dragon-ml-toolbox 19.12.0__py3-none-any.whl → 19.12.2__py3-none-any.whl

{dragon_ml_toolbox-19.12.0.dist-info → dragon_ml_toolbox-19.12.2.dist-info}/METADATA

@@ -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.dist-info → dragon_ml_toolbox-19.12.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-19.12.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-19.12.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
+dragon_ml_toolbox-19.12.2.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-19.12.2.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
 ml_tools/ETL_cleaning.py,sha256=cKXyRFaaFs_beAGDnQM54xnML671kq-yJEGjHafW-20,351
 ml_tools/ETL_engineering.py,sha256=cwh1FhtNdUHllUDvho-x3SIVj4KwG_rFQR6VYzWUg0U,898
 ml_tools/GUI_tools.py,sha256=O89rG8WQv6GY1DiphQjIsPzXFCQID6te7q_Sgt1iTkQ,294
@@ -38,7 +38,7 @@ ml_tools/SQL.py,sha256=ZYlY5L-k2mkDckOhNPtJEof2L7ePe_KBpgx55WG5NKs,84
 ml_tools/VIF_factor.py,sha256=xGUbnfhh1eqUiHX-tIpJBn_3Y_h3SOuNfVKkpsQXc7w,184
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
-ml_tools/data_exploration.py,sha256=qgo4hfuLnj-GzEpnOi4AzaX5xFjwM5Ox-uRjMaR4dug,1468
+ml_tools/data_exploration.py,sha256=vwCgOHhpPku2uuRVscrco6sXwkjc3ruOlfO002OQ74M,1468
 ml_tools/ensemble_evaluation.py,sha256=P26vyS2fMV3Pm_4w2MN1z1eS7aVJzYagsyLmqC-Io6Q,468
 ml_tools/ensemble_inference.py,sha256=sl_Dq9KaN0SrtZmyiVrrhWd6lSjdQangSIUUUIFvfj4,178
 ml_tools/ensemble_learning.py,sha256=BLPnpfJWCly-D75mkRP1FE5TExoWAAlAHR89KAzW9iU,336
@@ -54,18 +54,18 @@ ml_tools/utilities.py,sha256=dHNjGPH3Ck9V41IRFbRojE_RW6lACdxrNZz0FxI5SQY,691
 ml_tools/_core/_ETL_cleaning.py,sha256=_pTNKuapNHgWErmxvsXW-2YzCm4BaTshKV627A38RuA,28748
 ml_tools/_core/_ETL_engineering.py,sha256=JgIWrQGyNjmLrbyv5Kh0EHKBLmYlyrGKSnKRxGzxSco,57930
 ml_tools/_core/_GUI_tools.py,sha256=kpvk18Eb4vdLzo-I5mBV1yuwPXs-NJJ01rn-iCXHvIY,49079
-ml_tools/_core/_IO_tools.py,sha256=oWaYa_OVO-8ANVt_a9F1QPMvyOcI2yLbtq7LoVHlqek,16625
+ml_tools/_core/_IO_tools.py,sha256=sEbtzDHkc9GNkXvsFS9ic038LzAW-rxXPuLwtoHXzGw,17107
 ml_tools/_core/_MICE_imputation.py,sha256=64l20duGWt93Q2MbqcWqrA1s99JPRf5AJACb1CZi2xI,21149
 ml_tools/_core/_ML_callbacks.py,sha256=T0PjptlpC75_Tp3bWIMPTYhxsMX-8z4YtDT4FJ3p8jg,27988
 ml_tools/_core/_ML_chaining_inference.py,sha256=vXUPZzuQ2yKU71kkvUsE0xPo0hN-Yu6gfnL0JbXoRjI,7783
 ml_tools/_core/_ML_chaining_utilities.py,sha256=nsYowgRbkIYuzRiHlqsM3tnC3c-8O73CY8DHUF14XL0,19248
-ml_tools/_core/_ML_configuration.py,sha256=hwnDCo9URsFqRCgLuFJhGTtoOqbE1XJreNY8B_3spTg,52693
+ml_tools/_core/_ML_configuration.py,sha256=olRcam2s-Y5oUr8BAcmhwIBQDmaQZm2RHTv5sK2HeOU,53151
 ml_tools/_core/_ML_configuration_pytab.py,sha256=C3e4iScqdRePVDoqnic6xXMOW7DNYqpgTCeaFDyMdL4,3286
 ml_tools/_core/_ML_datasetmaster.py,sha256=yU1BMtzz6XumMWCetVACrRLk7WJQwmYhaQ-VAWu9Ots,32043
 ml_tools/_core/_ML_evaluation.py,sha256=bu8qlYzhWSC1B7wNfCC5TSF-oed-uP8EF7TV45VTiBM,37325
 ml_tools/_core/_ML_evaluation_captum.py,sha256=a69jnghIzE9qppuw2vzTBMdTErnZkDkTA3MPUUYjsS4,19212
 ml_tools/_core/_ML_evaluation_multi.py,sha256=n_AJbKF58DMUrYqJutwPFV5z6sNssDPA1Gl05IfPG5s,23647
-ml_tools/_core/_ML_finalize_handler.py,sha256=0eZ_0N2L5aUUIJUgvhAQ-rbd8XbE9UmNqTKSJq09uTI,6987
+ml_tools/_core/_ML_finalize_handler.py,sha256=1__wG3Jcr9h1a99F-CmHezhEw1_Ojxh3aDHNyJN2S5w,7127
 ml_tools/_core/_ML_inference.py,sha256=5swm2lnsrDLalBnCm7gZPlDucX4yNCq5vn7ck3SW_4Q,29791
