dragon-ml-toolbox 20.2.0__tar.gz → 20.4.0__tar.gz

{dragon_ml_toolbox-20.2.0/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: 20.2.0
+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-20.2.0 → 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: 20.2.0
+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-20.2.0 → dragon_ml_toolbox-20.4.0}/dragon_ml_toolbox.egg-info/SOURCES.txt

@@ -13,122 +13,99 @@ ml_tools/ETL_cleaning/__init__.py
 ml_tools/ETL_cleaning/_basic_clean.py
 ml_tools/ETL_cleaning/_clean_tools.py
 ml_tools/ETL_cleaning/_dragon_cleaner.py
-ml_tools/ETL_cleaning/_imprimir.py
 ml_tools/ETL_engineering/__init__.py
 ml_tools/ETL_engineering/_dragon_engineering.py
-ml_tools/ETL_engineering/_imprimir.py
 ml_tools/ETL_engineering/_transforms.py
 ml_tools/GUI_tools/_GUI_tools.py
 ml_tools/GUI_tools/__init__.py
-ml_tools/GUI_tools/_imprimir.py
 ml_tools/IO_tools/_IO_loggers.py
 ml_tools/IO_tools/_IO_save_load.py
 ml_tools/IO_tools/_IO_utils.py
 ml_tools/IO_tools/__init__.py
-ml_tools/IO_tools/_imprimir.py
 ml_tools/MICE/_MICE_imputation.py
 ml_tools/MICE/__init__.py
 ml_tools/MICE/_dragon_mice.py
-ml_tools/MICE/_imprimir.py
 ml_tools/ML_callbacks/__init__.py
 ml_tools/ML_callbacks/_base.py
 ml_tools/ML_callbacks/_checkpoint.py
 ml_tools/ML_callbacks/_early_stop.py
-ml_tools/ML_callbacks/_imprimir.py
 ml_tools/ML_callbacks/_scheduler.py
 ml_tools/ML_chain/__init__.py
 ml_tools/ML_chain/_chaining_tools.py
 ml_tools/ML_chain/_dragon_chain.py
-ml_tools/ML_chain/_imprimir.py
 ml_tools/ML_chain/_update_schema.py
 ml_tools/ML_configuration/__init__.py
 ml_tools/ML_configuration/_base_model_config.py
 ml_tools/ML_configuration/_finalize.py
-ml_tools/ML_configuration/_imprimir.py
 ml_tools/ML_configuration/_metrics.py
 ml_tools/ML_configuration/_models.py
 ml_tools/ML_configuration/_training.py
 ml_tools/ML_datasetmaster/__init__.py
 ml_tools/ML_datasetmaster/_base_datasetmaster.py
 ml_tools/ML_datasetmaster/_datasetmaster.py
-ml_tools/ML_datasetmaster/_imprimir.py
 ml_tools/ML_datasetmaster/_sequence_datasetmaster.py
 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/_imprimir.py
 ml_tools/ML_evaluation/_loss.py
 ml_tools/ML_evaluation/_regression.py
 ml_tools/ML_evaluation/_sequence.py
 ml_tools/ML_evaluation/_vision.py
 ml_tools/ML_evaluation_captum/_ML_evaluation_captum.py
 ml_tools/ML_evaluation_captum/__init__.py
-ml_tools/ML_evaluation_captum/_imprimir.py
 ml_tools/ML_finalize_handler/_ML_finalize_handler.py
 ml_tools/ML_finalize_handler/__init__.py
-ml_tools/ML_finalize_handler/_imprimir.py
 ml_tools/ML_inference/__init__.py
 ml_tools/ML_inference/_base_inference.py
 ml_tools/ML_inference/_chain_inference.py
 ml_tools/ML_inference/_dragon_inference.py
-ml_tools/ML_inference/_imprimir.py
 ml_tools/ML_inference/_multi_inference.py
 ml_tools/ML_inference_sequence/__init__.py
-ml_tools/ML_inference_sequence/_imprimir.py
 ml_tools/ML_inference_sequence/_sequence_inference.py
 ml_tools/ML_inference_vision/__init__.py
-ml_tools/ML_inference_vision/_imprimir.py
 ml_tools/ML_inference_vision/_vision_inference.py
 ml_tools/ML_models/__init__.py
-ml_tools/ML_models/_advanced_models.py
 ml_tools/ML_models/_base_mlp_attention.py
 ml_tools/ML_models/_base_save_load.py
+ml_tools/ML_models/_dragon_autoint.py
+ml_tools/ML_models/_dragon_gate.py
+ml_tools/ML_models/_dragon_node.py
+ml_tools/ML_models/_dragon_tabnet.py
 ml_tools/ML_models/_dragon_tabular.py
-ml_tools/ML_models/_imprimir.py
 ml_tools/ML_models/_mlp_attention.py
 ml_tools/ML_models/_models_advanced_helpers.py
