dragon-ml-toolbox 11.1.1__tar.gz → 12.0.1__tar.gz

{dragon_ml_toolbox-11.1.1/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-12.0.1}/PKG-INFO

@@ -1,14 +1,14 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 11.1.1
+Version: 12.0.1
 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
@@ -47,9 +47,6 @@ Requires-Dist: lightgbm<=4.5.0; extra == "mice"
 Requires-Dist: shap; extra == "mice"
 Requires-Dist: colorlog; extra == "mice"
 Requires-Dist: pyarrow; extra == "mice"
-Provides-Extra: pytorch
-Requires-Dist: torch; extra == "pytorch"
-Requires-Dist: torchvision; extra == "pytorch"
 Provides-Extra: excel
 Requires-Dist: pandas; extra == "excel"
 Requires-Dist: openpyxl; extra == "excel"
@@ -68,9 +65,6 @@ 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
@@ -90,7 +84,7 @@ A collection of Python utilities for data science and machine learning, structur
 
 ## Installation
 
-**Python 3.10+**
+**Python 3.12**
 
 ### Via PyPI
 
@@ -100,22 +94,22 @@ 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
@@ -128,13 +122,7 @@ 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:
 
@@ -147,6 +135,7 @@ ensemble_inference
 ensemble_learning
 ETL_cleaning
 ETL_engineering
+math_utilities
 ML_callbacks
 ML_datasetmaster
 ML_evaluation_multi
@@ -156,10 +145,12 @@ ML_models
 ML_optimization
 ML_scaler
 ML_trainer
+ML_utilities
 optimization_tools
 path_manager
 PSO_optimization
 RNN_forecast
+serde
 SQL
 utilities
 ```
@@ -179,7 +170,9 @@ pip install "dragon-ml-toolbox[mice]"
 ```Bash
 constants
 custom_logger
+math_utilities
 MICE_imputation
+serde
 VIF_factor
 path_manager
 utilities
@@ -208,16 +201,12 @@ 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
@@ -226,22 +215,19 @@ 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
@@ -273,6 +259,6 @@ 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-11.1.1 → dragon_ml_toolbox-12.0.1}/README.md

@@ -9,7 +9,7 @@ A collection of Python utilities for data science and machine learning, structur
 
 ## Installation
 
-**Python 3.10+**
+**Python 3.12**
 
 ### Via PyPI
 
@@ -19,22 +19,22 @@ 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
@@ -47,13 +47,7 @@ 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:
 
@@ -66,6 +60,7 @@ ensemble_inference
 ensemble_learning
 ETL_cleaning
 ETL_engineering
+math_utilities
 ML_callbacks
 ML_datasetmaster
 ML_evaluation_multi
@@ -75,10 +70,12 @@ ML_models
 ML_optimization
 ML_scaler
 ML_trainer
+ML_utilities
 optimization_tools
 path_manager
 PSO_optimization
 RNN_forecast
+serde
 SQL
 utilities
 ```
@@ -98,7 +95,9 @@ pip install "dragon-ml-toolbox[mice]"
 ```Bash
 constants
 custom_logger
+math_utilities
 MICE_imputation
+serde
 VIF_factor
 path_manager
 utilities
@@ -127,16 +126,12 @@ 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
@@ -145,22 +140,19 @@ 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
@@ -192,6 +184,6 @@ 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-11.1.1 → dragon_ml_toolbox-12.0.1/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,14 +1,14 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 11.1.1
+Version: 12.0.1
 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
@@ -47,9 +47,6 @@ Requires-Dist: lightgbm<=4.5.0; extra == "mice"
 Requires-Dist: shap; extra == "mice"
 Requires-Dist: colorlog; extra == "mice"
 Requires-Dist: pyarrow; extra == "mice"
-Provides-Extra: pytorch
-Requires-Dist: torch; extra == "pytorch"
-Requires-Dist: torchvision; extra == "pytorch"
 Provides-Extra: excel
 Requires-Dist: pandas; extra == "excel"
 Requires-Dist: openpyxl; extra == "excel"
@@ -68,9 +65,6 @@ 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
@@ -90,7 +84,7 @@ A collection of Python utilities for data science and machine learning, structur
 
