dragon-ml-toolbox 10.2.0__py3-none-any.whl → 14.2.0__py3-none-any.whl

{dragon_ml_toolbox-10.2.0.dist-info → dragon_ml_toolbox-14.2.0.dist-info}/METADATA

@@ -1,23 +1,17 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.2.0
+Version: 14.2.0
 Summary: A collection of tools for data science and machine learning projects.
-Author-email: Karl Loza <luigiloza@gmail.com>
+Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/DrAg0n-BoRn/ML_tools
 Project-URL: Changelog, https://github.com/DrAg0n-BoRn/ML_tools/blob/master/CHANGELOG.md
 Classifier: Programming Language :: Python :: 3
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
+Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: LICENSE-THIRD-PARTY.md
-Provides-Extra: base
-Requires-Dist: pandas; extra == "base"
-Requires-Dist: numpy; extra == "base"
-Requires-Dist: polars; extra == "base"
-Requires-Dist: joblib; extra == "base"
-Requires-Dist: colorlog; extra == "base"
 Provides-Extra: ml
 Requires-Dist: numpy>=2.0; extra == "ml"
 Requires-Dist: pandas; extra == "ml"
@@ -38,7 +32,12 @@ Requires-Dist: shap; extra == "ml"
 Requires-Dist: tqdm; extra == "ml"
 Requires-Dist: Pillow; extra == "ml"
 Requires-Dist: evotorch; extra == "ml"
+Requires-Dist: pyarrow; extra == "ml"
 Requires-Dist: colorlog; extra == "ml"
+Requires-Dist: torchmetrics; extra == "ml"
+Provides-Extra: py-tab
+Requires-Dist: pytorch_tabular; extra == "py-tab"
+Requires-Dist: omegaconf; extra == "py-tab"
 Provides-Extra: mice
 Requires-Dist: numpy<2.0; extra == "mice"
 Requires-Dist: pandas; extra == "mice"
@@ -51,9 +50,7 @@ Requires-Dist: statsmodels; extra == "mice"
 Requires-Dist: lightgbm<=4.5.0; extra == "mice"
 Requires-Dist: shap; extra == "mice"
 Requires-Dist: colorlog; extra == "mice"
-Provides-Extra: pytorch
-Requires-Dist: torch; extra == "pytorch"
-Requires-Dist: torchvision; extra == "pytorch"
+Requires-Dist: pyarrow; extra == "mice"
 Provides-Extra: excel
 Requires-Dist: pandas; extra == "excel"
 Requires-Dist: openpyxl; extra == "excel"
@@ -72,9 +69,6 @@ Requires-Dist: lightgbm; extra == "gui-boost"
 Provides-Extra: gui-torch
 Requires-Dist: numpy; extra == "gui-torch"
 Requires-Dist: FreeSimpleGUI>=5.2; extra == "gui-torch"
-Provides-Extra: plot
-Requires-Dist: matplotlib; extra == "plot"
-Requires-Dist: seaborn; extra == "plot"
 Provides-Extra: pyinstaller
 Requires-Dist: pyinstaller; extra == "pyinstaller"
 Provides-Extra: nuitka
@@ -94,7 +88,7 @@ A collection of Python utilities for data science and machine learning, structur
 
 ## Installation
 
-**Python 3.10+**
+**Python 3.12**
 
 ### Via PyPI
 
@@ -104,22 +98,22 @@ Install the latest stable release from PyPI:
 pip install dragon-ml-toolbox
 ```
 
-### Via GitHub (Editable)
+### Via conda-forge
 
-Clone the repository and install in editable mode with optional dependencies:
+Install from the conda-forge channel:
 
 ```bash
-git clone https://github.com/DrAg0n-BoRn/ML_tools.git
-cd ML_tools
-pip install -e .
+conda install -c conda-forge dragon-ml-toolbox
 ```
 
-### Via conda-forge
+### Via GitHub (Editable)
 
-Install from the conda-forge channel:
+Clone the repository and install in editable mode:
 
 ```bash
-conda install -c conda-forge dragon-ml-toolbox
+git clone https://github.com/DrAg0n-BoRn/ML_tools.git
+cd ML_tools
+pip install -e .
 ```
 
 ## Modular Installation
@@ -132,17 +126,12 @@ Installs a comprehensive set of tools for typical data science workflows, includ
 pip install "dragon-ml-toolbox[ML]"
 ```
 
