dragon-ml-toolbox 12.4.0__py3-none-any.whl → 12.6.0__py3-none-any.whl

{dragon_ml_toolbox-12.4.0.dist-info → dragon_ml_toolbox-12.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.4.0
+Version: 12.6.0
 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-12.4.0.dist-info → dragon_ml_toolbox-12.6.0.dist-info}/RECORD

@@ -1,41 +1,41 @@
-dragon_ml_toolbox-12.4.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-12.4.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
-ml_tools/ETL_cleaning.py,sha256=PLRSR-VYnt1nNT9XrcWq40SE0VzHCw7DQ8v9czfSQsU,20366
-ml_tools/ETL_engineering.py,sha256=l0I6Og9o4s6EODdk0kZXjbbC-a3vVPYy1FopP2BkQSQ,54909
+dragon_ml_toolbox-12.6.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-12.6.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
+ml_tools/ETL_cleaning.py,sha256=2VBRllV8F-ZiPylPp8Az2gwn5ztgazN0BH5OKnRUhV0,20402
+ml_tools/ETL_engineering.py,sha256=KfYqgsxupAx6e_TxwO1LZXeu5mFkIhVXJrNjP3CzIZc,54927
 ml_tools/GUI_tools.py,sha256=Va6ig-dHULPVRwQYYtH3fvY5XPIoqRcJpRW8oXC55Hw,45413
-ml_tools/MICE_imputation.py,sha256=eNN7JuT43bydAJ5E2k2A5sDjYDu3X8kCHtMdFBkzjR0,11699
+ml_tools/MICE_imputation.py,sha256=X273Qlgoqqg7KTmoKd75YDyAPB0UIbTzGP3xsCmRh3E,11717
 ml_tools/ML_callbacks.py,sha256=-XRIZEy3CPJWTHcoReyIw53FZlTs3pWcTVVnncTQQSc,13909
 ml_tools/ML_datasetmaster.py,sha256=t6q6mU9lz2rYKTVPKjA7yZ5ImV7_NykiciHaYnqIEpA,30822
 ml_tools/ML_evaluation.py,sha256=tLswOPgH4G1KExSMn0876YtNkbxPh-W3J4MYOjomMWA,16208
 ml_tools/ML_evaluation_multi.py,sha256=6OZyQ4SM9ALh38mOABmiHgIQDWcovsD_iOo7Bg9YZCE,12516
 ml_tools/ML_inference.py,sha256=ymFvncFsU10PExq87xnEj541DKV5ck0nMuK8ToJHzVQ,23067
 ml_tools/ML_models.py,sha256=pSCV6KbmVnPZr49Kbyg7g25CYaWBWJr6IinBHKgVKGw,28042
-ml_tools/ML_optimization.py,sha256=-Rb7ffp-VS6Bv5U0Dw6nSTNp2bGu7BaBQi04mTmSdEE,22942
+ml_tools/ML_optimization.py,sha256=es3TlQbY7RYgJMZnznkjYGbUxFnAqzZxE_g3_qLK9Q8,22960
 ml_tools/ML_scaler.py,sha256=tw6onj9o8_kk3FQYb930HUzvv1zsFZe2YZJdF3LtHkU,7538
-ml_tools/ML_simple_optimization.py,sha256=X96zX6XPu3ggrcOapuG69jsiZJczJNihS1rcwi9OsBI,18159
+ml_tools/ML_simple_optimization.py,sha256=W2mce1XFCuiOHTOjOsCNbETISHn5MwYlYsTIXH5hMMo,18177
 ml_tools/ML_trainer.py,sha256=_g48w5Ak-wQr5fGHdJqlcpnzv3gWyL1ghkOhy9VOZbo,23930
 ml_tools/ML_utilities.py,sha256=35DfZzAwfDwVwfRECD8X_2ynsU2NCpTdNJSmza6oAzQ,8712
