dragon-ml-toolbox 1.1.6__tar.gz → 1.2.1__tar.gz

dragon_ml_toolbox-1.2.1/LICENSE-THIRD-PARTY.md

@@ -0,0 +1,23 @@
+# Third-Party Licenses
+
+This project depends on the following third-party packages. Each is governed by its own license, linked below.
+
+- [pandas](https://github.com/pandas-dev/pandas/blob/main/LICENSE)
+- [numpy](https://github.com/numpy/numpy/blob/main/LICENSE.txt)
+- [matplotlib](https://github.com/matplotlib/matplotlib/blob/main/LICENSE/LICENSE)
+- [seaborn](https://github.com/mwaskom/seaborn/blob/main/LICENSE)
+- [statsmodels](https://github.com/statsmodels/statsmodels/blob/main/LICENSE.txt)
+- [ipython](https://github.com/ipython/ipython/blob/main/COPYING.rst)
+- [torch](https://github.com/pytorch/pytorch/blob/main/LICENSE)
+- [scikit-learn](https://github.com/scikit-learn/scikit-learn/blob/main/COPYING)
+- [imblearn](https://github.com/scikit-learn-contrib/imbalanced-learn/blob/main/LICENSE)
+- [Pillow](https://github.com/python-pillow/Pillow/blob/main/LICENSE)
+- [joblib](https://github.com/joblib/joblib/blob/main/LICENSE.txt)
+- [xgboost](https://github.com/dmlc/xgboost/blob/main/LICENSE)
+- [lightgbm](https://github.com/microsoft/LightGBM/blob/master/LICENSE)
+- [shap](https://github.com/shap/shap/blob/master/LICENSE)
+- [openpyxl](https://github.com/chronossc/openpyxl/blob/main/LICENSE)
+- [miceforest](https://github.com/AnotherSamWilson/miceforest/blob/main/LICENSE)
+- [polars](https://github.com/pola-rs/polars/blob/main/LICENSE)
+- [torchvision](https://github.com/pytorch/vision/blob/main/LICENSE)
+- [pyswarm](https://pythonhosted.org/pyswarm/#license)

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.1.6
-Summary: A collection of tools for machine learning projects
+Version: 1.2.1
+Summary: A collection of tools for data science and machine learning projects
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/DrAg0n-BoRn/ML_tools
@@ -11,6 +11,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
+License-File: LICENSE-THIRD-PARTY.md
 Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: matplotlib
@@ -70,6 +71,25 @@ Provides-Extra: vision-helpers
 Requires-Dist: Pillow; extra == "vision-helpers"
 Requires-Dist: torch; extra == "vision-helpers"
 Requires-Dist: torchvision; extra == "vision-helpers"
+Provides-Extra: full
+Requires-Dist: pandas; extra == "full"
+Requires-Dist: numpy; extra == "full"
+Requires-Dist: matplotlib; extra == "full"
+Requires-Dist: seaborn; extra == "full"
+Requires-Dist: statsmodels; extra == "full"
+Requires-Dist: ipython; extra == "full"
+Requires-Dist: torch; extra == "full"
+Requires-Dist: scikit-learn; extra == "full"
+Requires-Dist: imblearn; extra == "full"
+Requires-Dist: Pillow; extra == "full"
+Requires-Dist: joblib; extra == "full"
+Requires-Dist: xgboost; extra == "full"
+Requires-Dist: lightgbm; extra == "full"
+Requires-Dist: shap; extra == "full"
+Requires-Dist: openpyxl; extra == "full"
+Requires-Dist: miceforest; extra == "full"
+Requires-Dist: polars; extra == "full"
+Requires-Dist: torchvision; extra == "full"
 Dynamic: license-file
 
 # dragon-ml-tools
@@ -85,22 +105,30 @@ A collection of Python utilities and machine learning tools, structured as a mod
 
 ## Installation
 
-### Via GitHub (Editable / Development Mode)
+Python 3.9+ recommended.
 