-To install the standard CPU-only versions of Torch and Torchvision:
-
-```Bash
-pip install "dragon-ml-toolbox[pytorch]"
-```
-
-⚠️ To make use of GPU acceleration (highly recommended), follow the official instructions: [PyTorch website](https://pytorch.org/get-started/locally/)
+⚠️ PyTorch required, follow the official instructions: [PyTorch website](https://pytorch.org/get-started/locally/)
 
 #### Modules:
 
 ```bash
+constants
 custom_logger
 data_exploration
 ensemble_evaluation
@@ -150,19 +139,28 @@ ensemble_inference
 ensemble_learning
 ETL_cleaning
 ETL_engineering
+math_utilities
 ML_callbacks
 ML_datasetmaster
 ML_evaluation_multi
 ML_evaluation
 ML_inference
 ML_models
+ML_models_advanced # Requires the extra flag [py-tab]
 ML_optimization
 ML_scaler
 ML_trainer
+ML_utilities
+ML_vision_datasetmaster
+ML_vision_evaluation
+ML_vision_inference
+ML_vision_models
+ML_vision_transformers
 optimization_tools
 path_manager
 PSO_optimization
 RNN_forecast
+serde
 SQL
 utilities
 ```
@@ -180,8 +178,11 @@ pip install "dragon-ml-toolbox[mice]"
 #### Modules:
 
 ```Bash
+constants
 custom_logger
+math_utilities
 MICE_imputation
+serde
 VIF_factor
 path_manager
 utilities
@@ -209,42 +210,37 @@ path_manager
 
 ### 🎰 GUI for Boosting Algorithms (XGBoost, LightGBM) [gui-boost]
 
-For GUIs that include plotting functionality, you must also install the [plot] extra.
+GUI tools compatible with XGBoost and LightGBM models used for inference.
 
 ```Bash
 pip install "dragon-ml-toolbox[gui-boost]"
 ```
 
-```Bash
-pip install "dragon-ml-toolbox[gui-boost,plot]"
-```
-
 #### Modules:
 
 ```Bash
+constants
 custom_logger
 GUI_tools
 ensemble_inference
 path_manager
+serde
 ```
 
 ---
 
 ### 🤖 GUI for PyTorch Models [gui-torch]
 
-For GUIs that include plotting functionality, you must also install the [plot] extra.
+GUI tools compatible with PyTorch models used for inference.
 
 ```Bash
 pip install "dragon-ml-toolbox[gui-torch]"
 ```
 
-```Bash
-pip install "dragon-ml-toolbox[gui-torch,plot]"
-```
-
 #### Modules:
 
 ```Bash
+constants
 custom_logger
 GUI_tools
 ML_models
@@ -255,27 +251,6 @@ path_manager
 
 ---
 
-### 🎫 Base Tools [base]
-
-General purpose functions and classes.
-
-```Bash
-pip install "dragon-ml-toolbox[base]"
-```
-
-#### Modules:
-
-```Bash
-ETL_cleaning
-ETL_engineering
-custom_logger
-SQL
-utilities
-path_manager
-```
-
----
-
 ### ⚒️ APP bundlers
 
 Choose one if needed.
@@ -293,6 +268,6 @@ pip install "dragon-ml-toolbox[nuitka]"
 After installation, import modules like this:
 
 ```python
-from ml_tools.utilities import serialize_object, deserialize_object
+from ml_tools.serde import serialize_object, deserialize_object
 from ml_tools import custom_logger
 ```