 ml_tools/PSO_optimization.py,sha256=fVHeemqilBS0zrGV25E5yKwDlGdd2ZKa18d8CZ6Q6Fk,22961
 ml_tools/RNN_forecast.py,sha256=Qa2KoZfdAvSjZ4yE78N4BFXtr3tTr0Gx7tQJZPotsh0,1967
 ml_tools/SQL.py,sha256=vXLPGfVVg8bfkbBE3HVfyEclVbdJy0TBhuQONtMwSCQ,11234
-ml_tools/VIF_factor.py,sha256=dizjK0zmgOMuLBnJ66y5Sll5do6wjGWhAPVzJF1uwhQ,10404
+ml_tools/VIF_factor.py,sha256=at5IVqPvicja2-DNSTSIIy3SkzDWCmLzo3qTG_qr5n8,10422
 ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
 ml_tools/_logger.py,sha256=dlp5cGbzooK9YSNSZYB4yjZrOaQUGW8PTrM411AOvL8,4717
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
 ml_tools/custom_logger.py,sha256=xot-VeZFigKjcVxADgzvI54vZO_MqMMejo7JmDED8Xo,5892
-ml_tools/data_exploration.py,sha256=OwPJHAM6MpkUD-S76XF4v-NRXjw5-pizKNHpyKj5OwE,46809
+ml_tools/data_exploration.py,sha256=xvuWHrxk5HOtY7_WmtXEUNf1d_TUxuNPFPFyN7QJxCY,46836
 ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
 ml_tools/ensemble_inference.py,sha256=0yLmLNj45RVVoSCLH1ZYJG9IoAhTkWUqEZmLOQTFGTY,9348
-ml_tools/ensemble_learning.py,sha256=aTPeKthO4zRWBEaQJOUj8jEqVHiHjjOMXuiEWjI9NxM,21946
+ml_tools/ensemble_learning.py,sha256=vsIED7nlheYI4w2SBzP6SC1AnNeMfn-2A1Gqw5EfxsM,21964
 ml_tools/handle_excel.py,sha256=pfdAPb9ywegFkM9T54bRssDOsX-K7rSeV0RaMz7lEAo,14006
 ml_tools/keys.py,sha256=FDpbS3Jb0pjrVvvp2_8nZi919mbob_-xwuy5OOtKM_A,1848
 ml_tools/math_utilities.py,sha256=PxoOrnuj6Ntp7_TJqyDWi0JX03WpAO5iaFNK2Oeq5I4,8800
 ml_tools/optimization_tools.py,sha256=ewYMAdSGlFxYALAGFXn-MsHpvW_Sbx6I-sKg9Kp6rB8,13533
 ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
-ml_tools/serde.py,sha256=k0qAwfMf13lVBQSgq5u9MSXEoo31iOA2-Ncm8XgMCMI,3974
-ml_tools/utilities.py,sha256=gef62GLK7ev5BWkkQekeJoVZqwf2mIuOlOfyCw6WdtE,13882
-dragon_ml_toolbox-12.4.0.dist-info/METADATA,sha256=KylxsFKgAXRHl6A_0w3PXcevzLc_GnAtmR1SLRC4x8g,6166
-dragon_ml_toolbox-12.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-12.4.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-12.4.0.dist-info/RECORD,,
+ml_tools/serde.py,sha256=UIshIesHRFmxr8F6B3LxGG8bYc1HHK-nlE3kENSZL18,5288
+ml_tools/utilities.py,sha256=_uCYOo5f6Zp6wxabrHwDfjvaipqziD7BWSdKhjl2VGU,13923
+dragon_ml_toolbox-12.6.0.dist-info/METADATA,sha256=Bg2mEGcvqeyB4Pr-M3ETjAM3GOwr7FBH0s57XpuBij0,6166
+dragon_ml_toolbox-12.6.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-12.6.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-12.6.0.dist-info/RECORD,,

