dragon-ml-toolbox 10.8.0__py3-none-any.whl → 10.9.0__py3-none-any.whl

{dragon_ml_toolbox-10.8.0.dist-info → dragon_ml_toolbox-10.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.8.0
+Version: 10.9.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-10.8.0.dist-info → dragon_ml_toolbox-10.9.0.dist-info}/RECORD

@@ -1,12 +1,12 @@
-dragon_ml_toolbox-10.8.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-10.8.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+dragon_ml_toolbox-10.9.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-10.9.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
 ml_tools/ETL_cleaning.py,sha256=lSP5q6-ukGhJBPV8dlsqJvPXAzj4du_0J-SbtEd0Pjg,19292
 ml_tools/ETL_engineering.py,sha256=a6KCWH6kRatZtjaFEF_o917ApPMK5_vRD-BjfCDAl-E,49400
 ml_tools/GUI_tools.py,sha256=kEQWg-bog3pB5tI22gMGKWaCGHnz9TB2Lvvfhf5F2CI,45412
 ml_tools/MICE_imputation.py,sha256=kVSythWfxJFR4-2mtcYCWQaQ1Oz5yyx_SJu5gjnS7H8,11670
 ml_tools/ML_callbacks.py,sha256=JPvEw_cW5tYNJ2rMSgnNrKLuni_UrmuhDFaOw-u2SvA,13926
 ml_tools/ML_datasetmaster.py,sha256=BMmdCVAZ-HSnnSPLzKla2TdZKvHkHj4t9A0V1Ba3i-I,30821
-ml_tools/ML_evaluation.py,sha256=28JJ2M71p4pxniwav2Hv3b1a5dsvaoIYNLm-UJQuXvY,16002
+ml_tools/ML_evaluation.py,sha256=q4_RsBjmidc_yDX-DQvpJW8RCHrOCJbgXKBORQdt-TM,16111
 ml_tools/ML_evaluation_multi.py,sha256=2jTSNFCu8cz5C05EusnrDyffs59M2Fq3UXSHxo2TR1A,12515
 ml_tools/ML_inference.py,sha256=SGDPiPxs_OYDKKRZziFMyaWcC8A37c70W9t-dMP5niI,23066
 ml_tools/ML_models.py,sha256=FliuqGhxP7AWHCweTLlfssXFOjwvFhIYJsgj_w_-EI4,27901
@@ -15,22 +15,22 @@ ml_tools/ML_scaler.py,sha256=IrZsAr1xjvuLi8s5IKR-qbk2mS_awl3mn_xoXg5TJyA,7535
 ml_tools/ML_trainer.py,sha256=xw1zMgYpdqwsTt604xe3GTQNvpg6z6Ze-avmitGBFeU,23539
 ml_tools/PSO_optimization.py,sha256=q0VYpssQGbPum7xdnkDXlJQKhZMYZo8acHpKhajPK3c,22954
 ml_tools/RNN_forecast.py,sha256=8rNZr-eWOBXMiDQV22e_tQTPM5LM2IFggEAa1FaoXaI,1965
-ml_tools/SQL.py,sha256=WDgdZUYuLBUpv-4Am9XjVY_Aq_jxBWdLrbcgAIEwefI,10704
+ml_tools/SQL.py,sha256=givoz6CGWRUdqnBem3VGZxzGdo3ZbX00kyHNjzI8kWE,10803
 ml_tools/VIF_factor.py,sha256=MkMh_RIdsN2XUPzKNGRiEcmB17R_MmvGV4ezpL5zD2E,10403
 ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
 ml_tools/_logger.py,sha256=wcImAiXEZKPNcwM30qBh3t7HvoPURonJY0nrgMGF0sM,4719
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/custom_logger.py,sha256=ry43hk54K6xKo8jRAgq1sFxUpOA9T0LIJ7sw0so2BW0,5880
 ml_tools/data_exploration.py,sha256=4McT2BR9muK4JVVTKUfvRyThe0m_o2vpy9RJ1f_1FeY,28692
-ml_tools/ensemble_evaluation.py,sha256=xMEMfXJ5MjTkTfr1LkFOeD7iUtnVDCW3S9lm3zT-6tY,24778
+ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
 ml_tools/ensemble_inference.py,sha256=EFHnbjbu31fcVp88NBx8lWAVdu2Gpg9MY9huVZJHFfM,9350
 ml_tools/ensemble_learning.py,sha256=3s0kH4i_naj0IVl_T4knst-Hwg4TScWjEdsXX5KAi7I,21929
 ml_tools/handle_excel.py,sha256=He4UT15sCGhaG-JKfs7uYVAubxWjrqgJ6U7OhMR2fuE,14005
-ml_tools/keys.py,sha256=sZANLHvp_93pPigviMOz7AhampGlpokcop_llzsjWBw,1689
+ml_tools/keys.py,sha256=FDpbS3Jb0pjrVvvp2_8nZi919mbob_-xwuy5OOtKM_A,1848
 ml_tools/optimization_tools.py,sha256=P3I6lIpvZ8Xf2kX5FvvBKBmrK2pB6idBpkTzfUJxTeE,5073
 ml_tools/path_manager.py,sha256=wLJlz3Y9_1-LB9em4B2VYDCVuTOX2eOc7D6hbbebjgM,14990
-ml_tools/utilities.py,sha256=xddY0uASKQWSuUsYJEcfDUkeC-ccbYlkycqHKdkPnhk,25105
-dragon_ml_toolbox-10.8.0.dist-info/METADATA,sha256=Ly11G7vOgCFbYwEYXQXa8RBgvWof9thiBxVjlk9DZu4,6968
-dragon_ml_toolbox-10.8.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-10.8.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-10.8.0.dist-info/RECORD,,
+ml_tools/utilities.py,sha256=30z0x1aDLyBGzF98_tgSaxwFafYwQS-GTFzXHopBSGc,29105
+dragon_ml_toolbox-10.9.0.dist-info/METADATA,sha256=NK8z4StYOVR0ByF_l-vNjyrFgbb2qddBa6lOzlQsZrg,6968
+dragon_ml_toolbox-10.9.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-10.9.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-10.9.0.dist-info/RECORD,,