dragon_ml_toolbox-14.2.0.dist-info/RECORD

@@ -0,0 +1,48 @@
+dragon_ml_toolbox-14.2.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-14.2.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=gkOdNDbKYpIJezwSo2CEnISkLeYfYHv9t8b5K2-P69A,2687
+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=KLJXGQLKJ6AuWWttAG-LCCaxpS-ygM4dXPiguHDaL6Y,20815
+ml_tools/ML_callbacks.py,sha256=elD2Yr030sv_6gX_m9GVd6HTyrbmt34nFS8lrgS4HtM,15808
+ml_tools/ML_datasetmaster.py,sha256=rsJgZEGBJmfeKF6cR8CQZzfEx4T7Y-p1wUnR15_nNw0,28400
+ml_tools/ML_evaluation.py,sha256=4GU86rUWMIGbkXrvN6PyjfGwKtWvXKE7pMlWpWeBq14,18988
+ml_tools/ML_evaluation_multi.py,sha256=rJKdgtq-9I7oaI7PRzq7aIZ84XdNV0xzlVePZW4nj0k,16095
+ml_tools/ML_inference.py,sha256=YJ953bhNWsdlPRtJQh3h2ACfMIgp8dQ9KtL9Azar-5s,23489
+ml_tools/ML_models.py,sha256=PqOcNlws7vCJMbiVCKqlPuktxvskZVUHG3VfU-Yshf8,31415
+ml_tools/ML_models_advanced.py,sha256=vk3PZBSu3DVso2S1rKTxxdS43XG8Q5FnasIL3-rMajc,12410
+ml_tools/ML_optimization.py,sha256=P0zkhKAwTpkorIBtR0AOIDcyexo5ngmvFUzo3DfNO-E,22692
+ml_tools/ML_scaler.py,sha256=tw6onj9o8_kk3FQYb930HUzvv1zsFZe2YZJdF3LtHkU,7538
+ml_tools/ML_trainer.py,sha256=ZWI4MbUcLeBxyfoUTL96l5tjHHMp9I64h4SdXnjYmBE,49795
+ml_tools/ML_utilities.py,sha256=z6LbpbZwhn8F__fWlKi-g-cAJQXSxwg1NHfC5FBoAyc,21139
+ml_tools/ML_vision_datasetmaster.py,sha256=tOrdatuq_AP8-GDiTrtARvSJdpc8h7dT-OhDJtRQnsk,54433
+ml_tools/ML_vision_evaluation.py,sha256=t12R7i1RkOCt9zu1_lxSBr8OH6A6Get0k8ftDLctn6I,10486
+ml_tools/ML_vision_inference.py,sha256=He3KV3VJAm8PwO-fOq4b9VO8UXFr-GmpuCnoHXf4VZI,20588
+ml_tools/ML_vision_models.py,sha256=G3S4jB9AE9wMpU9ZygOgOx9q1K6t6LAXBYcJ-U2XQ1M,25600
+ml_tools/ML_vision_transformers.py,sha256=95e0aBkHY5VDGE8i5xy57COU7NvSNIgFknnhBubwE40,1832
+ml_tools/PSO_optimization.py,sha256=T-HWHMRJUnPvPwixdU5jif3_rnnI36TzcL8u3oSCwuA,22960
+ml_tools/RNN_forecast.py,sha256=Qa2KoZfdAvSjZ4yE78N4BFXtr3tTr0Gx7tQJZPotsh0,1967
+ml_tools/SQL.py,sha256=vXLPGfVVg8bfkbBE3HVfyEclVbdJy0TBhuQONtMwSCQ,11234
+ml_tools/VIF_factor.py,sha256=at5IVqPvicja2-DNSTSIIy3SkzDWCmLzo3qTG_qr5n8,10422
+ml_tools/_ML_vision_recipe.py,sha256=zrgxFUvTJqQVuwR7jWlbIC2FD29u6eNFPkTRoJ7yEZI,3178
+ml_tools/__init__.py,sha256=kJiankjz9_qXu7gU92mYqYg_anLvt-B6RtW0mMH8uGo,76
+ml_tools/_logger.py,sha256=dlp5cGbzooK9YSNSZYB4yjZrOaQUGW8PTrM411AOvL8,4717
+ml_tools/_schema.py,sha256=yu6aWmn_2Z4_AxAtJGDDCIa96y6JcUp-vgnCS013Qmw,3908
+ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
+ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
+ml_tools/custom_logger.py,sha256=TGc0Ww2Xlqj2XE3q4bP43hV7T3qnb5ci9f0pYHXF5TY,11226
+ml_tools/data_exploration.py,sha256=bwHzFJ-IAo5GN3T53F-1J_pXUg8VHS91sG_90utAsfg,69911
+ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
+ml_tools/ensemble_inference.py,sha256=0yLmLNj45RVVoSCLH1ZYJG9IoAhTkWUqEZmLOQTFGTY,9348
+ml_tools/ensemble_learning.py,sha256=vsIED7nlheYI4w2SBzP6SC1AnNeMfn-2A1Gqw5EfxsM,21964
+ml_tools/handle_excel.py,sha256=pfdAPb9ywegFkM9T54bRssDOsX-K7rSeV0RaMz7lEAo,14006
+ml_tools/keys.py,sha256=wZOBuEnnHc54vlOZiimnrxfk-sZh6f6suPppJW8rbPQ,3326
+ml_tools/math_utilities.py,sha256=xeKq1quR_3DYLgowcp4Uam_4s3JltUyOnqMOGuAiYWU,8802
+ml_tools/optimization_tools.py,sha256=TYFQ2nSnp7xxs-VyoZISWgnGJghFbsWasHjruegyJRs,12763
+ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
+ml_tools/serde.py,sha256=c8uDYjYry_VrLvoG4ixqDj5pij88lVn6Tu4NHcPkwDU,6943
+ml_tools/utilities.py,sha256=aWqvYzmxlD74PD5Yqu1VuTekDJeYLQrmPIU_VeVyRp0,22526
+dragon_ml_toolbox-14.2.0.dist-info/METADATA,sha256=T0eIxD-eO3cbAIzJ1HskJbog6RUYgXwXQQ2OU8Z-GQM,6475
+dragon_ml_toolbox-14.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-14.2.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-14.2.0.dist-info/RECORD,,

