dragon-ml-toolbox 19.12.0__tar.gz → 19.12.2__tar.gz

{dragon_ml_toolbox-19.12.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-19.12.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 19.12.0
+Version: 19.12.2
 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-19.12.0 → dragon_ml_toolbox-19.12.2/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 19.12.0
+Version: 19.12.2
 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-19.12.0 → dragon_ml_toolbox-19.12.2}/ml_tools/_core/_IO_tools.py

@@ -434,8 +434,8 @@ def train_logger(train_config: Union[dict, Any],
     Logs training data to JSON, adding a timestamp to the filename.
     
     Args:
-        train_config (dict | Any): Training configuration parameters.
-        model_parameters (dict | Any): Model parameters.
+        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.
         train_history (dict | None): Training history log.
         save_directory (str | Path): Directory to save the log file.
     """
@@ -443,6 +443,9 @@ def train_logger(train_config: Union[dict, Any],
     if not isinstance(train_config, dict):
         if hasattr(train_config, "to_log") and callable(getattr(train_config, "to_log")):
             train_config_dict: dict = train_config.to_log()
+            if not isinstance(train_config_dict, dict):
+                _LOGGER.error("'train_config.to_log()' did not return a dictionary.")
+                raise ValueError()
         else:
             _LOGGER.error("'train_config' must be a dict or an object with a 'to_log()' method.")
             raise ValueError()
@@ -458,6 +461,9 @@ def train_logger(train_config: Union[dict, Any],
     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.")
+                raise ValueError()
         else:
             _LOGGER.error("'model_parameters' must be a dict or an object with a 'to_log()' method.")
             raise ValueError()

{dragon_ml_toolbox-19.12.0 → dragon_ml_toolbox-19.12.2}/ml_tools/_core/_ML_configuration.py

@@ -660,18 +660,27 @@ class DragonTrainingConfig(_BaseModelParams):
                  initial_learning_rate: float,
                  batch_size: int,
                  random_state: int = 101,
-                 early_stop_patience: Optional[int] = None,
-                 scheduler_patience: Optional[int] = None,
-                 scheduler_lr_factor: Optional[float] = None,
+                #  early_stop_patience: Optional[int] = None,
+                #  scheduler_patience: Optional[int] = None,
+                #  scheduler_lr_factor: Optional[float] = None,
                  **kwargs: Any) -> None:
+        """  
+        Args:
+            validation_size (float): Proportion of data for validation set.
+            test_size (float): Proportion of data for test set.
+            initial_learning_rate (float): Starting learning rate.
+            batch_size (int): Number of samples per training batch.
+            random_state (int): Seed for reproducibility.
+            **kwargs: Additional training parameters as key-value pairs.
+        """
         self.validation_size = validation_size
         self.test_size = test_size
         self.initial_learning_rate = initial_learning_rate
         self.batch_size = batch_size
         self.random_state = random_state
-        self.early_stop_patience = early_stop_patience
-        self.scheduler_patience = scheduler_patience
-        self.scheduler_lr_factor = scheduler_lr_factor
+        # self.early_stop_patience = early_stop_patience
+        # self.scheduler_patience = scheduler_patience
+        # self.scheduler_lr_factor = scheduler_lr_factor
         
         # Process kwargs with validation
         for key, value in kwargs.items():

{dragon_ml_toolbox-19.12.0 → dragon_ml_toolbox-19.12.2}/ml_tools/_core/_ML_finalize_handler.py

@@ -51,7 +51,7 @@ class FinalizedFileHandler:
         self._initial_sequence: Optional[np.ndarray] = None
         self._target_name: Optional[str] = None
         self._target_names: Optional[list[str]] = None
-        self._model_state_dict: Optional[Any] = None
+        self._model_state_dict: Optional[dict[str, Any]] = None
         
         # Set warning outputs
         self._verbose: bool=True
@@ -90,7 +90,7 @@ class FinalizedFileHandler:
             
         else:
             # It is a dict, but missing the keys, assume it is the raw state dict
-            _LOGGER.info(f"File '{pth_path.name}' does not have the required keys for a finalized-file. Treating it as raw PyTorch state dictionary.")
+            _LOGGER.warning(f"File '{pth_path.name}' does not have the required keys for a Dragon-ML finalized-file. Keys found:\n    {list(pth_file_content.keys())}")
             self._model_state_dict = pth_file_content
     
             
@@ -113,9 +113,10 @@ class FinalizedFileHandler:
         return self._task
     
     @property
-    def model_state_dict(self):
+    def model_state_dict(self) -> dict[str, Any]:
         """Returns the model state dictionary."""
-        return self._model_state_dict
+        # No need to check for None, as it is guaranteed to be set in __init__
+        return self._model_state_dict # type: ignore
     
     @property
     def epoch(self) -> Optional[int]:

{dragon_ml_toolbox-19.12.0 → dragon_ml_toolbox-19.12.2}/ml_tools/_core/_ML_trainer.py

@@ -663,7 +663,7 @@ class DragonTrainer(_BaseDragonTrainer):
         Evaluates the model, routing to the correct evaluation function based on task `kind`.
 