ml_tools/ML_evaluation.py

@@ -22,6 +22,7 @@ from .path_manager import make_fullpath
 from ._logger import _LOGGER
 from typing import Union, Optional, List
 from ._script_info import _script_info
+from .keys import SHAPKeys
 
 
 __all__ = [
@@ -333,7 +334,8 @@ def shap_summary_plot(model,
     plt.close()
 
     # Save Summary Data to CSV
-    summary_path = save_dir_path / "shap_summary.csv"
+    shap_summary_filename = SHAPKeys.SAVENAME + ".csv"
+    summary_path = save_dir_path / shap_summary_filename
     # Ensure the array is 1D before creating the DataFrame
     mean_abs_shap = np.abs(shap_values).mean(axis=0).flatten()
     
@@ -341,9 +343,9 @@ def shap_summary_plot(model,
         feature_names = [f'feature_{i}' for i in range(len(mean_abs_shap))]
         
     summary_df = pd.DataFrame({
-        'feature': feature_names,
-        'mean_abs_shap_value': mean_abs_shap
-    }).sort_values('mean_abs_shap_value', ascending=False)
+        SHAPKeys.FEATURE_COLUMN: feature_names,
+        SHAPKeys.SHAP_VALUE_COLUMN: mean_abs_shap
+    }).sort_values(SHAPKeys.SHAP_VALUE_COLUMN, ascending=False)
     
     summary_df.to_csv(summary_path, index=False)
     

ml_tools/SQL.py

@@ -4,7 +4,7 @@ from pathlib import Path
 from typing import Union, Dict, Any, Optional, List, Literal
 from ._logger import _LOGGER
 from ._script_info import _script_info
-from .path_manager import make_fullpath
+from .path_manager import make_fullpath, sanitize_filename
 
 
 __all__ = [
@@ -94,11 +94,13 @@ class DatabaseManager:
         if not self.cursor:
             _LOGGER.error("Database connection is not open.")
             raise sqlite3.Error()
+        
+        sanitized_table_name = sanitize_filename(table_name)
 
         columns_def = ", ".join([f'"{col_name}" {col_type}' for col_name, col_type in schema.items()])
         exists_clause = "IF NOT EXISTS" if if_not_exists else ""
         