{dragon_ml_toolbox-10.2.0.dist-info → dragon_ml_toolbox-14.2.0.dist-info}/licenses/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2025 Karl Loza
+Copyright (c) 2025 Karl Luigi Loza Vidaurre
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

{dragon_ml_toolbox-10.2.0.dist-info → dragon_ml_toolbox-14.2.0.dist-info}/licenses/LICENSE-THIRD-PARTY.md

@@ -26,3 +26,14 @@ This project depends on the following third-party packages. Each is governed by
 - [polars](https://github.com/pola-rs/polars/blob/main/LICENSE)
 - [plotnine](https://github.com/has2k1/plotnine/blob/main/LICENSE)
 - [tqdm](https://github.com/tqdm/tqdm/blob/master/LICENSE)
+- [pyarrow](https://github.com/apache/arrow/blob/main/LICENSE.txt)
+- [colorlog](https://github.com/borntyping/python-colorlog/blob/main/LICENSE)
+- [evotorch](https://github.com/nnaisense/evotorch/blob/master/LICENSE)
+- [FreeSimpleGUI](https://github.com/spyoungtech/FreeSimpleGUI/blob/main/license.txt)
+- [nuitka](https://github.com/Nuitka/Nuitka/blob/main/LICENSE.txt)
+- [omegaconf](https://github.com/omry/omegaconf/blob/master/LICENSE)
+- [ordered-set](https://github.com/rspeer/ordered-set/blob/master/MIT-LICENSE)
+- [pyinstaller](https://github.com/pyinstaller/pyinstaller/blob/develop/COPYING.txt)
+- [pytorch_tabular](https://github.com/manujosephv/pytorch_tabular/blob/main/LICENSE)
+- [torchmetrics](https://github.com/Lightning-AI/torchmetrics/blob/master/LICENSE)
+- [zstandard](https://github.com/indygreg/python-zstandard/blob/main/LICENSE)

ml_tools/ETL_cleaning.py

@@ -2,9 +2,10 @@ import polars as pl
 import pandas as pd
 from pathlib import Path
 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
 
@@ -19,20 +20,26 @@ __all__ = [
 
 
 ################ Unique Values per column #################
-def save_unique_values(csv_path: Union[str, Path], output_dir: Union[str, Path], verbose: bool=False) -> None:
+def save_unique_values(csv_path: Union[str, Path], 
+                       output_dir: Union[str, Path], 
+                       verbose: bool=False,
+                       keep_column_order: bool = True) -> None:
     """
     Loads a CSV file, then analyzes it and saves the unique non-null values
     from each column into a separate text file exactly as they appear.
 
     This is useful for understanding the raw categories or range of values
-    within a dataset before cleaning.
+    within a dataset before and after cleaning.
 