-Clone the repository and install in editable mode with optional dependencies:
+### Via PyPI (Stable Releases)
+
+Install the latest stable release from PyPI with optional dependencies:
 
 ```bash
-git clone https://github.com/DrAg0n-BoRn/ML_tools.git
-cd ML_tools
-pip install -e '.[logger]'
+pip install dragon-ml-tools[logger,trainer]
 ```
 
-### Via PyPI (Stable Releases)
+To install dependencies from all modules
 
-Install the latest stable release from PyPI with optional dependencies:
+```bash
+pip install dragon-ml-tools[full]
+```
+
+### Via GitHub (Editable)
+
+Clone the repository and install in editable mode with optional dependencies:
 
 ```bash
-pip install dragon-ml-tools[logger,trainer]
+git clone https://github.com/DrAg0n-BoRn/ML_tools.git
+cd ML_tools
+pip install -e '.[logger]'
 ```
 
 ## Usage
@@ -111,14 +139,3 @@ After installation, import modules like this:
 from ml_tools.utilities import sanitize_filename
 from ml_tools.logger import custom_logger
 ```
-
-## Development
-
-Python 3.9+ recommended.
-
-To install all dependencies including development tools:
-
-```python
-pip install -e '.[dev]'
-```
-

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/README.md

@@ -11,22 +11,30 @@ A collection of Python utilities and machine learning tools, structured as a mod
 
 ## Installation
 
-### Via GitHub (Editable / Development Mode)
+Python 3.9+ recommended.
 
-Clone the repository and install in editable mode with optional dependencies:
+### Via PyPI (Stable Releases)
+
+Install the latest stable release from PyPI with optional dependencies:
 
 ```bash
-git clone https://github.com/DrAg0n-BoRn/ML_tools.git
-cd ML_tools
-pip install -e '.[logger]'
+pip install dragon-ml-tools[logger,trainer]
 ```
 
-### Via PyPI (Stable Releases)
+To install dependencies from all modules
 
-Install the latest stable release from PyPI with optional dependencies:
+```bash
+pip install dragon-ml-tools[full]
+```
+
+### Via GitHub (Editable)
+
+Clone the repository and install in editable mode with optional dependencies:
 
 ```bash
-pip install dragon-ml-tools[logger,trainer]
+git clone https://github.com/DrAg0n-BoRn/ML_tools.git
+cd ML_tools
+pip install -e '.[logger]'
 ```
 
 ## Usage
@@ -37,14 +45,3 @@ After installation, import modules like this:
 from ml_tools.utilities import sanitize_filename
 from ml_tools.logger import custom_logger
 ```
-
-## Development
-
-Python 3.9+ recommended.
-
-To install all dependencies including development tools:
-
-```python
-pip install -e '.[dev]'
-```
-

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/dragon_ml_toolbox.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.1.6
-Summary: A collection of tools for machine learning projects
+Version: 1.2.1
+Summary: A collection of tools for data science and machine learning projects
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/DrAg0n-BoRn/ML_tools
@@ -11,6 +11,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
+License-File: LICENSE-THIRD-PARTY.md
 Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: matplotlib
@@ -70,6 +71,25 @@ Provides-Extra: vision-helpers
 Requires-Dist: Pillow; extra == "vision-helpers"
 Requires-Dist: torch; extra == "vision-helpers"
 Requires-Dist: torchvision; extra == "vision-helpers"
+Provides-Extra: full
+Requires-Dist: pandas; extra == "full"
+Requires-Dist: numpy; extra == "full"
+Requires-Dist: matplotlib; extra == "full"
+Requires-Dist: seaborn; extra == "full"
+Requires-Dist: statsmodels; extra == "full"
+Requires-Dist: ipython; extra == "full"
+Requires-Dist: torch; extra == "full"
+Requires-Dist: scikit-learn; extra == "full"
+Requires-Dist: imblearn; extra == "full"
+Requires-Dist: Pillow; extra == "full"
+Requires-Dist: joblib; extra == "full"
+Requires-Dist: xgboost; extra == "full"
+Requires-Dist: lightgbm; extra == "full"
+Requires-Dist: shap; extra == "full"
+Requires-Dist: openpyxl; extra == "full"
+Requires-Dist: miceforest; extra == "full"
+Requires-Dist: polars; extra == "full"
+Requires-Dist: torchvision; extra == "full"
 Dynamic: license-file
 
 # dragon-ml-tools
@@ -85,22 +105,30 @@ A collection of Python utilities and machine learning tools, structured as a mod
 
 ## Installation
 
-### Via GitHub (Editable / Development Mode)
+Python 3.9+ recommended.
 