-        query = f"CREATE TABLE {exists_clause} {table_name} ({columns_def})"
+        query = f"CREATE TABLE {exists_clause} {sanitized_table_name} ({columns_def})"
         
         _LOGGER.info(f"➡️ Executing: {query}")
         self.cursor.execute(query)

ml_tools/ensemble_evaluation.py

@@ -25,6 +25,7 @@ from typing import Union, Optional, Literal
 from .path_manager import sanitize_filename, make_fullpath
 from ._script_info import _script_info
 from ._logger import _LOGGER
+from .keys import SHAPKeys
 
 
 __all__ = [
@@ -472,7 +473,7 @@ def get_shap_values(
         save_dir: Directory to save visualizations.
     """
     sanitized_target_name = sanitize_filename(target_name)
-    global_save_path = make_fullpath(save_dir, make=True)
+    global_save_path = make_fullpath(save_dir, make=True, enforce="directory")
     
     def _apply_plot_style():
         styles = ['seaborn', 'seaborn-v0_8-darkgrid', 'seaborn-v0_8', 'default']
@@ -539,6 +540,15 @@ def get_shap_values(
                         plot_type=plot_type,
                         title=f"{model_name} - {target_name} (Class {class_name})"
                     )
+                    
+                # Save the summary data for the current class
+                summary_save_path = global_save_path / f"SHAP_{sanitized_target_name}_{class_name}.csv"
+                _save_summary_csv(
+                    shap_values_for_summary=class_shap,
+                    feature_names=feature_names,
+                    save_path=summary_save_path
+                )
+                    
         else:
             values = shap_values[1] if isinstance(shap_values, list) else shap_values
             for plot_type in ["bar", "dot"]:
@@ -549,6 +559,15 @@ def get_shap_values(
                     plot_type=plot_type,
                     title=f"{model_name} - {target_name}"
                 )
+                
+            # Save the summary data for the positive class
+            shap_summary_filename = SHAPKeys.SAVENAME + ".csv"
+            summary_save_path = global_save_path / shap_summary_filename
+            _save_summary_csv(
+                shap_values_for_summary=values,
+                feature_names=feature_names,
+                save_path=summary_save_path
+            )
 
     def _plot_for_regression(shap_values):
         for plot_type in ["bar", "dot"]:
@@ -559,6 +578,34 @@ def get_shap_values(
                 plot_type=plot_type,
                 title=f"{model_name} - {target_name}"
             )
+        
+        # Save the summary data to a CSV file
+        shap_summary_filename = SHAPKeys.SAVENAME + ".csv"
+        summary_save_path = global_save_path / shap_summary_filename
+        _save_summary_csv(
+            shap_values_for_summary=shap_values,
+            feature_names=feature_names,
+            save_path=summary_save_path
+        )
+        
+    def _save_summary_csv(shap_values_for_summary: np.ndarray, feature_names: list[str], save_path: Path):
+        """Calculates and saves the SHAP summary data to a CSV file."""
+        mean_abs_shap = np.abs(shap_values_for_summary).mean(axis=0)
+        
+        # Create default feature names if none are provided
+        current_feature_names = feature_names
+        if current_feature_names is None:
+            current_feature_names = [f'feature_{i}' for i in range(len(mean_abs_shap))]
+        
+        summary_df = pd.DataFrame({
+            SHAPKeys.FEATURE_COLUMN: feature_names,
+            SHAPKeys.SHAP_VALUE_COLUMN: mean_abs_shap
+        }).sort_values(SHAPKeys.SHAP_VALUE_COLUMN, ascending=False)
+        
+        summary_df.to_csv(save_path, index=False)
+        # print(f"📝 SHAP summary data saved as '{save_path.name}'")
+    
+            
     #START_O
 
     explainer = shap.TreeExplainer(model)

ml_tools/keys.py

@@ -61,6 +61,13 @@ class DatasetKeys:
     SCALER_PREFIX = "scaler_"
 