 ml_tools/ML_models_sequence/__init__.py
-ml_tools/ML_models_sequence/_imprimir.py
 ml_tools/ML_models_sequence/_sequence_models.py
 ml_tools/ML_models_vision/__init__.py
 ml_tools/ML_models_vision/_base_wrapper.py
 ml_tools/ML_models_vision/_image_classification.py
 ml_tools/ML_models_vision/_image_segmentation.py
-ml_tools/ML_models_vision/_imprimir.py
 ml_tools/ML_models_vision/_object_detection.py
 ml_tools/ML_optimization/__init__.py
-ml_tools/ML_optimization/_imprimir.py
 ml_tools/ML_optimization/_multi_dragon.py
 ml_tools/ML_optimization/_single_dragon.py
 ml_tools/ML_optimization/_single_manual.py
 ml_tools/ML_scaler/_ML_scaler.py
 ml_tools/ML_scaler/__init__.py
-ml_tools/ML_scaler/_imprimir.py
 ml_tools/ML_trainer/__init__.py
 ml_tools/ML_trainer/_base_trainer.py
 ml_tools/ML_trainer/_dragon_detection_trainer.py
 ml_tools/ML_trainer/_dragon_sequence_trainer.py
 ml_tools/ML_trainer/_dragon_trainer.py
-ml_tools/ML_trainer/_imprimir.py
 ml_tools/ML_utilities/__init__.py
 ml_tools/ML_utilities/_artifact_finder.py
-ml_tools/ML_utilities/_imprimir.py
 ml_tools/ML_utilities/_inspection.py
 ml_tools/ML_utilities/_train_tools.py
 ml_tools/ML_vision_transformers/__init__.py
 ml_tools/ML_vision_transformers/_core_transforms.py
-ml_tools/ML_vision_transformers/_imprimir.py
 ml_tools/ML_vision_transformers/_offline_augmentation.py
 ml_tools/PSO_optimization/_PSO.py
 ml_tools/PSO_optimization/__init__.py
-ml_tools/PSO_optimization/_imprimir.py
 ml_tools/SQL/__init__.py
 ml_tools/SQL/_dragon_SQL.py
-ml_tools/SQL/_imprimir.py
 ml_tools/VIF/_VIF_factor.py
 ml_tools/VIF/__init__.py
-ml_tools/VIF/_imprimir.py
 ml_tools/_core/__init__.py
 ml_tools/_core/_logger.py
 ml_tools/_core/_schema_load_ops.py
@@ -137,46 +114,33 @@ ml_tools/data_exploration/__init__.py
 ml_tools/data_exploration/_analysis.py
 ml_tools/data_exploration/_cleaning.py
 ml_tools/data_exploration/_features.py
-ml_tools/data_exploration/_imprimir.py
 ml_tools/data_exploration/_plotting.py
 ml_tools/data_exploration/_schema_ops.py
 ml_tools/ensemble_evaluation/__init__.py
 ml_tools/ensemble_evaluation/_ensemble_evaluation.py
-ml_tools/ensemble_evaluation/_imprimir.py
 ml_tools/ensemble_inference/__init__.py
 ml_tools/ensemble_inference/_ensemble_inference.py
-ml_tools/ensemble_inference/_imprimir.py
 ml_tools/ensemble_learning/__init__.py
 ml_tools/ensemble_learning/_ensemble_learning.py
-ml_tools/ensemble_learning/_imprimir.py
 ml_tools/excel_handler/__init__.py
 ml_tools/excel_handler/_excel_handler.py
-ml_tools/excel_handler/_imprimir.py
 ml_tools/keys/__init__.py
-ml_tools/keys/_imprimir.py
 ml_tools/keys/_keys.py
 ml_tools/math_utilities/__init__.py
-ml_tools/math_utilities/_imprimir.py
 ml_tools/math_utilities/_math_utilities.py
 ml_tools/optimization_tools/__init__.py
-ml_tools/optimization_tools/_imprimir.py
 ml_tools/optimization_tools/_optimization_bounds.py
 ml_tools/optimization_tools/_optimization_plots.py
 ml_tools/path_manager/__init__.py
 ml_tools/path_manager/_dragonmanager.py
-ml_tools/path_manager/_imprimir.py
 ml_tools/path_manager/_path_tools.py
 ml_tools/plot_fonts/__init__.py
-ml_tools/plot_fonts/_imprimir.py
 ml_tools/plot_fonts/_plot_fonts.py
 ml_tools/schema/__init__.py
 ml_tools/schema/_feature_schema.py
 ml_tools/schema/_gui_schema.py
-ml_tools/schema/_imprimir.py
 ml_tools/serde/__init__.py
-ml_tools/serde/_imprimir.py
 ml_tools/serde/_serde.py
 ml_tools/utilities/__init__.py
-ml_tools/utilities/_imprimir.py
 ml_tools/utilities/_utility_save_load.py
 ml_tools/utilities/_utility_tools.py

