dragon-ml-toolbox 19.10.0__py3-none-any.whl → 19.11.0__py3-none-any.whl

{dragon_ml_toolbox-19.10.0.dist-info → dragon_ml_toolbox-19.11.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 19.10.0
+Version: 19.11.0
 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-19.10.0.dist-info → dragon_ml_toolbox-19.11.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-19.10.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-19.10.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
+dragon_ml_toolbox-19.11.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-19.11.0.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
@@ -55,7 +55,7 @@ ml_tools/_core/_ETL_cleaning.py,sha256=_pTNKuapNHgWErmxvsXW-2YzCm4BaTshKV627A38R
 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/_MICE_imputation.py,sha256=_juIymUnNDRWjSLepL8Ee_PncoShbxjR7YtqTtYbteU,21107
+ml_tools/_core/_MICE_imputation.py,sha256=64l20duGWt93Q2MbqcWqrA1s99JPRf5AJACb1CZi2xI,21149
 ml_tools/_core/_ML_callbacks.py,sha256=qtCrVFHTq-nk4NIsAdwIkfkKwFXX6I-6PoCgqZELp70,16734
 ml_tools/_core/_ML_chaining_inference.py,sha256=vXUPZzuQ2yKU71kkvUsE0xPo0hN-Yu6gfnL0JbXoRjI,7783
 ml_tools/_core/_ML_chaining_utilities.py,sha256=nsYowgRbkIYuzRiHlqsM3tnC3c-8O73CY8DHUF14XL0,19248
@@ -78,19 +78,19 @@ ml_tools/_core/_ML_sequence_evaluation.py,sha256=AiPHtZ9DRpE6zL9n3Tp5eGGD9vrYRkL
 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=hSsudWrlYWpi53DXIlKI6ovVhz7xLrQ8oKIDJOXf4Eg,117747
-ml_tools/_core/_ML_utilities.py,sha256=yXVKow-bgpahMChpp7iUlSxAEtgityXwC54FPReeNNA,30487
+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
 ml_tools/_core/_ML_vision_inference.py,sha256=6K9gMFjAAZKfLAIQlOkm_I9hvCPmO--9-1vnskQRk0I,20190
 ml_tools/_core/_ML_vision_models.py,sha256=oUik-RLxFvZFZCtFztjkSfFYgJuRx4QzfwHVY1ny4Sc,26217
 ml_tools/_core/_ML_vision_transformers.py,sha256=imjL9h5kwpfuRn9rBelNpgtrdU-EecBEcHMFZMXTeZA,15303
-ml_tools/_core/_PSO_optimization.py,sha256=Dg76d7t2ixPCXqQ-KceG9nzuLajHGN0s5RiawRGzsT4,22970
+ml_tools/_core/_PSO_optimization.py,sha256=W3g5xw2v2eOUQadv8KHFkt5HNm9AiY3ZUk-TeyVuZjw,22991
 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/_ensemble_evaluation.py,sha256=17lWl4bWLT1BAMv_fhGf2D3wy-F4jx0HgnJ79lYkRuE,28419
-ml_tools/_core/_ensemble_inference.py,sha256=PfZG-r65Vw3IAmBJZg9W0zYGEe-QbhfUh_rd2ho-rr8,8610
+ml_tools/_core/_ensemble_inference.py,sha256=9UpARSETzmqPdQmxqizD768tjkqldxHw1ER_hM9Kx9M,8631
 ml_tools/_core/_ensemble_learning.py,sha256=X8ghbjDOLMENCWdISXLhDlHQtR3C6SW1tkTBAcfRRPY,22016
 ml_tools/_core/_excel_handler.py,sha256=gV4rSIsiowb0xllpEJxzUKaYDDVpmP_lxs9wZA76-cc,14050
 ml_tools/_core/_keys.py,sha256=pOqxhEFcDuAeuQveJNykdQfB6gVEg8ZY7L7MYQmtY_o,7551
@@ -98,14 +98,14 @@ ml_tools/_core/_logger.py,sha256=86Ge0sDE_WgwsZBglQRYPyFYX3lcsIo0NzszNPzlxuk,525
 ml_tools/_core/_math_utilities.py,sha256=IlXAiZgTcLtus03jJOBOyF9ZCQDf8qLGjrCHu9Mrgak,9091
 ml_tools/_core/_models_advanced_base.py,sha256=ceW0V_CcfOnSFqHlxUhVU8-5mtQq4tFyo8TX-xVexrY,4982
 ml_tools/_core/_models_advanced_helpers.py,sha256=yrAVgYdBsNYD6Vy-pYL5__wI9Z7inOvNUngMgyuypjo,38973
-ml_tools/_core/_optimization_tools.py,sha256=2LkntNRc19uGur9u0yI-KnNX56tc63sxaRNj6W440Og,20077
-ml_tools/_core/_path_manager.py,sha256=z4zqYqppKhgOj3ArfkKo4tieO8oNaHWUoshCQRNbd1w,20284
+ml_tools/_core/_optimization_tools.py,sha256=WdQkkknbErk4p1cCj2l5CLImK2oRAzhmR3QFR50Hbzk,20098
+ml_tools/_core/_path_manager.py,sha256=-gJ5qoEzpXsQT7gfxV_6kA7mk33iDsMXRmtOoVPl1JA,20845
 ml_tools/_core/_plot_fonts.py,sha256=CjYXW2gZ9AUaGkyX8_WOXXNYs6d1PTK-nEJBrv_Zb2o,2287
 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=iA8fLWdhsIx4ut2Dp8M_OyU0Y3PPLgGdIklyl17x6xk,22560
-dragon_ml_toolbox-19.10.0.dist-info/METADATA,sha256=HNycos2k-C6KCjfj1g1pprR6APPYcst7HkoKylfgeR8,8193
-dragon_ml_toolbox-19.10.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-19.10.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-19.10.0.dist-info/RECORD,,
+ml_tools/_core/_utilities.py,sha256=D7FGyEszcMHxGkMW4aqN7JUwabTICCcQz9qsGtOj97o,22787
+dragon_ml_toolbox-19.11.0.dist-info/METADATA,sha256=HUeAsHLQTdaopzM0YVyRgaofMaHXoOZUan456E5M1JU,8193
+dragon_ml_toolbox-19.11.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-19.11.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-19.11.0.dist-info/RECORD,,