ml_tools/ETL_cleaning.py

@@ -5,7 +5,7 @@ from typing import Union, List, Dict
 
 from .path_manager import sanitize_filename, make_fullpath
 from .data_exploration import drop_macro
-from .utilities import save_dataframe, load_dataframe
+from .utilities import save_dataframe_filename, load_dataframe
 from ._script_info import _script_info
 from ._logger import _LOGGER
 
@@ -263,7 +263,7 @@ def basic_clean(input_filepath: Union[str,Path], output_filepath: Union[str,Path
     df_final = _cleaner_core(df_in=df, all_lowercase=all_lowercase)
     
     # Save cleaned dataframe
-    save_dataframe(df=df_final, save_dir=output_path.parent, filename=output_path.name)
+    save_dataframe_filename(df=df_final, save_dir=output_path.parent, filename=output_path.name)
     
     _LOGGER.info(f"Data successfully cleaned.")
     
@@ -329,7 +329,7 @@ def basic_clean_drop(input_filepath: Union[str,Path], output_filepath: Union[str
                           threshold=threshold)
     
     # Save cleaned dataframe
-    save_dataframe(df=df_final, save_dir=output_path.parent, filename=output_path.name)
+    save_dataframe_filename(df=df_final, save_dir=output_path.parent, filename=output_path.name)
     
     _LOGGER.info(f"Data successfully cleaned.")
 
@@ -494,7 +494,7 @@ class DataFrameCleaner:
         if isinstance(output_filepath, str):
             output_filepath = make_fullpath(input_path=output_filepath, enforce="file")
         
-        save_dataframe(df=df_clean, save_dir=output_filepath.parent, filename=output_filepath.name)
+        save_dataframe_filename(df=df_clean, save_dir=output_filepath.parent, filename=output_filepath.name)
         
         return None
 

ml_tools/ETL_engineering.py

@@ -3,7 +3,7 @@ import re
 from pathlib import Path
 from typing import Literal, Union, Optional, Any, Callable, List, Dict, Tuple
 
-from .utilities import load_dataframe, save_dataframe
+from .utilities import load_dataframe, save_dataframe_filename
 from .path_manager import make_fullpath
 from ._script_info import _script_info
 from ._logger import _LOGGER
@@ -230,7 +230,7 @@ class DataProcessor:
         df_processed = self.transform(df)
         
         # save processed df
-        save_dataframe(df=df_processed, save_dir=out_path.parent, filename=out_path.name)
+        save_dataframe_filename(df=df_processed, save_dir=out_path.parent, filename=out_path.name)
         
     def __str__(self) -> str:
         """

ml_tools/MICE_imputation.py

@@ -6,7 +6,7 @@ import numpy as np
 from plotnine import ggplot, labs, theme, element_blank # type: ignore
 from typing import Optional, Union
 
-from .utilities import load_dataframe, merge_dataframes, save_dataframe
+from .utilities import load_dataframe, merge_dataframes, save_dataframe_filename
 from .math_utilities import threshold_binary_values
 from .path_manager import sanitize_filename, make_fullpath, list_csv_paths
 from ._logger import _LOGGER
@@ -75,7 +75,7 @@ def apply_mice(df: pd.DataFrame, df_name: str, binary_columns: Optional[list[str
 def save_imputed_datasets(save_dir: Union[str, Path], imputed_datasets: list, df_targets: pd.DataFrame, imputed_dataset_names: list[str]):
     for imputed_df, subname in zip(imputed_datasets, imputed_dataset_names):
         merged_df = merge_dataframes(imputed_df, df_targets, direction="horizontal", verbose=False)
-        save_dataframe(df=merged_df, save_dir=save_dir, filename=subname)
+        save_dataframe_filename(df=merged_df, save_dir=save_dir, filename=subname)
 
 
 #Get names of features that had missing values before imputation

ml_tools/ML_optimization.py

@@ -18,7 +18,7 @@ from .ML_inference import PyTorchInferenceHandler
 from .keys import PyTorchInferenceKeys
 from .SQL import DatabaseManager
 from .optimization_tools import _save_result
-from .utilities import save_dataframe
+from .utilities import save_dataframe_filename
 from .math_utilities import discretize_categorical_values
 
 
@@ -513,7 +513,7 @@ def _run_single_optimization_rep(
 
 def _handle_pandas_log(logger: PandasLogger, save_path: Path, target_name: str):
     log_dataframe = logger.to_dataframe()
-    save_dataframe(df=log_dataframe, save_dir=save_path / "EvolutionLogs", filename=target_name)
+    save_dataframe_filename(df=log_dataframe, save_dir=save_path / "EvolutionLogs", filename=target_name)
 
 
 def info():

ml_tools/ML_simple_optimization.py

@@ -18,7 +18,7 @@ from .ML_inference import PyTorchInferenceHandler
 from .keys import PyTorchInferenceKeys
 from .SQL import DatabaseManager
 from .optimization_tools import _save_result
-from .utilities import save_dataframe
+from .utilities import save_dataframe_filename
 from .math_utilities import threshold_binary_values
 