 
+class SHAPKeys:
+    """Keys for SHAP functions"""
+    FEATURE_COLUMN = "feature"
+    SHAP_VALUE_COLUMN = "mean_abs_shap_value"
+    SAVENAME = "shap_summary"
+
+
 class _OneHotOtherPlaceholder:
     """Used internally by GUI_tools."""
     OTHER_GUI = "OTHER"

ml_tools/utilities.py

@@ -9,7 +9,7 @@ from joblib.externals.loky.process_executor import TerminatedWorkerError
 from .path_manager import sanitize_filename, make_fullpath, list_csv_paths, list_files_by_extension, list_subdirectories
 from ._script_info import _script_info
 from ._logger import _LOGGER
-from .keys import DatasetKeys, PytorchModelArchitectureKeys, PytorchArtifactPathKeys
+from .keys import DatasetKeys, PytorchModelArchitectureKeys, PytorchArtifactPathKeys, SHAPKeys
 
 
 # Keep track of available tools
@@ -26,7 +26,8 @@ __all__ = [
     "distribute_dataset_by_target",
     "train_dataset_orchestrator",
     "train_dataset_yielder",
-    "find_model_artifacts"
+    "find_model_artifacts",
+    "select_features_by_shap"
 ]
 
 
@@ -34,6 +35,7 @@ __all__ = [
 @overload
 def load_dataframe(
     df_path: Union[str, Path], 
+    use_columns: Optional[list[str]] = None, 
     kind: Literal["pandas"] = "pandas",
     all_strings: bool = False,
     verbose: bool = True
@@ -44,7 +46,8 @@ def load_dataframe(
 @overload
 def load_dataframe(
     df_path: Union[str, Path], 
-    kind: Literal["polars"],
+    use_columns: Optional[list[str]] = None,
+    kind: Literal["polars"] = "polars",
     all_strings: bool = False,
     verbose: bool = True
 ) -> Tuple[pl.DataFrame, str]:
@@ -52,6 +55,7 @@ def load_dataframe(
 
 def load_dataframe(
     df_path: Union[str, Path], 
+    use_columns: Optional[list[str]] = None,
     kind: Literal["pandas", "polars"] = "pandas",
     all_strings: bool = False,
     verbose: bool = True
@@ -60,11 +64,13 @@ def load_dataframe(
     Load a CSV file into a DataFrame and extract its base name.
 
     Can load data as either a pandas or a polars DataFrame. Allows for loading all
-    columns as string types to prevent type inference errors.
+    columns or a subset of columns as string types to prevent type inference errors.
 
     Args:
         df_path (str, Path): 
             The path to the CSV file.
+        use_columns (list[str] | None):
+            If provided, only these columns will be loaded from the CSV.
         kind ("pandas", "polars"): 
             The type of DataFrame to load. Defaults to "pandas".
         all_strings (bool): 
@@ -78,28 +84,43 @@ def load_dataframe(
             
     Raises:
         FileNotFoundError: If the file does not exist at the given path.
-        ValueError: If the DataFrame is empty or an invalid 'kind' is provided.
+        ValueError: If the DataFrame is empty, an invalid 'kind' is provided, or a column in 'use_columns' is not found in the file.
     """
     path = make_fullpath(df_path)
     
     df_name = path.stem
 
-    if kind == "pandas":
-        if all_strings:
-            df = pd.read_csv(path, encoding='utf-8', dtype=str)
-        else:
-            df = pd.read_csv(path, encoding='utf-8')
-            
-    elif kind == "polars":
-        if all_strings:
-            df = pl.read_csv(path, infer_schema=False)
+    try:
+        if kind == "pandas":
+            pd_kwargs: dict[str,Any]
+            pd_kwargs = {'encoding': 'utf-8'}
+            if use_columns:
+                pd_kwargs['usecols'] = use_columns
+            if all_strings:
+                pd_kwargs['dtype'] = str
+                
+            df = pd.read_csv(path, **pd_kwargs)
+
+        elif kind == "polars":
+            pl_kwargs: dict[str,Any]
+            pl_kwargs = {}
+            if use_columns:
+                pl_kwargs['columns'] = use_columns
+                
+            if all_strings:
+                pl_kwargs['infer_schema'] = False
+            else:
+                pl_kwargs['infer_schema_length'] = 1000
+                
+            df = pl.read_csv(path, **pl_kwargs)
+
         else:
-            # Default behavior: infer the schema.
-            df = pl.read_csv(path, infer_schema_length=1000)
+            _LOGGER.error(f"Invalid kind '{kind}'. Must be one of 'pandas' or 'polars'.")
+            raise ValueError()
             