ml_tools/_core/_MICE_imputation.py

@@ -256,7 +256,7 @@ def run_mice_pipeline(df_path_or_dir: Union[str,Path], target_columns: list[str]
     if input_path.is_file():
         all_file_paths = [input_path]
     else:
-        all_file_paths = list(list_csv_paths(input_path).values())
+        all_file_paths = list(list_csv_paths(input_path, raise_on_empty=True).values())
     
     for df_path in all_file_paths:
         df: pd.DataFrame
@@ -461,7 +461,7 @@ class DragonMICE:
         if input_path.is_file():
             all_file_paths = [input_path]
         else:
-            all_file_paths = list(list_csv_paths(input_path).values())
+            all_file_paths = list(list_csv_paths(input_path, raise_on_empty=True).values())
         
         for df_path in all_file_paths:
             

ml_tools/_core/_ML_utilities.py

@@ -46,17 +46,24 @@ class ArtifactFinder:
         └── FeatureSchema.json     (Required if `load_schema` is True)
     ```
     """
-    def __init__(self, directory: Union[str, Path], load_scaler: bool, load_schema: bool) -> None:
+    def __init__(self, 
+                 directory: Union[str, Path], 
+                 load_scaler: bool, 
+                 load_schema: bool,
+                 strict: bool=False,
+                 verbose: bool=True) -> None:
         """
         Args:
             directory (str | Path): The path to the directory that contains training artifacts.
             load_scaler (bool): If True, requires and searches for a scaler file `scaler_*.pth`.
             load_schema (bool): If True, requires and searches for a FeatureSchema file `FeatureSchema.json`.
+            strict (bool): If True, raises an error if any artifact is missing. If False, returns None for missing artifacts silently.
+            verbose (bool): Displays the missing artifacts in the directory or a success message.
         """
         # validate directory
         dir_path = make_fullpath(directory, enforce="directory")
         
