Updated project with new features

.github/workflows/python-publish.yml

@@ -0,0 +1,32 @@
+name: Publish Python package
+
+on:
+  push:
+    branches:
+      - main  # Yalnız main branch-ə push ediləndə işləyəcək
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9  # Python versiyasını uyğun olaraq seçin
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install setuptools wheel twine
+
+      - name: Build distribution
+        run: |
+          python setup.py sdist bdist_wheel
+
+      - name: Upload to PyPI
+        run: |
+          python -m twine upload dist/* -u __token__ -p ${{ secrets.PYPI_API_TOKEN }}

CHANGELOG.txt

@@ -0,0 +1,10 @@
+# Changelog
+
+## [1.0.0] - 2025-01-30
+- Initial release with support for hyperparameter tuning of 20+ classifiers.
+- Implemented GridSearchCV for model evaluation and selection.
+- Added the ability to pass custom parameters for model tuning.
+- Cross-validation support integrated.
+
+## [Unreleased]
+- Future improvements and features will be added in upcoming versions.

GridSearchHelper.egg-info/PKG-INFO

@@ -0,0 +1,39 @@
+Metadata-Version: 2.2
+Name: GridSearchHelper
+Version: 0.2.0
+Summary: A library for hyperparameter tuning using grid search for machine learning models.
+Home-page: https://github.com/username/ModelTuner
+Author: Abdulla Alimov
+Author-email: [email protected]
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENCE.txt
+Requires-Dist: scikit-learn>=0.24.0
+Requires-Dist: numpy>=1.19.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Hyperparameter Tuning for Classifiers
+
+This project implements a hyperparameter tuning utility for multiple classifiers using `GridSearchCV` from `sklearn`. The supported classifiers include Random Forest, Gradient Boosting, AdaBoost, SVM, K-Nearest Neighbors, Logistic Regression, Decision Trees, Naive Bayes, MLP, and more.
+
+## Features
+- Grid search for hyperparameter optimization on a variety of models.
+- Support for additional custom parameters.
+- Cross-validation (CV) support for model evaluation.
+- Parallel processing for faster results.
+
+## Setup
+1. Clone this repository:
+   ```bash
+   git clone <repository_url>

GridSearchHelper.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+CHANGELOG.txt
+LICENCE.txt
+MANIFEST.in
+README.md
+setup.py
+GridSearchHelper/__init__.py
+GridSearchHelper/grid_search.py
+GridSearchHelper/models.py
+GridSearchHelper.egg-info/PKG-INFO
+GridSearchHelper.egg-info/SOURCES.txt
+GridSearchHelper.egg-info/dependency_links.txt
+GridSearchHelper.egg-info/not-zip-safe
+GridSearchHelper.egg-info/requires.txt
+GridSearchHelper.egg-info/top_level.txt

GridSearchHelper.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

GridSearchHelper.egg-info/not-zip-safe

@@ -0,0 +1 @@
+

GridSearchHelper.egg-info/requires.txt

@@ -0,0 +1,2 @@
+scikit-learn>=0.24.0
+numpy>=1.19.0

GridSearchHelper.egg-info/top_level.txt

@@ -0,0 +1 @@
+GridSearchHelper

GridSearchHelper/__init__.py

@@ -0,0 +1,26 @@
+# __init__.py
+
+from .models import (
+    RandomForestClassifier,
+    GradientBoostingClassifier,
+    AdaBoostClassifier,
+    ExtraTreesClassifier,
+    BaggingClassifier,
+    HistGradientBoostingClassifier,
+    SVC,
+    LinearSVC,
+    KNeighborsClassifier,
+    LogisticRegression,
+    RidgeClassifier,
+    SGDClassifier,
+    PassiveAggressiveClassifier,
+    DecisionTreeClassifier,
+    GaussianNB,
+    BernoulliNB,
+    MultinomialNB,
+    MLPClassifier,
+    LinearDiscriminantAnalysis,
+    QuadraticDiscriminantAnalysis,
+)
+
+from .grid_search import get_param_grid, perform_grid_search

GridSearchHelper/grid_search.py

@@ -0,0 +1,194 @@
+# grid_search.py
+
+from sklearn.model_selection import GridSearchCV
+from typing import Dict, Optional, Union, Tuple, Any
+import numpy as np
+from numpy.typing import ArrayLike
+
