dragon-ml-toolbox 19.12.1__tar.gz → 19.12.2__tar.gz

{dragon_ml_toolbox-19.12.1/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: 19.12.1
+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-19.12.1 → 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: 19.12.1
+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-19.12.1 → 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-19.12.1 → 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-19.12.1 → 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-19.12.1 → dragon_ml_toolbox-19.12.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "19.12.1"
+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-19.12.1 → 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",
 ]