-        parsing_dict = _find_model_artifacts(target_directory=dir_path, load_scaler=load_scaler, verbose=False)
+        parsing_dict = _find_model_artifacts(target_directory=dir_path, load_scaler=load_scaler, verbose=False, strict=strict)
         
         self._weights_path = parsing_dict[PytorchArtifactPathKeys.WEIGHTS_PATH]
         self._feature_names_path = parsing_dict[PytorchArtifactPathKeys.FEATURES_PATH]
@@ -64,71 +71,121 @@ class ArtifactFinder:
         self._model_architecture_path = parsing_dict[PytorchArtifactPathKeys.ARCHITECTURE_PATH]
         self._scaler_path = None
         self._schema = None
+        self._strict = strict
         
         if load_scaler:
             self._scaler_path = parsing_dict[PytorchArtifactPathKeys.SCALER_PATH]
             
         if load_schema:
-            self._schema = FeatureSchema.from_json(directory=dir_path)
+            try:
+                self._schema = FeatureSchema.from_json(directory=dir_path)
+            except Exception:
+                if strict:
+                    # FeatureSchema logs its own error details
+                    # _LOGGER.error(f"Failed to load FeatureSchema from '{dir_path.name}': {e}")
+                    raise FileNotFoundError()
+                else:
+                    # _LOGGER.warning(f"Could not load FeatureSchema from '{dir_path.name}': {e}")
+                    self._schema = None
+
+        # Process feature names
+        if self._feature_names_path is not None:
+            self._feature_names = self._process_text(self._feature_names_path)
+        else:
+            self._feature_names = None
+        # Process target names
+        if self._target_names_path is not None:
+            self._target_names = self._process_text(self._target_names_path)
+        else:
+            self._target_names = None
+            
+        if verbose:
+            # log missing artifacts
+            missing_artifacts = []
+            if self._feature_names is None:
+                missing_artifacts.append("Feature Names")
+            if self._target_names is None:
+                missing_artifacts.append("Target Names")
+            if self._weights_path is None:
+                missing_artifacts.append("Weights File")
+            if self._model_architecture_path is None:
+                missing_artifacts.append("Model Architecture File")
+            if load_scaler and self._scaler_path is None:
+                missing_artifacts.append("Scaler File")
+            if load_schema and self._schema is None:
+                missing_artifacts.append("FeatureSchema File")
+            
+            if missing_artifacts:
+                _LOGGER.warning(f"Missing artifacts in '{dir_path.name}': {', '.join(missing_artifacts)}.")
+            else:
+                _LOGGER.info(f"All artifacts successfully loaded from '{dir_path.name}'.")
 
-        # Process text files
-        self._feature_names = self._process_text(self._feature_names_path)
-        self._target_names = self._process_text(self._target_names_path)
-        
     def _process_text(self, text_file_path: Path):
         list_strings = load_list_strings(text_file=text_file_path, verbose=False)
         return list_strings
     
     @property
-    def feature_names(self) -> list[str]:
+    def feature_names(self) -> Union[list[str], None]:
         """Returns the feature names as a list of strings."""
+        if self._strict and not self._feature_names:
+            _LOGGER.error("No feature names loaded for Strict mode.")
+            raise ValueError()
         return self._feature_names
     
     @property
-    def target_names(self) -> list[str]:
+    def target_names(self) -> Union[list[str], None]:
         """Returns the target names as a list of strings."""
+        if self._strict and not self._target_names:
+            _LOGGER.error("No target names loaded for Strict mode.")
+            raise ValueError()
         return self._target_names
     
     @property
-    def weights_path(self) -> Path:
+    def weights_path(self) -> Union[Path, None]:
         """Returns the path to the state dictionary pth file."""
+        if self._strict and self._weights_path is None:
+            _LOGGER.error("No weights file loaded for Strict mode.")
+            raise ValueError()
         return self._weights_path
     
     @property
-    def model_architecture_path(self) -> Path:
+    def model_architecture_path(self) -> Union[Path, None]:
         """Returns the path to the model architecture json file."""
+        if self._strict and self._model_architecture_path is None:
+            _LOGGER.error("No model architecture file loaded for Strict mode.")
+            raise ValueError()
         return self._model_architecture_path
     
     @property
-    def scaler_path(self) -> Path:
+    def scaler_path(self) -> Union[Path, None]:
         """Returns the path to the scaler file."""
-        if self._scaler_path is None:
-            _LOGGER.error("No scaler file loaded. Set 'load_scaler=True'.")
+        if self._strict and self._scaler_path is None:
+            _LOGGER.error("No scaler file loaded for Strict mode.")
             raise ValueError()
         else:
             return self._scaler_path
         