         Args:
-            model_checkpoint ('auto' | Path | None): 
+            model_checkpoint (Path | "best" | "current"): 
                 - Path to a valid checkpoint for the model. The state of the trained model will be overwritten in place.
                 - If 'best', the best checkpoint will be loaded if a DragonModelCheckpoint was provided. The state of the trained model will be overwritten in place.
                 - If 'current', use the current state of the trained model up the latest trained epoch.
@@ -1608,7 +1608,7 @@ class DragonDetectionTrainer(_BaseDragonTrainer):
 
         Args:
             save_dir (str | Path): Directory to save all reports and plots.
-            model_checkpoint ('auto' | Path | None): 
+            model_checkpoint (Path | "best" | "current"): 
                 - Path to a valid checkpoint for the model. The state of the trained model will be overwritten in place.
                 - If 'best', the best checkpoint will be loaded if a DragonModelCheckpoint was provided. The state of the trained model will be overwritten in place.
                 - If 'current', use the current state of the trained model up the latest trained epoch.
@@ -2046,7 +2046,7 @@ class DragonSequenceTrainer(_BaseDragonTrainer):
         Evaluates the model, routing to the correct evaluation function.
 
         Args:
-            model_checkpoint ('auto' | Path | None): 
+            model_checkpoint (Path | "best" | "current"): 
                 - Path to a valid checkpoint for the model.
                 - If 'best', the best checkpoint will be loaded.
                 - If 'current', use the current state of the trained model.

{dragon_ml_toolbox-19.12.0 → dragon_ml_toolbox-19.12.2}/ml_tools/_core/_data_exploration.py

@@ -17,7 +17,6 @@ from ._schema import FeatureSchema
 _LOGGER = get_logger("Data Exploration")
 
 
-# Keep track of all available tools, show using `info()`
 __all__ = [
     "summarize_dataframe",
     "drop_constant_columns",
@@ -754,6 +753,8 @@ def plot_categorical_vs_target(
     This function is a core EDA step for regression tasks to understand the
     relationship between a categorical independent variable and a continuous
     dependent variable.
+    
+    Plots are saved as individual .svg files in a structured way, with a subdirectory created for each target.
 
     Args:
         df (pd.DataFrame): The input DataFrame.
@@ -1167,7 +1168,7 @@ def clip_outliers_single(
 
 def clip_outliers_multi(
     df: pd.DataFrame,
-    clip_dict: Dict[str, Tuple[Union[int, float], Union[int, float]]],
+    clip_dict: Union[Dict[str, Tuple[int, int]], Dict[str, Tuple[float, float]]],
     verbose: bool=False
 ) -> pd.DataFrame:
     """

{dragon_ml_toolbox-19.12.0 → dragon_ml_toolbox-19.12.2}/ml_tools/_core/_utilities.py

@@ -396,7 +396,7 @@ def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], full_path: Path):
     if not isinstance(full_path, Path) or not full_path.suffix.endswith(".csv"):
         _LOGGER.error('A path object pointing to a .csv file must be provided.')
         raise ValueError()
-        
+
     save_dataframe_filename(df=df, 
                             save_dir=full_path.parent,
                             filename=full_path.name)

{dragon_ml_toolbox-19.12.0 → dragon_ml_toolbox-19.12.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "19.12.0"
+version = "19.12.2"
 description = "Complete pipelines and helper tools for data science and machine learning projects."
 authors = [
     { name = "Karl Luigi Loza Vidaurre", email = "luigiloza@gmail.com" }

{dragon_ml_toolbox-19.12.0 → dragon_ml_toolbox-19.12.2}/ml_tools/data_exploration.py

@@ -37,18 +37,18 @@ __all__ = [
     "plot_value_distributions", 
     "plot_continuous_vs_target",
     "plot_categorical_vs_target",
-    "encode_categorical_features",
     "split_features_targets", 
-    "split_continuous_binary", 
+    "encode_categorical_features",
     "clip_outliers_single", 
     "clip_outliers_multi",
     "drop_outlier_samples",
     "plot_correlation_heatmap", 
+    "finalize_feature_schema",
     "match_and_filter_columns_by_regex",
     "standardize_percentages",
     "reconstruct_one_hot",
     "reconstruct_binary",
     "reconstruct_multibinary",
-    "finalize_feature_schema",
+    "split_continuous_binary", 
     "apply_feature_schema",
 ]