dragon-ml-toolbox 12.6.0__tar.gz → 12.8.0__tar.gz

{dragon_ml_toolbox-12.6.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-12.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.6.0
+Version: 12.8.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-12.6.0 → dragon_ml_toolbox-12.8.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.6.0
+Version: 12.8.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-12.6.0 → dragon_ml_toolbox-12.8.0}/ml_tools/ML_utilities.py

@@ -1,12 +1,13 @@
 import pandas as pd
 from pathlib import Path
-from typing import Union, Any
+from typing import Union, Any, Optional
 
 from .path_manager import make_fullpath, list_subdirectories, list_files_by_extension
 from ._script_info import _script_info
 from ._logger import _LOGGER
 from .keys import DatasetKeys, PytorchModelArchitectureKeys, PytorchArtifactPathKeys, SHAPKeys
 from .utilities import load_dataframe
+from .custom_logger import save_list_strings
 
 
 __all__ = [
@@ -139,6 +140,7 @@ def find_model_artifacts(target_directory: Union[str,Path], load_scaler: bool, v
 def select_features_by_shap(
     root_directory: Union[str, Path],
     shap_threshold: float,
+    log_feature_names_directory: Optional[Union[str, Path]],
     verbose: bool = True) -> list[str]:
     """
     Scans subdirectories to find SHAP summary CSVs, then extracts feature
@@ -148,11 +150,13 @@ def select_features_by_shap(
     importance scores aggregated from multiple models.
 
     Args:
-        root_directory (Union[str, Path]):
+        root_directory (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.
+        log_feature_names_directory (str | Path | None):
+            If given, saves the chosen feature names as a .txt file in this directory.
 
     Returns:
         list[str]:
@@ -211,6 +215,13 @@ def select_features_by_shap(
     final_features = sorted(list(master_feature_set))
     if verbose:
         _LOGGER.info(f"Selected {len(final_features)} unique features across all files.")
+        
+    if log_feature_names_directory is not None:
+        save_names_path = make_fullpath(log_feature_names_directory, make=True, enforce="directory")
+        save_list_strings(list_strings=final_features,
+                          directory=save_names_path,
+                          filename=DatasetKeys.FEATURE_NAMES,
+                          verbose=verbose)
     
     return final_features
 

{dragon_ml_toolbox-12.6.0 → dragon_ml_toolbox-12.8.0}/ml_tools/data_exploration.py

@@ -362,6 +362,7 @@ def encode_categorical_features(
         encode_nulls (bool): If True, encodes Null values as a distinct category
             "Other" with a value of 0. Other categories start from 1. 
             If False, Nulls are ignored and categories start from 0.
+            Note: Use False when encoding binary values with missing entries.
         split_resulting_dataset (bool): If True, returns two separate DataFrames:
             one with non-categorical columns and one with the encoded columns.
             If False, returns a single DataFrame with all columns.

{dragon_ml_toolbox-12.6.0 → dragon_ml_toolbox-12.8.0}/ml_tools/optimization_tools.py

@@ -98,7 +98,7 @@ def create_optimization_bounds(
 
     # 3. Populate categorical bounds (Index-based)
     # The indices in categorical_map (e.g., {2: 4}) directly correspond
-    # to the indices in our new `feature_names` list.
+    # to the indices in the `feature_names` list.
     for index, cardinality in categorical_map.items():
         if not (0 <= index < total_features):
             _LOGGER.error(f"Categorical index {index} is out of range for the {total_features} features.")
@@ -125,8 +125,8 @@ def create_optimization_bounds(
             # Map name to its index in the *feature-only* list
             index = feature_names.index(name)
         except ValueError:
-            _LOGGER.error(f"Feature name '{name}' from 'continuous_bounds_map' not found in the CSV's feature columns.")
-            raise ValueError()
+            _LOGGER.warning(f"Feature name '{name}' from 'continuous_bounds_map' not found in the CSV's feature columns.")
+            continue
             
         if lower_bounds[index] is not None:
             # This index was already set by the categorical map

{dragon_ml_toolbox-12.6.0 → dragon_ml_toolbox-12.8.0}/ml_tools/utilities.py

@@ -12,6 +12,7 @@ from ._logger import _LOGGER
 # Keep track of available tools
 __all__ = [
     "load_dataframe",
+    "load_dataframe_greedy",
     "yield_dataframes_from_dir",
     "merge_dataframes",
     "save_dataframe_filename",
@@ -124,6 +125,54 @@ def load_dataframe(
     return df, df_name # type: ignore
 
 
+def load_dataframe_greedy(directory: Union[str, Path],
+                          use_columns: Optional[list[str]] = None,
+                          all_strings: bool = False,
+                          verbose: bool = True) -> pd.DataFrame:
+    """
+    Greedily loads the first found CSV file from a directory into a Pandas DataFrame.
+
+    This function scans the specified directory for any CSV files. It will
+    attempt to load the *first* CSV file it finds using the `load_dataframe`
+    function as a Pandas DataFrame.
+
+    Args:
+        directory (str, Path): 
+            The path to the directory to search for a CSV file.
+        use_columns (list[str] | None):
+            A list of column names to load. If None, all columns are loaded.
+        all_strings (bool): 
+            If True, loads all columns as string data types.
+
+    Returns:
+        pd.DataFrame: 
+            A pandas DataFrame loaded from the first CSV file found.
+
+    Raises:
+        FileNotFoundError: 
+            If the specified directory does not exist or the CSV file path
+            found is invalid.
+        ValueError: 
+            If the loaded DataFrame is empty or `use_columns` contains
+            invalid column names.
+    """
+    # validate directory
+    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)
+    
+    for df_path in csv_dict.values():
+        df , _df_name = load_dataframe(df_path=df_path,
+                                    use_columns=use_columns,
+                                    kind="pandas",
+                                    all_strings=all_strings,
+                                    verbose=verbose)
+        break
+    
+    return df
+
+
 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.

{dragon_ml_toolbox-12.6.0 → dragon_ml_toolbox-12.8.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "12.6.0"
+version = "12.8.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl L. Loza Vidaurre", email = "luigiloza@gmail.com" }