 ## Installation
 
-**Python 3.10+**
+**Python 3.12**
 
 ### Via PyPI
 
@@ -100,22 +94,22 @@ 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
@@ -128,13 +122,7 @@ 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:
 
@@ -147,6 +135,7 @@ ensemble_inference
 ensemble_learning
 ETL_cleaning
 ETL_engineering
+math_utilities
 ML_callbacks
 ML_datasetmaster
 ML_evaluation_multi
@@ -156,10 +145,12 @@ ML_models
 ML_optimization
 ML_scaler
 ML_trainer
+ML_utilities
 optimization_tools
 path_manager
 PSO_optimization
 RNN_forecast
+serde
 SQL
 utilities
 ```
@@ -179,7 +170,9 @@ pip install "dragon-ml-toolbox[mice]"
 ```Bash
 constants
 custom_logger
+math_utilities
 MICE_imputation
+serde
 VIF_factor
 path_manager
 utilities
@@ -208,16 +201,12 @@ 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
@@ -226,22 +215,19 @@ 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
@@ -273,6 +259,6 @@ 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-11.1.1 → dragon_ml_toolbox-12.0.1}/dragon_ml_toolbox.egg-info/SOURCES.txt

@@ -20,6 +20,7 @@ ml_tools/ML_models.py
 ml_tools/ML_optimization.py
 ml_tools/ML_scaler.py
 ml_tools/ML_trainer.py
+ml_tools/ML_utilities.py
 ml_tools/PSO_optimization.py
 ml_tools/RNN_forecast.py
 ml_tools/SQL.py
@@ -35,6 +36,8 @@ ml_tools/ensemble_inference.py
 ml_tools/ensemble_learning.py
 ml_tools/handle_excel.py
 ml_tools/keys.py
+ml_tools/math_utilities.py
 ml_tools/optimization_tools.py
 ml_tools/path_manager.py
+ml_tools/serde.py
 ml_tools/utilities.py

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/dragon_ml_toolbox.egg-info/requires.txt

@@ -62,13 +62,5 @@ nuitka
 zstandard
 ordered-set
 
-[plot]
-matplotlib
-seaborn
-
 [pyinstaller]
 pyinstaller
-
-[pytorch]
-torch
-torchvision

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/ETL_cleaning.py

@@ -2,6 +2,7 @@ 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

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/ETL_engineering.py

@@ -2,6 +2,7 @@ import polars as pl
 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 .path_manager import make_fullpath
 from ._script_info import _script_info
@@ -370,8 +371,20 @@ class AutoDummifier:
                           Column names are auto-generated by Polars as
                           '{original_col_name}_{category_value}'.
         """
-        # Ensure the column is treated as a string before creating dummies
-        return column.cast(pl.Utf8).to_dummies(drop_first=self.drop_first)
+        # Store the original column name to construct the potential null column name
+        col_name = column.name
+
+        # Create the dummy variables from the series
+        dummies = column.cast(pl.Utf8).to_dummies(drop_first=self.drop_first)
+
+        # Define the name of the column that Polars creates for null values
+        null_col_name = f"{col_name}_null"
+
+        # Check if the null column exists and drop it if it does
+        if null_col_name in dummies.columns:
+            return dummies.drop(null_col_name)
+
+        return dummies
 
 
 class MultiBinaryDummifier:
@@ -388,7 +401,7 @@ class MultiBinaryDummifier:
             A list of strings, where each string is a keyword to search for. A separate
             binary column will be created for each keyword.
         case_insensitive (bool):
-            If True, keyword matching ignores case. Defaults to True.
+            If True, keyword matching ignores case.
     """
     def __init__(self, keywords: List[str], case_insensitive: bool = True):
         if not isinstance(keywords, list) or not all(isinstance(k, str) for k in keywords):
@@ -944,8 +957,7 @@ class RatioCalculator:
 
 class TriRatioCalculator:
     """
-    A transformer that handles three-part ("A:B:C") and two-part ("A:C")
-    ratios, enforcing a strict output structure.
+    A transformer that handles three-part ("A:B:C") ratios, enforcing a strict output structure.
 