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ETL_cleaning/__init__.py

@@ -13,7 +13,7 @@ from ._clean_tools import (
     save_unique_values
 )
 
-from ._imprimir import info
+from .._core import _imprimir_disponibles
 
 
 __all__ = [
@@ -24,3 +24,7 @@ __all__ = [
     "basic_clean_drop",
     "drop_macro_polars",
 ]
+
+
+def info():
+    _imprimir_disponibles(__all__)

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ETL_cleaning/_basic_clean.py

@@ -261,7 +261,7 @@ def _generate_null_report(df: pl.DataFrame, save_dir: Path, filename: str):
         (pl.col("null_count") / total_rows * 100).round(2).alias("missing_percent")
     ).sort("missing_percent", descending=True)
     
-    save_dataframe_filename(df=report, save_dir=save_dir, filename=filename)
+    save_dataframe_filename(df=report, save_dir=save_dir, filename=filename, verbose=2)
 
 
 def drop_macro_polars(df: pl.DataFrame, 

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ETL_engineering/__init__.py

@@ -21,7 +21,7 @@ from ._transforms import (
     MolecularFormulaTransformer
 )
 
-from ._imprimir import info
+from .._core import _imprimir_disponibles
 
 
 __all__ = [
@@ -43,3 +43,7 @@ __all__ = [
     "DateFeatureExtractor",
     "MolecularFormulaTransformer"
 ]
+
+
+def info():
+    _imprimir_disponibles(__all__)

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/GUI_tools/__init__.py

@@ -6,7 +6,7 @@ from ._GUI_tools import (
     catch_exceptions,
 )
 
-from ._imprimir import info
+from .._core import _imprimir_disponibles
 
 
 __all__ = [
@@ -16,3 +16,7 @@ __all__ = [
     "DragonGUIHandler",
     "catch_exceptions", 
 ]
+
+
+def info():
+    _imprimir_disponibles(__all__)

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/IO_tools/_IO_loggers.py

@@ -29,6 +29,7 @@ def custom_logger(
     log_name: str,
     add_timestamp: bool=True,
     dict_as: Literal['auto', 'json', 'csv'] = 'auto',
+    verbose: int = 3
 ) -> None:
     """
     Logs various data types to corresponding output formats:
@@ -63,6 +64,7 @@ def custom_logger(
     """
     try:
         if not isinstance(data, BaseException) and not data:
+            # Display a warning instead of error to allow program continuation
             _LOGGER.warning("Empty data received. No log file will be saved.")
             return
         