-Clone the repository and install in editable mode with optional dependencies:
+### Via PyPI (Stable Releases)
+
+Install the latest stable release from PyPI with optional dependencies:
 
 ```bash
-git clone https://github.com/DrAg0n-BoRn/ML_tools.git
-cd ML_tools
-pip install -e '.[logger]'
+pip install dragon-ml-tools[logger,trainer]
 ```
 
-### Via PyPI (Stable Releases)
+To install dependencies from all modules
 
-Install the latest stable release from PyPI with optional dependencies:
+```bash
+pip install dragon-ml-tools[full]
+```
+
+### Via GitHub (Editable)
+
+Clone the repository and install in editable mode with optional dependencies:
 
 ```bash
-pip install dragon-ml-tools[logger,trainer]
+git clone https://github.com/DrAg0n-BoRn/ML_tools.git
+cd ML_tools
+pip install -e '.[logger]'
 ```
 
 ## Usage
@@ -111,14 +139,3 @@ After installation, import modules like this:
 from ml_tools.utilities import sanitize_filename
 from ml_tools.logger import custom_logger
 ```
-
-## Development
-
-Python 3.9+ recommended.
-
-To install all dependencies including development tools:
-
-```python
-pip install -e '.[dev]'
-```
-

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/dragon_ml_toolbox.egg-info/SOURCES.txt

@@ -1,4 +1,5 @@
 LICENSE
+LICENSE-THIRD-PARTY.md
 README.md
 pyproject.toml
 dragon_ml_toolbox.egg-info/PKG-INFO

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/dragon_ml_toolbox.egg-info/requires.txt

@@ -32,6 +32,26 @@ xgboost
 lightgbm
 shap
 
+[full]
+pandas
+numpy
+matplotlib
+seaborn
+statsmodels
+ipython
+torch
+scikit-learn
+imblearn
+Pillow
+joblib
+xgboost
+lightgbm
+shap
+openpyxl
+miceforest
+polars
+torchvision
+
 [handle_excel]
 openpyxl
 pandas

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/ml_tools/MICE_imputation.py

@@ -3,7 +3,7 @@ import miceforest as mf
 import os
 import matplotlib.pyplot as plt
 import numpy as np
-from utilities import load_dataframe, list_csv_paths
+from ml_tools.utilities import load_dataframe, list_csv_paths
 
 
 def apply_mice(df: pd.DataFrame, df_name: str, resulting_datasets: int=1, iterations: int=20, random_state: int=101):

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/ml_tools/data_exploration.py

@@ -11,12 +11,11 @@ from typing import Union, Literal, Dict, Tuple, Optional
 import os
 import sys
 import textwrap
-from utilities import sanitize_filename
+from ml_tools.utilities import sanitize_filename
 
 
 # Keep track of all available functions, show using `info()`
-__all__ = ["load_dataframe",
-           "summarize_dataframe",
+__all__ = ["summarize_dataframe",
            "drop_rows_with_missing_data",
            "split_features_targets", 
            "show_null_columns",
@@ -33,21 +32,6 @@ __all__ = ["load_dataframe",
            "drop_vif_based"]
 
 
-def load_dataframe(df_path: str) -> pd.DataFrame:
-    """
-    Loads a DataFrame from a CSV file.
-
-    Args:
-        df_path (str): Path to the CSV file.
-
-    Returns:
-        pd.DataFrame: Loaded DataFrame.
-    """
-    df = pd.read_csv(df_path, encoding='utf-8')
-    print(f"DataFrame shape {df.shape}")
-    return df
-
-
 def summarize_dataframe(df: pd.DataFrame, round_digits: int = 2):
     """
     Returns a summary DataFrame with data types, non-null counts, number of unique values,

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/ml_tools/ensemble_learning.py