-    else:
-        _LOGGER.error(f"Invalid kind '{kind}'. Must be one of 'pandas' or 'polars'.")
-        raise ValueError()
+    except (ValueError, pl.exceptions.ColumnNotFoundError) as e:
+        _LOGGER.error(f"Failed to load '{df_name}'. A specified column may not exist in the file.")
+        raise e
 
     # This check works for both pandas and polars DataFrames
     if df.shape[0] == 0:
@@ -111,7 +132,6 @@ def load_dataframe(
     
     return df, df_name # type: ignore
 
-
 def yield_dataframes_from_dir(datasets_dir: Union[str,Path], verbose: bool=True):
     """
     Iterates over all CSV files in a given directory, loading each into a Pandas DataFrame.
@@ -683,5 +703,84 @@ def find_model_artifacts(target_directory: Union[str,Path], load_scaler: bool, v
     return all_artifacts
 
 
+def select_features_by_shap(
+    root_directory: Union[str, Path],
+    shap_threshold: float = 1.0,
+    verbose: bool = True) -> list[str]:
+    """
+    Scans subdirectories to find SHAP summary CSVs, then extracts feature
+    names whose mean absolute SHAP value meets a specified threshold.
+
+    This function is useful for automated feature selection based on feature
+    importance scores aggregated from multiple models.
+
+    Args:
+        root_directory (Union[str, Path]):
+            The path to the root directory that contains model subdirectories.
+        shap_threshold (float):
+            The minimum mean absolute SHAP value for a feature to be included
+            in the final list.
+
+    Returns:
+        list[str]:
+            A single, sorted list of unique feature names that meet the
+            threshold criteria across all found files.
+    """
+    if verbose:
+        _LOGGER.info(f"Starting feature selection with SHAP threshold >= {shap_threshold}")
+    root_path = make_fullpath(root_directory, enforce="directory")
+
+    # --- Step 2: Directory and File Discovery ---
+    subdirectories = list_subdirectories(root_dir=root_path, verbose=False)
+    
+    shap_filename = SHAPKeys.SAVENAME + ".csv"
+
+    valid_csv_paths = []
+    for dir_name, dir_path in subdirectories.items():
+        expected_path = dir_path / shap_filename
+        if expected_path.is_file():
+            valid_csv_paths.append(expected_path)
+        else:
+            _LOGGER.warning(f"No '{shap_filename}' found in subdirectory '{dir_name}'.")
+    
+    if not valid_csv_paths:
+        _LOGGER.error(f"Process halted: No '{shap_filename}' files were found in any subdirectory.")
+        return []
+
+    if verbose:
+        _LOGGER.info(f"Found {len(valid_csv_paths)} SHAP summary files to process.")
+
+    # --- Step 3: Data Processing and Feature Extraction ---
+    master_feature_set = set()
+    for csv_path in valid_csv_paths:
+        try:
+            df, _ = load_dataframe(csv_path, kind="pandas", verbose=False)
+            
+            # Validate required columns
+            required_cols = {SHAPKeys.FEATURE_COLUMN, SHAPKeys.SHAP_VALUE_COLUMN}
+            if not required_cols.issubset(df.columns):
+                _LOGGER.warning(f"Skipping '{csv_path}': missing required columns.")
+                continue
+
+            # Filter by threshold and extract features
+            filtered_df = df[df[SHAPKeys.SHAP_VALUE_COLUMN] >= shap_threshold]
+            features = filtered_df[SHAPKeys.FEATURE_COLUMN].tolist()
+            master_feature_set.update(features)
+
+        except (ValueError, pd.errors.EmptyDataError):
+            _LOGGER.warning(f"Skipping '{csv_path}' because it is empty or malformed.")
+            continue
+        except Exception as e:
+            _LOGGER.error(f"An unexpected error occurred while processing '{csv_path}': {e}")
+            continue
+
+    # --- Step 4: Finalize and Return ---
+    final_features = sorted(list(master_feature_set))
+    if verbose:
+        _LOGGER.info(f"Selected {len(final_features)} unique features across all files.")
+    
+    return final_features
+
+
 def info():
     _script_info(__all__)