@@ -103,8 +105,9 @@ def custom_logger(
         else:
             _LOGGER.error("Unsupported data type. Must be list, dict, str, or BaseException.")
             raise ValueError()
-
-        _LOGGER.info(f"Log saved as: '{base_path.name}'")
+        
+        if verbose >= 2:
+            _LOGGER.info(f"Log saved as: '{base_path.name}'")
 
     except Exception:
         _LOGGER.exception(f"Log not saved.")
@@ -167,15 +170,16 @@ 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]):
+                 save_directory: Union[str, Path],
+                 verbose: int = 3) -> None:
     """
     Logs training data to JSON, adding a timestamp to the filename.
     
     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.
     """
@@ -197,23 +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
@@ -230,6 +238,10 @@ def train_logger(train_config: Union[dict, Any],
         save_directory=save_directory,
         log_name="Training_Log",
         add_timestamp=True,
-        dict_as='json'
+        dict_as='json',
+        verbose=1
     )
+    
+    if verbose >= 2:
+        _LOGGER.info(f"Training log saved to '{save_directory}/Training_Log.json'")
 

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/IO_tools/__init__.py

@@ -14,7 +14,7 @@ from ._IO_save_load import (
     load_list_strings,
 )
 
-from ._imprimir import info
+from .._core import _imprimir_disponibles
 
 
 __all__ = [
@@ -26,3 +26,7 @@ __all__ = [
     "load_list_strings",
     "compare_lists"
 ]
+
+
+def info():
+    _imprimir_disponibles(__all__)

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/MICE/__init__.py

@@ -4,9 +4,11 @@ from ._dragon_mice import (
     get_imputed_distributions,
 )
 
-from ._MICE_imputation import run_mice_pipeline
+from ._MICE_imputation import (
+    run_mice_pipeline,
+)
 
-from ._imprimir import info
+from .._core import _imprimir_disponibles
 
 
 __all__ = [
@@ -15,3 +17,7 @@ __all__ = [
     "get_imputed_distributions",
     "run_mice_pipeline",
 ]
+
+
+def info():
+    _imprimir_disponibles(__all__)

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/MICE/_dragon_mice.py

@@ -284,7 +284,7 @@ class DragonMICE:
 def _save_imputed_datasets(save_dir: Union[str, Path], imputed_datasets: list, df_targets: pd.DataFrame, imputed_dataset_names: list[str]):
     for imputed_df, subname in zip(imputed_datasets, imputed_dataset_names):
         merged_df = merge_dataframes(imputed_df, df_targets, direction="horizontal", verbose=False)
-        save_dataframe_filename(df=merged_df, save_dir=save_dir, filename=subname)
+        save_dataframe_filename(df=merged_df, save_dir=save_dir, filename=subname, verbose=2)
 
 
 #Convergence diagnostic

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ML_callbacks/__init__.py

@@ -12,7 +12,7 @@ from ._scheduler import (
     DragonPlateauScheduler,
 )
 
-from ._imprimir import info
+from .._core import _imprimir_disponibles
 
 
 __all__ = [
@@ -22,3 +22,7 @@ __all__ = [
     "DragonScheduler",
     "DragonPlateauScheduler",
 ]
+
+
+def info():
+    _imprimir_disponibles(__all__)

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ML_chain/__init__.py

@@ -12,7 +12,7 @@ from ._update_schema import (
     derive_next_step_schema
 )
 
-from ._imprimir import info
+from .._core import _imprimir_disponibles
 
 
 __all__ = [
@@ -22,3 +22,7 @@ __all__ = [
     "augment_dataset_with_predictions_multi",
     "prepare_chaining_dataset",
 ]
+
+
+def info():
+    _imprimir_disponibles(__all__)

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ML_configuration/__init__.py

@@ -41,9 +41,10 @@ from ._models import (
 from ._training import (
     DragonTrainingConfig,
     DragonParetoConfig,
+    DragonOptimizerConfig
 )
 
-from ._imprimir import info
+from .._core import _imprimir_disponibles
 
 
 __all__ = [
@@ -87,4 +88,9 @@ __all__ = [
     # --- Training Config ---
     "DragonTrainingConfig",
     "DragonParetoConfig",
+    "DragonOptimizerConfig",
 ]
+
+
+def info():
+    _imprimir_disponibles(__all__)