     @property
-    def feature_schema(self) -> FeatureSchema:
+    def feature_schema(self) -> Union[FeatureSchema, None]:
         """Returns the FeatureSchema object."""
-        if self._schema is None:
-            _LOGGER.error("No FeatureSchema loaded. Set 'load_schema=True'.")
+        if self._strict and self._schema is None:
+            _LOGGER.error("No FeatureSchema loaded for Strict mode.")
             raise ValueError()
         else:
             return self._schema
         
     def __repr__(self) -> str:
-        dir_name = self._weights_path.parent.name
-        n_features = len(self._feature_names)
-        n_targets = len(self._target_names)
+        dir_name = self._weights_path.parent.name if self._weights_path else "Unknown"
+        n_features = len(self._feature_names) if self._feature_names else "None"
+        n_targets = len(self._target_names) if self._target_names else "None"
         scaler_status = self._scaler_path.name if self._scaler_path else "None"
         schema_status = "Loaded" if self._schema else "None"
         
         return (
             f"{self.__class__.__name__}\n"
             f"    directory='{dir_name}'\n"
-            f"    weights='{self._weights_path.name}'\n"
-            f"    architecture='{self._model_architecture_path.name}'\n"
+            f"    weights='{self._weights_path.name if self._weights_path else 'None'}'\n"
+            f"    architecture='{self._model_architecture_path.name if self._model_architecture_path else 'None'}'\n"
             f"    scaler='{scaler_status}'\n"
             f"    schema='{schema_status}'\n"
             f"    features={n_features}\n" 
@@ -136,7 +193,7 @@ class ArtifactFinder:
         )
 
 
-def _find_model_artifacts(target_directory: Union[str,Path], load_scaler: bool, verbose: bool=False) -> dict[str, Path]:
+def _find_model_artifacts(target_directory: Union[str,Path], load_scaler: bool, verbose: bool=True, strict:bool=True) -> dict[str, Union[Path, None]]:
     """
     Scans a directory to find paths to model weights, target names, feature names, and model architecture. Optionally an scaler path if `load_scaler` is True.
     
@@ -155,41 +212,70 @@ def _find_model_artifacts(target_directory: Union[str,Path], load_scaler: bool,
         target_directory (str | Path): The path to the directory that contains training artifacts.
         load_scaler (bool): If True, the function requires and searches for a scaler file `scaler_*.pth`.
         verbose (bool): If True, enables detailed logging during the search process.
+        strict (bool): If True, raises errors on missing files. If False, returns None for missing files.
     """
     # validate directory
     dir_path = make_fullpath(target_directory, enforce="directory")
     dir_name = dir_path.name
     
     # find files
-    model_pth_dict = list_files_by_extension(directory=dir_path, extension="pth", verbose=verbose)
+    model_pth_dict = list_files_by_extension(directory=dir_path, extension="pth", verbose=False, raise_on_empty=False)
     
-    # restriction
-    if load_scaler:
-        if len(model_pth_dict) != 2:
-            _LOGGER.error(f"Directory '{dir_name}' should contain exactly 2 '.pth' files: scaler and weights.")
-            raise IOError()
-    else:
-        if len(model_pth_dict) != 1:
-            _LOGGER.error(f"Directory '{dir_name}' should contain exactly 1 '.pth' file for weights.")
+    if not model_pth_dict:
+        pth_msg=f"No '.pth' files found in directory: {dir_name}."
+        if strict:
+            _LOGGER.error(pth_msg)
             raise IOError()
+        else:
+            if verbose:
+                _LOGGER.warning(pth_msg)
+            model_pth_dict = None
+    
+    # restriction
+    if model_pth_dict is not None:
+        valid_count = False
+        msg = ""
+        
+        if load_scaler:
+            if len(model_pth_dict) == 2:
+                valid_count = True
+            else:
+                msg = f"Directory '{dir_name}' should contain exactly 2 '.pth' files: scaler and weights. Found {len(model_pth_dict)}."
+        else:
+            if len(model_pth_dict) == 1:
+                valid_count = True
+            else:
+                msg = f"Directory '{dir_name}' should contain exactly 1 '.pth' file for weights. Found {len(model_pth_dict)}."
+        
+        # Respect strict mode for count mismatch
+        if not valid_count:
+            if strict:
+                _LOGGER.error(msg)
+                raise IOError()
+            else:
+                if verbose:
+                    _LOGGER.warning(msg)
+                # Invalidate dictionary
+                model_pth_dict = None
     