 """
@@ -406,7 +406,7 @@ def s_run_optimization(
 
 def _handle_pandas_log(logger: PandasLogger, save_path: Path, target_name: str):
     log_dataframe = logger.to_dataframe()
-    save_dataframe(df=log_dataframe, save_dir=save_path / "EvolutionLogs", filename=target_name)
+    save_dataframe_filename(df=log_dataframe, save_dir=save_path / "EvolutionLogs", filename=target_name)
 
 
 def info():

ml_tools/VIF_factor.py

@@ -7,7 +7,7 @@ from statsmodels.tools.tools import add_constant
 import warnings
 from pathlib import Path
 
-from .utilities import yield_dataframes_from_dir, save_dataframe
+from .utilities import yield_dataframes_from_dir, save_dataframe_filename
 from .path_manager import sanitize_filename, make_fullpath
 from ._logger import _LOGGER
 from ._script_info import _script_info
@@ -229,7 +229,7 @@ def compute_vif_multi(input_directory: Union[str, Path],
             result_df, dropped_cols = drop_vif_based(df=df, vif_df=vif_dataframe)
             
             if len(dropped_cols) > 0:
-                save_dataframe(df=result_df, save_dir=output_dataset_path, filename=new_filename)
+                save_dataframe_filename(df=result_df, save_dir=output_dataset_path, filename=new_filename)
 
 
 def info():

ml_tools/data_exploration.py

@@ -10,7 +10,7 @@ import re
 from .path_manager import sanitize_filename, make_fullpath
 from ._script_info import _script_info
 from ._logger import _LOGGER
-from .utilities import save_dataframe
+from .utilities import save_dataframe_filename
 
 
 # Keep track of all available tools, show using `info()`
@@ -269,7 +269,7 @@ def drop_macro(df: pd.DataFrame,
     
     # Log initial state
     missing_data = show_null_columns(df=df_clean)
-    save_dataframe(df=missing_data.reset_index(drop=False),
+    save_dataframe_filename(df=missing_data.reset_index(drop=False),
                    save_dir=log_directory,
                    filename="Missing_Data_start")
     
@@ -298,7 +298,7 @@ def drop_macro(df: pd.DataFrame,
     
     # log final state
     missing_data = show_null_columns(df=df_clean)
-    save_dataframe(df=missing_data.reset_index(drop=False),
+    save_dataframe_filename(df=missing_data.reset_index(drop=False),
                    save_dir=log_directory,
                    filename="Missing_Data_final")
     

ml_tools/ensemble_learning.py

@@ -14,7 +14,7 @@ from sklearn.model_selection import train_test_split
 from sklearn.base import clone
 
 from .utilities import yield_dataframes_from_dir, train_dataset_yielder
-from .serde import serialize_object
+from .serde import serialize_object_filename
 from .path_manager import sanitize_filename, make_fullpath
 from ._script_info import _script_info
 from .keys import EnsembleKeys
@@ -411,7 +411,7 @@ def _save_model(trained_model, model_name: str, target_name:str, feature_names:
                EnsembleKeys.FEATURES: feature_names,
                EnsembleKeys.TARGET: target_name}
 
-    serialize_object(obj=to_save, save_dir=save_directory, filename=filename, verbose=False, raise_on_error=True)
+    serialize_object_filename(obj=to_save, save_dir=save_directory, filename=filename, verbose=False, raise_on_error=True)
 
 
 # TRAIN EVALUATE PIPELINE

ml_tools/serde.py

@@ -9,12 +9,13 @@ from ._logger import _LOGGER
 
 
 __all__ = [
+    "serialize_object_filename",
     "serialize_object",
     "deserialize_object",
 ]
 
 
-def serialize_object(obj: Any, save_dir: Union[str,Path], filename: str, verbose: bool=True, raise_on_error: bool=False) -> None:
+def serialize_object_filename(obj: Any, save_dir: Union[str,Path], filename: str, verbose: bool=True, raise_on_error: bool=False) -> None:
     """
     Serializes a Python object using joblib; suitable for Python built-ins, numpy, and pandas.
 
