to_sql (bool): If True, also writes the results to a SQLite database in the save_dir.
             sql_table_name (str, optional): Specific table name for SQL. If None, uses the solutions filename.
             sql_if_exists (str): Behavior if SQL table exists ('fail', 'replace', 'append').
@@ -377,9 +378,24 @@ class DragonParetoOptimizer:
         # sanitize filename and add extension if missing
         sanitized_filename = sanitize_filename(filename)
         csv_filename = sanitized_filename if sanitized_filename.lower().endswith(".csv") else f"{sanitized_filename}.csv"
+        full_csv_path = save_path / csv_filename
         
-        save_dataframe_filename(df=df_to_save, save_dir=save_path, filename=csv_filename, verbose=1)
-        _LOGGER.info(f"💾 Pareto solutions saved to CSV: '{save_path.name}/{csv_filename}'. Shape: {df_to_save.shape}")
+        # Logic to handle Append/Fail/Replace for CSV
+        if csv_if_exists == 'append' and full_csv_path.exists():
+            try:
+                # Append mode: write without header, index=False to match standard data exports
+                df_to_save.to_csv(full_csv_path, mode='a', header=False, index=False)
+                _LOGGER.info(f"💾 Pareto solutions APPENDED to CSV: '{save_path.name}/{csv_filename}'. Added {len(df_to_save)} rows.")
+            except Exception as e:
+                _LOGGER.error(f"Failed to append CSV: {e}")
+                raise e
+        elif csv_if_exists == 'fail' and full_csv_path.exists():
+            _LOGGER.error(f"File '{full_csv_path}' already exists and csv_if_exists='fail'.")
+            raise FileExistsError()
+        else:
+            # Default 'replace' or new file creation using the existing utility
+            save_dataframe_filename(df=df_to_save, save_dir=save_path, filename=csv_filename, verbose=1)
+            _LOGGER.info(f"💾 Pareto solutions saved to CSV: '{save_path.name}/{csv_filename}'. Shape: {df_to_save.shape}")
         
         # Save optimization bounds as JSON for reference (debug mode)
         if self._debug:
@@ -404,13 +420,13 @@ class DragonParetoOptimizer:
                 save_json(
                     data=bounds_data, 
                     directory=save_path, 
-                    filename="all_optimization_bounds.json", 
+                    filename="all_debug_optimization_bounds.json", 
                     verbose=False
                 )
-                _LOGGER.info(f"💾 Optimization bounds saved to: '{save_path.name}/all_optimization_bounds.json'")
+                _LOGGER.info(f"💾 Optimization bounds saved to: '{save_path.name}/all_debug_optimization_bounds.json'")
                 
             except Exception as e:
-                _LOGGER.warning(f"Failed to save optimization bounds to JSON: {e}")
+                _LOGGER.warning(f"Failed to save debug optimization bounds to JSON: {e}")
         
         # --- 2. Save SQL (Optional) ---
         if save_to_sql:
@@ -636,7 +652,7 @@ class DragonParetoOptimizer:
                        z_target: Union[int, str],
                        hue_target: Optional[Union[int, str]] = None):
         """
-        Public API to generate 3D visualizations for specific targets.
+        Generate 3D visualizations for specific targets.
         
         Args:
             x_target (int|str): Index or name of the target for the X axis.

{dragon_ml_toolbox-20.3.0 → dragon_ml_toolbox-20.4.0}/ml_tools/keys/_keys.py

@@ -297,7 +297,7 @@ class _EvaluationConfig:
     # large sizes for SVG layout to accommodate large fonts
     REGRESSION_PLOT_SIZE = (12, 8)
     SEQUENCE_PLOT_SIZE = (12, 8)
-    CLASSIFICATION_PLOT_SIZE = (10, 10)
+    CLASSIFICATION_PLOT_SIZE = (9, 9)
     # Loss plot
     LOSS_PLOT_SIZE = (18, 9)
     LOSS_PLOT_LABEL_SIZE = 24

{dragon_ml_toolbox-20.3.0 → dragon_ml_toolbox-20.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "20.3.0"
+version = "20.4.0"
 description = "Complete pipelines and helper tools for data science and machine learning projects."
 authors = [
     { name = "Karl Luigi Loza Vidaurre", email = "luigiloza@gmail.com" }