     - Three-part ratios produce A/B and A/C.
     - Two-part ratios are assumed to be A:C and produce None for A/B.

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/GUI_tools.py

@@ -4,8 +4,9 @@ import traceback
 import FreeSimpleGUI as sg
 from functools import wraps
 from typing import Any, Dict, Tuple, List, Literal, Union, Optional, Callable
-from ._script_info import _script_info
 import numpy as np
+
+from ._script_info import _script_info
 from ._logger import _LOGGER
 from .keys import _OneHotOtherPlaceholder
 

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/MICE_imputation.py

@@ -3,13 +3,16 @@ import miceforest as mf
 from pathlib import Path
 import matplotlib.pyplot as plt
 import numpy as np
-from .utilities import load_dataframe, merge_dataframes, save_dataframe, threshold_binary_values
-from .path_manager import sanitize_filename, make_fullpath, list_csv_paths
 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 .math_utilities import threshold_binary_values
+from .path_manager import sanitize_filename, make_fullpath, list_csv_paths
 from ._logger import _LOGGER
 from ._script_info import _script_info
 
+
 __all__ = [
     "apply_mice",
     "save_imputed_datasets",

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/ML_callbacks.py

@@ -1,13 +1,13 @@
 import numpy as np
 import torch
 from tqdm.auto import tqdm
+from typing import Union, Literal, Optional
+from pathlib import Path
+
 from .path_manager import make_fullpath, sanitize_filename
 from .keys import PyTorchLogKeys
 from ._logger import _LOGGER
-from typing import Optional
 from ._script_info import _script_info
-from typing import Union, Literal
-from pathlib import Path
 
 
 __all__ = [

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/ML_datasetmaster.py

@@ -10,6 +10,7 @@ from torchvision.datasets import ImageFolder
 from torchvision import transforms
 import matplotlib.pyplot as plt
 from pathlib import Path
+
 from .path_manager import make_fullpath, sanitize_filename
 from ._logger import _LOGGER
 from ._script_info import _script_info

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/ML_evaluation.py

@@ -18,9 +18,10 @@ from sklearn.metrics import (
 import torch
 import shap
 from pathlib import Path
+from typing import Union, Optional, List
+
 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
 

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/ML_evaluation_multi.py

@@ -25,6 +25,7 @@ from .path_manager import make_fullpath, sanitize_filename
 from ._logger import _LOGGER
 from ._script_info import _script_info
 
+
 __all__ = [
     "multi_target_regression_metrics",
     "multi_label_classification_metrics",

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/ML_inference.py

@@ -11,6 +11,7 @@ from ._logger import _LOGGER
 from .path_manager import make_fullpath
 from .keys import PyTorchInferenceKeys
 
+
 __all__ = [
     "PyTorchInferenceHandler",
     "PyTorchInferenceHandlerMulti",

{dragon_ml_toolbox-11.1.1 → dragon_ml_toolbox-12.0.1}/ml_tools/ML_models.py

@@ -3,6 +3,7 @@ from torch import nn
 from typing import List, Union, Tuple, Dict, Any
 from pathlib import Path
 import json
+
 from ._logger import _LOGGER
 from .path_manager import make_fullpath
 from ._script_info import _script_info
@@ -155,6 +156,7 @@ class _BaseAttention(_BaseMLP):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         # By default, models inheriting this do not have the flag.
+        self.attention = None
         self.has_interpretable_attention = False
     
     def forward(self, x: torch.Tensor) -> torch.Tensor:
@@ -165,7 +167,7 @@ class _BaseAttention(_BaseMLP):
     def forward_attention(self, x: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
         """Returns logits and attention weights."""
         # This logic is now shared and defined in one place
-        x, attention_weights = self.attention(x)
+        x, attention_weights = self.attention(x) # type: ignore
         x = self.mlp(x)
         logits = self.output_layer(x)
         return logits, attention_weights