     ##### Scaler and Weights #####
     scaler_path = None
     weights_path = None
     
     # load weights and scaler if present
-    for pth_filename, pth_path in model_pth_dict.items():
-        if load_scaler and pth_filename.lower().startswith(DatasetKeys.SCALER_PREFIX):
-            scaler_path = pth_path
-        else:
-            weights_path = pth_path
+    if model_pth_dict is not None:
+        for pth_filename, pth_path in model_pth_dict.items():
+            if load_scaler and pth_filename.lower().startswith(DatasetKeys.SCALER_PREFIX):
+                scaler_path = pth_path
+            else:
+                weights_path = pth_path
     
     # validation
-    if not weights_path:
+    if not weights_path and strict:
         _LOGGER.error(f"Error parsing the model weights path from '{dir_name}'")
         raise IOError()
     
-    if load_scaler and not scaler_path:
+    if strict and load_scaler and not scaler_path:
         _LOGGER.error(f"Error parsing the scaler path from '{dir_name}'")
         raise IOError()
     
@@ -198,32 +284,44 @@ def _find_model_artifacts(target_directory: Union[str,Path], load_scaler: bool,
     feature_names_path = None
     
     # load feature and target names
-    model_txt_dict = list_files_by_extension(directory=dir_path, extension="txt", verbose=verbose)
+    model_txt_dict = list_files_by_extension(directory=dir_path, extension="txt", verbose=False, raise_on_empty=False)
     
+    # if the directory has no txt files, the loop is skipped
     for txt_filename, txt_path in model_txt_dict.items():
         if txt_filename == DatasetKeys.FEATURE_NAMES:
             feature_names_path = txt_path
         elif txt_filename == DatasetKeys.TARGET_NAMES:
             target_names_path = txt_path
     
-    # validation
-    if not target_names_path or not feature_names_path:
-        _LOGGER.error(f"Error parsing features path or targets path from '{dir_name}'")
+    # validation per case
+    if strict and not target_names_path:
+        _LOGGER.error(f"Error parsing the target names path from '{dir_name}'")
         raise IOError()
+    elif verbose and not target_names_path:
+        _LOGGER.warning(f"Target names file not found in '{dir_name}'.")
     
+    if strict and not feature_names_path:
+        _LOGGER.error(f"Error parsing the feature names path from '{dir_name}'")
+        raise IOError()
+    elif verbose and not feature_names_path:
+        _LOGGER.warning(f"Feature names file not found in '{dir_name}'.")
+
     ##### load model architecture path #####
     architecture_path = None
     
-    model_json_dict = list_files_by_extension(directory=dir_path, extension="json", verbose=verbose)
+    model_json_dict = list_files_by_extension(directory=dir_path, extension="json", verbose=False, raise_on_empty=False)
     
+    # if the directory has no json files, the loop is skipped
     for json_filename, json_path in model_json_dict.items():
         if json_filename == PytorchModelArchitectureKeys.SAVENAME:
             architecture_path = json_path
     
     # validation
-    if not architecture_path:
+    if strict and not architecture_path:
         _LOGGER.error(f"Error parsing the model architecture path from '{dir_name}'")
         raise IOError()
+    elif verbose and not architecture_path:
+        _LOGGER.warning(f"Model architecture file not found in '{dir_name}'.")
     
     ##### Paths dictionary #####
     parsing_dict = {
@@ -233,7 +331,7 @@ def _find_model_artifacts(target_directory: Union[str,Path], load_scaler: bool,
         PytorchArtifactPathKeys.TARGETS_PATH: target_names_path,
     }
     
-    if scaler_path is not None:
+    if load_scaler:
         parsing_dict[PytorchArtifactPathKeys.SCALER_PATH] = scaler_path
     
     return parsing_dict
@@ -246,6 +344,9 @@ def find_model_artifacts_multi(target_directory: Union[str,Path], load_scaler: b
     This function operates on a specific directory structure. It expects the
     `target_directory` to contain one or more subdirectories, where each
     subdirectory represents a single trained model result.
+    
+    This function works using a strict mode, meaning that it will raise errors if
+    any required artifacts are missing in a model's subdirectory.
 