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ML_configuration/_training.py

@@ -14,7 +14,8 @@ _LOGGER = get_logger("ML Configuration")
 __all__ = [    
     # --- Training Config ---
     "DragonTrainingConfig",
-    "DragonParetoConfig"
+    "DragonParetoConfig",
+    "DragonOptimizerConfig",
 ]
 
 
@@ -137,3 +138,66 @@ class DragonParetoConfig(_BaseModelParams):
         self.plot_font_size = plot_font_size
         self.discretize_start_at_zero = discretize_start_at_zero
 
+
+class DragonOptimizerConfig(_BaseModelParams):
+    """
+    Configuration object for the Single-Objective DragonOptimizer.
+    """
+    def __init__(self,
+                 target_name: str,
+                 task: Literal["min", "max"],
+                 continuous_bounds_map: Union[dict[str, tuple[float, float]], str, Path],
+                 save_directory: Union[str, Path],
+                 save_format: Literal['csv', 'sqlite', 'both'] = 'csv',
+                 algorithm: Literal["SNES", "CEM", "Genetic"] = "Genetic",
+                 population_size: int = 500,
+                 generations: int = 1000,
+                 repetitions: int = 1,
+                 discretize_start_at_zero: bool = True,
+                 **searcher_kwargs: Any):
+        """
+        Args:
+            target_name (str): The name of the target variable to optimize.
+            task (str): The optimization goal, either "min" or "max".
+            continuous_bounds_map (Dict | str | Path): Dictionary {feature_name: (min, max)} or path to "optimization_bounds.json".
+            save_directory (str | Path): Directory to save results.
+            save_format (str): Format for saving results ('csv', 'sqlite', 'both').
+            algorithm (str): Search algorithm ("SNES", "CEM", "Genetic").
+            population_size (int): Population size for CEM and GeneticAlgorithm.
+            generations (int): Number of generations per repetition.
+            repetitions (int): Number of independent optimization runs.
+            discretize_start_at_zero (bool): True if discrete encoding starts at 0.
+            **searcher_kwargs: Additional arguments for the specific search algorithm 
+                               (e.g., stdev_init for SNES).
+        """
+        # Validate paths
+        self.save_directory = make_fullpath(save_directory, make=True, enforce="directory")
+        
+        if isinstance(continuous_bounds_map, (str, Path)):
+            self.continuous_bounds_map = make_fullpath(continuous_bounds_map, make=False, enforce="directory")
+        else:
+            self.continuous_bounds_map = continuous_bounds_map
+
+        # Core params
+        self.target_name = target_name
+        self.task = task
+        self.save_format = save_format
+        self.algorithm = algorithm
+        self.population_size = population_size
+        self.generations = generations
+        self.repetitions = repetitions
+        self.discretize_start_at_zero = discretize_start_at_zero
+        
+        # Store algorithm specific kwargs
+        self.searcher_kwargs = searcher_kwargs
+
+        # Basic Validation
+        if self.task not in ["min", "max"]:
+             _LOGGER.error(f"Invalid task '{self.task}'. Must be 'min' or 'max'.")
+             raise ValueError()
+             
+        valid_algos = ["SNES", "CEM", "Genetic"]
+        if self.algorithm not in valid_algos:
+            _LOGGER.error(f"Invalid algorithm '{self.algorithm}'. Must be one of {valid_algos}.")
+            raise ValueError()
+

{dragon_ml_toolbox-20.2.0 → dragon_ml_toolbox-20.4.0}/ml_tools/ML_datasetmaster/__init__.py

@@ -13,7 +13,7 @@ from ._vision_datasetmaster import (
     DragonDatasetObjectDetection
 )
 
-from ._imprimir import info
+from .._core import _imprimir_disponibles
 
 
 __all__ = [
@@ -26,3 +26,7 @@ __all__ = [
     "DragonDatasetSegmentation",
     "DragonDatasetObjectDetection",
 ]
+
+
+def info():
+    _imprimir_disponibles(__all__)