     Args:
-        csv_path (Union[str, Path]):
+        csv_path (str | Path):
             The file path to the input CSV file.
-        output_dir (Union[str, Path]):
+        output_dir (str | Path):
             The path to the directory where the .txt files will be saved.
             The directory will be created if it does not exist.
+        keep_column_order (bool):
+            If True, prepends a numeric prefix (e.g., '1_', '2_') to each
+            output filename to maintain the original column order.
     """
     # --- 1. Input Validation ---
     csv_path = make_fullpath(input_path=csv_path, enforce="file")
@@ -74,7 +81,12 @@ def save_unique_values(csv_path: Union[str, Path], output_dir: Union[str, Path],
         sanitized_name = sanitize_filename(column_name)
         if not sanitized_name.strip('_'):
             sanitized_name = f'column_{i}'
-        file_path = output_dir / f"{sanitized_name}_unique_values.txt"
+        
+        # --- create filename prefix ---
+        # If keep_column_order is True, create a prefix like "1_", "2_", etc.
+        prefix = f"{i + 1}_" if keep_column_order else ''
+        
+        file_path = output_dir / f"{prefix}{sanitized_name}_unique_values.txt"
 
         # --- Write to file ---
         try:
@@ -96,7 +108,7 @@ def save_unique_values(csv_path: Union[str, Path], output_dir: Union[str, Path],
 
 
 ########## Basic df cleaners #############
-def _cleaner_core(df_in: pl.DataFrame) -> pl.DataFrame:
+def _cleaner_core(df_in: pl.DataFrame, all_lowercase: bool) -> pl.DataFrame:
     # Cleaning rules
     cleaning_rules = {
         # 1. Comprehensive Punctuation & Symbol Normalization
@@ -126,27 +138,44 @@ def _cleaner_core(df_in: pl.DataFrame) -> pl.DataFrame:
         'ｓ': 's', 'ｔ': 't', 'ｕ': 'u', 'ｖ': 'v', 'ｗ': 'w', 'ｘ': 'x',
         'ｙ': 'y', 'ｚ': 'z',
         # Punctuation
-        '》': '>', '《': '<', '：': ':', '，': ',', '。': '.', '；': ';', '【': '[', '】': ']', 
+        '》': '>', '《': '<', '：': ':', '。': '.', '；': ';', '【': '[', '】': ']', '∼': '~',
         '（': '(', '）': ')', '？': '?', '！': '!', '～': '~', '＠': '@', '＃': '#', '＋': '+', '－': '-',
-        '＄': '$', '％': '%', '＾': '^', '＆': '&', '＊': '*', '＼': '\\', '｜': '|', '、':',', '≈':'=',
+        '＄': '$', '％': '%', '＾': '^', '＆': '&', '＊': '*', '＼': '-', '｜': '|', '≈':'=', '·': '', '⋅': '',
+        '¯': '-',
+        
+        # Commas (avoid commas in entries)
+        '，': ';',
+        ',': ';',
+        '、':';',
         
         # Others
+        'σ': '',
+        '□': '',
         '©': '',
         '®': '',
         '™': '',
+        r'[°˚]': '',
         
-        # Collapse repeating punctuation
-        r'\.{2,}': '.',      # Replace two or more dots with a single dot
-        r'\?{2,}': '?',      # Replace two or more question marks with a single question mark
-        r'!{2,}': '!',      # Replace two or more exclamation marks with a single one
+        # Replace special characters in entries
+        r'\\': '_',
         
         # Typographical standardization
-        # Unify various dashes and hyphens to a standard hyphen-minus
+        # Unify various dashes and hyphens to a standard hyphen
         r'[—–―]': '-',
         r'−': '-',
-        # Unify various quote types to standard quotes
-        r'[“”]': "'",
-        r'[‘’′]': "'",
+        # remove various quote types
+        r'[“”"]': '',
+        r"[‘’′']": '',
+        
+        # Collapse repeating punctuation
+        r'\.{2,}': '.',      # Replace two or more dots with a single dot
+        r'\?{2,}': '?',      # Replace two or more question marks with a single question mark
+        r'!{2,}': '!',      # Replace two or more exclamation marks with a single one
+        r';{2,}': ';',
+        r'-{2,}': '-',
+        r'/{2,}': '/',
+        r'%{2,}': '%',
+        r'&{2,}': '&',
 
         # 2. Internal Whitespace Consolidation
         # Collapse any sequence of whitespace chars (including non-breaking spaces) to a single space
@@ -158,7 +187,7 @@ def _cleaner_core(df_in: pl.DataFrame) -> pl.DataFrame:
         
         # 4. Textual Null Standardization (New Step)
         # Convert common null-like text to actual nulls.
-        r'^(N/A|无|NA|NULL|NONE|NIL|)$': None,
+        r'^(N/A|无|NA|NULL|NONE|NIL|-|\.|;|/|%|&)$': None,
 