     The expected directory structure for each model is as follows:
     ```
@@ -278,14 +379,16 @@ def find_model_artifacts_multi(target_directory: Union[str,Path], load_scaler: b
     all_artifacts: list[dict[str, Path]] = list()
     
     # find model directories
-    result_dirs_dict = list_subdirectories(root_dir=root_path, verbose=verbose)
+    result_dirs_dict = list_subdirectories(root_dir=root_path, verbose=verbose, raise_on_empty=True)
     for _dir_name, dir_path in result_dirs_dict.items():
         
         parsing_dict = _find_model_artifacts(target_directory=dir_path,
                                             load_scaler=load_scaler,
-                                            verbose=verbose)
+                                            verbose=verbose,
+                                            strict=True)
         
-        all_artifacts.append(parsing_dict)
+        # parsing_dict is guaranteed to have all required paths due to strict=True
+        all_artifacts.append(parsing_dict)  # type: ignore
     
     return all_artifacts
 
@@ -721,7 +824,7 @@ def select_features_by_shap(
     root_path = make_fullpath(root_directory, enforce="directory")
 
     # --- Step 2: Directory and File Discovery ---
-    subdirectories = list_subdirectories(root_dir=root_path, verbose=False)
+    subdirectories = list_subdirectories(root_dir=root_path, verbose=False, raise_on_empty=True)
     
     shap_filename = SHAPKeys.SAVENAME + ".csv"
 

ml_tools/_core/_PSO_optimization.py

@@ -169,7 +169,7 @@ def multiple_objective_functions_from_dir(directory: Union[str,Path], add_noise:
     """
     objective_functions = list()
     objective_function_names = list()
-    for file_name, file_path in list_files_by_extension(directory=directory, extension='joblib').items():
+    for file_name, file_path in list_files_by_extension(directory=directory, extension='joblib', raise_on_empty=True).items():
         current_objective = ObjectiveFunction(trained_model_path=file_path,
                                               add_noise=add_noise,
                                               task=task,

ml_tools/_core/_ensemble_inference.py

@@ -42,7 +42,7 @@ class DragonEnsembleInferenceHandler:
         self.verbose = verbose
         self._feature_names: Optional[List[str]] = None
         
-        model_files = list_files_by_extension(directory=models_dir, extension="joblib")
+        model_files = list_files_by_extension(directory=models_dir, extension="joblib", raise_on_empty=True)
         
         for fname, fpath in model_files.items():
             try:

ml_tools/_core/_optimization_tools.py

@@ -269,7 +269,7 @@ def plot_optimal_feature_distributions(results_dir: Union[str, Path],
     output_path = make_fullpath(results_path / "DistributionPlots", make=True)
     
     # Check that the directory contains csv files
-    list_csv_paths(results_path, verbose=False)
+    list_csv_paths(results_path, verbose=False, raise_on_empty=True)
 
     # --- Data Loading and Preparation ---
     _LOGGER.debug(f"📁 Starting analysis from results in: '{results_dir}'")

ml_tools/_core/_path_manager.py

@@ -436,35 +436,28 @@ def sanitize_filename(filename: str) -> str:
     return sanitized
 
 
-def list_csv_paths(directory: Union[str,Path], verbose: bool=True) -> dict[str, Path]:
+def list_csv_paths(directory: Union[str, Path], verbose: bool = True, raise_on_empty: bool = True) -> dict[str, Path]:
     """
     Lists all `.csv` files in the specified directory and returns a mapping: filenames (without extensions) to their absolute paths.
 
     Parameters:
         directory (str | Path): Path to the directory containing `.csv` files.
+        verbose (bool): If True, prints found files.
+        raise_on_empty (bool): If True, raises IOError if no files are found.
 
     Returns:
         (dict[str, Path]): Dictionary mapping {filename: filepath}.
     """
-    dir_path = make_fullpath(directory)
+    # wraps the more general function
+    return list_files_by_extension(directory=directory, extension="csv", verbose=verbose, raise_on_empty=raise_on_empty)
 
-    csv_paths = list(dir_path.glob("*.csv"))
-    if not csv_paths:
-        _LOGGER.error(f"No CSV files found in directory: {dir_path.name}")
-        raise IOError()
-    
-    # make a dictionary of paths and names
-    name_path_dict = {p.stem: p for p in csv_paths}
-    
-    if verbose:
-        _LOGGER.info("🗂️ CSV files found:")
-        for name in name_path_dict.keys():
-            print(f"\t{name}")
 
-    return name_path_dict
-
-
-def list_files_by_extension(directory: Union[str,Path], extension: str, verbose: bool=True) -> dict[str, Path]:
+def list_files_by_extension(
+    directory: Union[str, Path], 
+    extension: str, 
+    verbose: bool = True,
+    raise_on_empty: bool = True
+) -> dict[str, Path]:
     """
     Lists all files with the specified extension in the given directory and returns a mapping: 
     filenames (without extensions) to their absolute paths.
@@ -472,20 +465,29 @@ def list_files_by_extension(directory: Union[str,Path], extension: str, verbose:
     Parameters:
         directory (str | Path): Path to the directory to search in.
         extension (str): File extension to search for (e.g., 'json', 'txt').
+        verbose (bool): If True, logs the files found.
+        raise_on_empty (bool): If True, raises IOError if no matching files are found.
 