@@ -40,6 +41,41 @@ def serialize_object(obj: Any, save_dir: Union[str,Path], filename: str, verbose
             _LOGGER.info(f"Object of type '{type(obj)}' saved to '{full_path}'")
         return None
 
+
+def serialize_object(obj: Any, file_path: Path, verbose: bool = True, raise_on_error: bool = False) -> None:
+    """
+    Serializes a Python object using joblib to a specific file path.
+
+    Suitable for Python built-ins, numpy, and pandas.
+
+    Parameters:
+        obj (Any) : The Python object to serialize.
+        file_path (Path) : The full file path to save the object to.
+                           '.joblib' extension will be appended if missing.
+        raise_on_error (bool) : If True, raises exceptions on failure.
+    """
+    try:
+        # Ensure the extension is correct
+        if file_path.suffix != '.joblib':
+            file_path = file_path.with_suffix(file_path.suffix + '.joblib')
+
+        # Ensure the parent directory exists
+        _save_dir = make_fullpath(file_path.parent, make=True, enforce="directory")
+
+        # Dump the object
+        joblib.dump(obj, file_path)
+
+    except (IOError, OSError, TypeError, TerminatedWorkerError) as e:
+        _LOGGER.error(f"Failed to serialize object of type '{type(obj)}' to '{file_path}'. Error: {e}")
+        if raise_on_error:
+            raise e
+        return None
+    else:
+        if verbose:
+            _LOGGER.info(f"Object of type '{type(obj)}' saved to '{file_path}'")
+        return None
+
+
 # Define a TypeVar to link the expected type to the return type of deserialization
 T = TypeVar('T')
     

ml_tools/utilities.py

@@ -14,8 +14,8 @@ __all__ = [
     "load_dataframe",
     "yield_dataframes_from_dir",
     "merge_dataframes",
+    "save_dataframe_filename",
     "save_dataframe",
-    "save_dataframe_path",
     "distribute_dataset_by_target",
     "train_dataset_orchestrator",
     "train_dataset_yielder"
@@ -210,7 +210,7 @@ def merge_dataframes(
     return merged_df
 
 
-def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Union[str,Path], filename: str) -> None:
+def save_dataframe_filename(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Union[str,Path], filename: str) -> None:
     """
     Saves a pandas or polars DataFrame to a CSV file.
 
@@ -250,11 +250,11 @@ def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Union[str,Pa
     _LOGGER.info(f"Saved dataset: '{filename}' with shape: {df.shape}")
 
 
-def save_dataframe_path(df: Union[pd.DataFrame, pl.DataFrame], full_path: Path):
+def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], full_path: Path):
     """
     Saves a DataFrame to a specified full path.
 
-    This function is a convenience wrapper for `save_dataframe()`. It takes a
+    This function is a wrapper for `save_dataframe_filename()`. It takes a
     single `pathlib.Path` object pointing to a `.csv` file.
 
     Args:
@@ -265,9 +265,9 @@ def save_dataframe_path(df: Union[pd.DataFrame, pl.DataFrame], full_path: Path):
         _LOGGER.error('A path object pointing to a .csv file must be provided.')
         raise ValueError()
         
-    save_dataframe(df=df, 
-                   save_dir=full_path.parent,
-                   filename=full_path.name)
+    save_dataframe_filename(df=df, 
+                            save_dir=full_path.parent,
+                            filename=full_path.name)
 
 
 def distribute_dataset_by_target(
@@ -351,7 +351,7 @@ def train_dataset_orchestrator(list_of_dirs: list[Union[str,Path]],
                         filename = df_dir.name + '_' + target_name + '_' + df_name
                     else:
                         filename = target_name + '_' + df_name
-                    save_dataframe(df=df, save_dir=save_dir, filename=filename)
+                    save_dataframe_filename(df=df, save_dir=save_dir, filename=filename)
                     total_saved += 1
             except Exception as e:
                 _LOGGER.error(f"Failed to process file '{df_path}'. Reason: {e}")