         # 5. Final Nullification of Empty Strings
         # After all cleaning, if a string is now empty, convert it to a null
@@ -179,9 +208,13 @@ def _cleaner_core(df_in: pl.DataFrame) -> pl.DataFrame:
         df_cleaned = df_cleaner.clean(df_in, clone_df=False) # Use clone_df=False for efficiency
         
         # apply lowercase to all string columns
-        df_final = df_cleaned.with_columns(
-            pl.col(pl.String).str.to_lowercase()
-        )
+        if all_lowercase:
+            df_final = df_cleaned.with_columns(
+                pl.col(pl.String).str.to_lowercase()
+            )
+        else:
+            df_final = df_cleaned
+
     except Exception as e:
         _LOGGER.error(f"An error occurred during the cleaning process.")
         raise e
@@ -199,7 +232,7 @@ def _path_manager(path_in: Union[str,Path], path_out: Union[str,Path]):
     return input_path, output_path
 
 
-def basic_clean(input_filepath: Union[str,Path], output_filepath: Union[str,Path]):
+def basic_clean(input_filepath: Union[str,Path], output_filepath: Union[str,Path], all_lowercase: bool=True):
     """
     Performs a comprehensive, standardized cleaning on all columns of a CSV file.
 
@@ -209,13 +242,16 @@ def basic_clean(input_filepath: Union[str,Path], output_filepath: Union[str,Path
     - Stripping any leading or trailing whitespace.
     - Converting common textual representations of null (e.g., "N/A", "NULL") to true null values.
     - Converting strings that become empty after cleaning into true null values.
-    - Normalizing all text to lowercase.
+    - Normalizing all text to lowercase (Optional).
 
     Args:
-        input_filepath (Union[str, Path]):
+        input_filepath (str | Path):
             The path to the source CSV file to be cleaned.
-        output_filepath (Union[str, Path, None], optional):
+        output_filepath (str | Path):
             The path to save the cleaned CSV file.
+        all_lowercase (bool):
+            Whether to normalize all text to lowercase.
+        
     """
     # Handle paths
     input_path, output_path = _path_manager(path_in=input_filepath, path_out=output_filepath)
@@ -224,16 +260,16 @@ def basic_clean(input_filepath: Union[str,Path], output_filepath: Union[str,Path
     df, _ = load_dataframe(df_path=input_path, kind="polars", all_strings=True)
     
     # CLEAN
-    df_final = _cleaner_core(df)
+    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.")
     
 
 def basic_clean_drop(input_filepath: Union[str,Path], output_filepath: Union[str,Path], log_directory: Union[str,Path], targets: list[str], 
-                     skip_targets: bool=False, threshold: float=0.8):
+                     skip_targets: bool=False, threshold: float=0.8, all_lowercase: bool=True):
     """
     Performs standardized cleaning followed by iterative removal of rows and 
     columns with excessive missing data.
@@ -250,12 +286,12 @@ def basic_clean_drop(input_filepath: Union[str,Path], output_filepath: Union[str
     dropping process are saved to the specified log directory.  
 
     Args:
-        input_filepath (str, Path):
+        input_filepath (str | Path):
             The path to the source CSV file to be cleaned.
-        output_filepath (str, Path):
+        output_filepath (str | Path):
             The path to save the fully cleaned CSV file after cleaning 
             and missing-data-based pruning.
-        log_directory (str, Path):
+        log_directory (str | Path):
             Path to the directory where missing data reports will be stored.
         targets (list[str]):
             A list of column names to be treated as target variables. 
@@ -267,6 +303,8 @@ def basic_clean_drop(input_filepath: Union[str,Path], output_filepath: Union[str
             The proportion of missing data required to drop a row or column. 
             For example, 0.8 means a row/column will be dropped if 80% or more 
             of its data is missing.
+        all_lowercase (bool):
+            Whether to normalize all text to lowercase.
     """
     # handle log path
     log_path = make_fullpath(log_directory, make=True, enforce="directory")
@@ -278,7 +316,7 @@ def basic_clean_drop(input_filepath: Union[str,Path], output_filepath: Union[str
     df, _ = load_dataframe(df_path=input_path, kind="polars", all_strings=True)
     
     # CLEAN
-    df_cleaned = _cleaner_core(df)
+    df_cleaned = _cleaner_core(df_in=df, all_lowercase=all_lowercase)
     
     # switch to pandas
     df_cleaned_pandas = df_cleaned.to_pandas()
@@ -291,7 +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.")
 
@@ -456,7 +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