     Returns:
-        (dict[str, Path]): Dictionary mapping {filename: filepath}.
+        (dict[str, Path]): Dictionary mapping {filename: filepath}. Returns empty dict if none found and raise_on_empty is False.
     """
-    dir_path = make_fullpath(directory)
+    dir_path = make_fullpath(directory, enforce="directory")
     
     # Normalize the extension (remove leading dot if present)
     normalized_ext = extension.lstrip(".").lower()
     pattern = f"*.{normalized_ext}"
     
     matched_paths = list(dir_path.glob(pattern))
+    
     if not matched_paths:
-        _LOGGER.error(f"No '.{normalized_ext}' files found in directory: {dir_path}.")
-        raise IOError()
+        msg = f"No '.{normalized_ext}' files found in directory: {dir_path}."
+        if raise_on_empty:
+            _LOGGER.error(msg)
+            raise IOError()
+        else:
+            if verbose:
+                _LOGGER.warning(msg)
+            return {}
 
     name_path_dict = {p.stem: p for p in matched_paths}
     
@@ -497,13 +499,18 @@ def list_files_by_extension(directory: Union[str,Path], extension: str, verbose:
     return name_path_dict
 
 
-def list_subdirectories(root_dir: Union[str,Path], verbose: bool=True) -> dict[str, Path]:
+def list_subdirectories(
+    root_dir: Union[str, Path], 
+    verbose: bool = True, 
+    raise_on_empty: bool = True
+) -> dict[str, Path]:
     """
     Scans a directory and returns a dictionary of its immediate subdirectories.
 
     Args:
         root_dir (str | Path): The path to the directory to scan.
         verbose (bool): If True, prints the number of directories found. 
+        raise_on_empty (bool): If True, raises IOError if no subdirectories are found.
 
     Returns:
         dict[str, Path]: A dictionary mapping subdirectory names (str) to their full Path objects.
@@ -513,8 +520,14 @@ def list_subdirectories(root_dir: Union[str,Path], verbose: bool=True) -> dict[s
     directories = [p.resolve() for p in root_path.iterdir() if p.is_dir()]
     
     if len(directories) < 1:
-        _LOGGER.error(f"No subdirectories found inside '{root_path}'")
-        raise IOError()
+        msg = f"No subdirectories found inside '{root_path}'"
+        if raise_on_empty:
+            _LOGGER.error(msg)
+            raise IOError()
+        else:
+            if verbose:
+                _LOGGER.warning(msg)
+            return {}
     
     if verbose:
         count = len(directories)

ml_tools/_core/_utilities.py

@@ -166,8 +166,12 @@ def load_dataframe_greedy(directory: Union[str, Path],
     dir_path = make_fullpath(directory, enforce="directory")
     
     # list all csv files and grab one (should be the only one)
-    csv_dict = list_csv_paths(directory=dir_path, verbose=False)
+    csv_dict = list_csv_paths(directory=dir_path, verbose=False, raise_on_empty=True)
     
+    # explicitly check that there is only one csv file
+    if len(csv_dict) > 1:
+        _LOGGER.warning(f"Multiple CSV files found in '{dir_path}'. Only one will be loaded.")
+        
     for df_path in csv_dict.values():
         df , _df_name = load_dataframe(df_path=df_path,
                                     use_columns=use_columns,
@@ -260,7 +264,7 @@ def yield_dataframes_from_dir(datasets_dir: Union[str,Path], verbose: bool=True)
     - Output is streamed via a generator to support lazy loading of multiple datasets.
     """
     datasets_path = make_fullpath(datasets_dir)
-    files_dict = list_csv_paths(datasets_path, verbose=verbose)
+    files_dict = list_csv_paths(datasets_path, verbose=verbose, raise_on_empty=True)
     for df_name, df_path in files_dict.items():
         df: pd.DataFrame
         df, _ = load_dataframe(df_path, kind="pandas", verbose=verbose) # type: ignore