 ml_tools/_core/_ML_models.py,sha256=8FUx4-TVghlBF9srh1_5UxovrWPU7YEZ6XXLqwJei88,27974
 ml_tools/_core/_ML_models_advanced.py,sha256=oU6M5FEBMQ9yPp32cziWh3bz8SXRho07vFMC8ZDVcuU,45002
@@ -77,7 +77,7 @@ ml_tools/_core/_ML_sequence_datasetmaster.py,sha256=0YVOPf-y4ZNdgUxropXUWrmInNyG
 ml_tools/_core/_ML_sequence_evaluation.py,sha256=AiPHtZ9DRpE6zL9n3Tp5eGGD9vrYRkLbZ0Nc274mL7I,8069
 ml_tools/_core/_ML_sequence_inference.py,sha256=zd3hBwOtLmjAV4JtdB2qFY9GxhysajFufATdy8fjGTE,16316
 ml_tools/_core/_ML_sequence_models.py,sha256=5qcEYLU6wDePBITnikBrj_H9mCvyJmElKa3HiWGXhZs,5639
-ml_tools/_core/_ML_trainer.py,sha256=EeNqZ0pCWrBxGaYgOVmDxofMBQhV56Bvsj-VuBwBgHQ,117580
+ml_tools/_core/_ML_trainer.py,sha256=ZYDH-P8GJhFe0vpeMtgLS0O3Fz0d4qr8zcTm-C30T1I,117595
 ml_tools/_core/_ML_utilities.py,sha256=elLGD0QYh148_9iNLlqGe1vz-wCFspJa6CWtWTfA3jY,35594
 ml_tools/_core/_ML_vision_datasetmaster.py,sha256=8EsE7luzphVlwBXdOsOwsFfz1D4UIUSEQtqHlM0Vf-o,67084
 ml_tools/_core/_ML_vision_evaluation.py,sha256=BSLf9xrGpaR02Dhkf-fAbgxSpwRjf7DruNIcQadl7qg,11631
@@ -88,7 +88,7 @@ ml_tools/_core/_PSO_optimization.py,sha256=W3g5xw2v2eOUQadv8KHFkt5HNm9AiY3ZUk-Te
 ml_tools/_core/_SQL.py,sha256=zX_8EgYfmLmvvrnL851KMkI4w9kdkjHJ997BTvS5aig,11556
 ml_tools/_core/_VIF_factor.py,sha256=BM0mTowBqt45PXFy9oJLhT9C-CTWWo0TQhgCyWYLHtQ,10457
 ml_tools/_core/__init__.py,sha256=d4IG0OxUXj2HffepzQcYixHlZeuuuDMAFa09H_6LtmU,12
-ml_tools/_core/_data_exploration.py,sha256=-g_e4Lox4LN8c2AfhpcPmnI9TNIZGl84O8hWEVH5asA,77438
+ml_tools/_core/_data_exploration.py,sha256=uynIjMppbr5nFJ-7wag0R0HDQCp2rTXqz_IpgNKKNOM,77508
 ml_tools/_core/_ensemble_evaluation.py,sha256=17lWl4bWLT1BAMv_fhGf2D3wy-F4jx0HgnJ79lYkRuE,28419
 ml_tools/_core/_ensemble_inference.py,sha256=9UpARSETzmqPdQmxqizD768tjkqldxHw1ER_hM9Kx9M,8631
 ml_tools/_core/_ensemble_learning.py,sha256=X8ghbjDOLMENCWdISXLhDlHQtR3C6SW1tkTBAcfRRPY,22016
@@ -104,8 +104,8 @@ ml_tools/_core/_plot_fonts.py,sha256=CjYXW2gZ9AUaGkyX8_WOXXNYs6d1PTK-nEJBrv_Zb2o
 ml_tools/_core/_schema.py,sha256=TM5WVVMoKOvr_Bc2z34sU_gzKlM465PRKTgdZaEOkGY,14076
 ml_tools/_core/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/_core/_serde.py,sha256=tsI4EO2Y7jrBMmbQ1pinDsPOrOg-SaPuB-Dt40q0taE,5609
-ml_tools/_core/_utilities.py,sha256=D7FGyEszcMHxGkMW4aqN7JUwabTICCcQz9qsGtOj97o,22787
-dragon_ml_toolbox-19.12.0.dist-info/METADATA,sha256=MoUoxvRMHfPhedd87f68yWWlPJFEGVFCOa1OpgKwpHE,8193
-dragon_ml_toolbox-19.12.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-19.12.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-19.12.0.dist-info/RECORD,,
+ml_tools/_core/_utilities.py,sha256=oU-0hBipE96bXox66NG-hFuEMMNkKa9MkAy1yJGCSIA,22779
+dragon_ml_toolbox-19.12.2.dist-info/METADATA,sha256=Nuk7YVRdDotD_TURCpIFKqcDuTlkBs9fpTv-8jCm5aU,8193
+dragon_ml_toolbox-19.12.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-19.12.2.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-19.12.2.dist-info/RECORD,,

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()

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():

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]:

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.

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:
     """

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)

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",
 ]