@@ -21,6 +21,8 @@ from sklearn.preprocessing import StandardScaler, MaxAbsScaler, MinMaxScaler
 from sklearn.metrics import accuracy_score, classification_report, ConfusionMatrixDisplay, mean_absolute_error, mean_squared_error, r2_score, roc_curve, roc_auc_score
 import shap
 
+from .utilities import yield_dataframes_from_dir
+
 import warnings # Ignore warnings 
 warnings.filterwarnings('ignore', category=DeprecationWarning)
 warnings.filterwarnings('ignore', category=FutureWarning)
@@ -28,23 +30,6 @@ warnings.filterwarnings('ignore', category=UserWarning)
 
 
 ###### 1. Dataset Loader ######
-#Load imputed datasets as a generator
-def yield_imputed_dataframe(datasets_dir: str):
-    '''
-    Yields a tuple `(dataframe, dataframe_name)`
-    '''
-    dataset_filenames = [dataset for dataset in os.listdir(datasets_dir) if dataset.endswith(".csv")]
-    if not dataset_filenames:
-        raise IOError(f"No imputed datasets have been found at {datasets_dir}")
-    
-    for dataset_filename in dataset_filenames:
-        full_path = os.path.join(datasets_dir, dataset_filename)
-        df = pd.read_csv(full_path)
-        #remove extension
-        filename = os.path.splitext(os.path.basename(dataset_filename))[0]
-        print(f"Working on dataset: {filename}")
-        yield (df, filename)
-
 #Split a dataset into features and targets datasets
 def dataset_yielder(df: pd.DataFrame, target_cols: list[str]):
     ''' 
@@ -543,7 +528,7 @@ def get_shap_values(model, model_name: str,
             plot_size=figsize,
             max_display=max_display_features,
             alpha=0.7,
-            color=plt.get_cmap('viridis')
+            color=plt.get_cmap('viridis') # type: ignore
         )
         
         # Add professional styling
@@ -674,7 +659,7 @@ def run_pipeline(datasets_dir: str, save_dir: str, target_columns: list[str], ta
     #Check paths
     _check_paths(datasets_dir, save_dir)
     #Yield imputed dataset
-    for dataframe, dataframe_name in yield_imputed_dataframe(datasets_dir):
+    for dataframe, dataframe_name in yield_dataframes_from_dir(datasets_dir):
         #Yield features dataframe and target dataframe
         for df_features, df_target, feature_names, target_name in dataset_yielder(df=dataframe, target_cols=target_columns):
             #Dataset pipeline

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/ml_tools/logger.py

@@ -5,7 +5,7 @@ import pandas as pd
 from openpyxl.styles import Font, PatternFill
 import traceback
 import json
-from utilities import sanitize_filename
+from ml_tools.utilities import sanitize_filename
 
 
 def custom_logger(

{dragon_ml_toolbox-1.1.6 → dragon_ml_toolbox-1.2.1}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "1.1.6"
-description = "A collection of tools for machine learning projects"
+version = "1.2.1"
+description = "A collection of tools for data science and machine learning projects"
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }
 ]
@@ -99,7 +99,30 @@ vision_helpers = [
     "torchvision"
 ]
 
+full = [
+    "pandas",
+    "numpy",
+    "matplotlib",
+    "seaborn",
+    "statsmodels",
+    "ipython",
+    "torch",
+    "scikit-learn",
+    "imblearn",
+    "Pillow",
+    "joblib",
+    "xgboost",
+    "lightgbm",
+    "shap",
+    "openpyxl",
+    "miceforest",
+    "polars",
+    "torchvision"
+]
+
 [build-system]
 requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
 
+[tool.setuptools]
+packages = ["ml_tools"]