+def get_param_grid(model_name: str, additional_params: Optional[Dict[str, Union[int, float, list]]] = None) -> Dict[str, list]:
+    """
+    Seçilən modelə uyğun hiperparametr gridini qaytarır.
+    
+    Args:
+        model_name (str): Modelin adı.
+        additional_params (dict, optional): Əlavə parametrlər.
+
+    Returns:
+        dict: Parametrlər gridini qaytarır.
+    """
+    param_grids = {
+        'RandomForest': {
+            'n_estimators': [50, 100, 200, 300],
+            'max_depth': [5, 10, 15, 20, None],
+            'min_samples_split': [2, 5, 10],
+            'min_samples_leaf': [1, 2, 4],
+            'max_features': ['sqrt', 'log2', None],
+            'bootstrap': [True, False]
+        },
+        'GradientBoosting': {
+            'n_estimators': [50, 100, 200],
+            'learning_rate': [0.01, 0.05, 0.1, 0.2],
+            'max_depth': [3, 5, 7, 9],
+            'subsample': [0.8, 0.9, 1.0],
+            'min_samples_split': [2, 5, 10],
+            'min_samples_leaf': [1, 2, 4]
+        },
+        'HistGradientBoosting': {
+            'max_iter': [50, 100, 200],
+            'learning_rate': [0.01, 0.1, 0.2],
+            'max_depth': [3, 5, 7],
+            'min_samples_leaf': [1, 5, 20],
+            'l2_regularization': [0, 1.0, 10.0]
+        },
+        'AdaBoost': {
+            'n_estimators': [50, 100, 200],
+            'learning_rate': [0.01, 0.1, 1.0],
+            'algorithm': ['SAMME', 'SAMME.R']
+        },
+        'ExtraTrees': {
+            'n_estimators': [50, 100, 200],
+            'max_depth': [5, 10, 15, None],
+            'min_samples_split': [2, 5, 10],
+            'min_samples_leaf': [1, 2, 4],
+            'max_features': ['sqrt', 'log2', None]
+        },
+        'Bagging': {
+            'n_estimators': [10, 30, 50],
+            'max_samples': [0.5, 0.7, 1.0],
+            'max_features': [0.5, 0.7, 1.0],
+            'bootstrap': [True, False],
+            'bootstrap_features': [True, False]
+        },
+        'SVC': {
+            'C': [0.1, 1, 10, 100],
+            'kernel': ['linear', 'rbf', 'poly', 'sigmoid'],
+            'gamma': ['scale', 'auto'],
+            'degree': [2, 3, 4],
+            'coef0': [0.0, 0.1, 0.5]
+        },
+        'LinearSVC': {
+            'C': [0.1, 1, 10],
+            'penalty': ['l1', 'l2'],
+            'dual': [True, False],
+            'max_iter': [1000, 2000, 5000]
+        },
+        'KNeighbors': {
+            'n_neighbors': [3, 5, 7, 9, 11],
+            'weights': ['uniform', 'distance'],
+            'metric': ['euclidean', 'manhattan', 'minkowski'],
+            'p': [1, 2],
+            'leaf_size': [10, 30, 50]
+        },
+        'LogisticRegression': {
+            'C': [0.001, 0.01, 0.1, 1, 10],
+            'penalty': ['l1', 'l2', 'elasticnet', None],
+            'solver': ['lbfgs', 'liblinear', 'newton-cg', 'sag', 'saga'],
+            'max_iter': [1000, 2000, 5000],
+            'l1_ratio': [0.2, 0.5, 0.8]
+        },
+        'RidgeClassifier': {
+            'alpha': [0.1, 1.0, 10.0],
+            'solver': ['auto', 'svd', 'cholesky', 'sparse_cg'],
+            'max_iter': [None, 1000, 2000]
+        },
+        'SGDClassifier': {
+            'loss': ['hinge', 'log_loss', 'modified_huber'],
+            'penalty': ['l1', 'l2', 'elasticnet'],
+            'alpha': [0.0001, 0.001, 0.01],
+            'max_iter': [1000, 2000, 5000],
+            'learning_rate': ['constant', 'optimal', 'adaptive']
+        },
+        'PassiveAggressive': {
+            'C': [0.1, 1.0, 10.0],
+            'max_iter': [1000, 2000, 5000],
+            'early_stopping': [True, False],
+            'validation_fraction': [0.1, 0.2]
+        },
+        'DecisionTree': {
+            'max_depth': [5, 10, 15, 20, None],
+            'min_samples_split': [2, 5, 10],
+            'min_samples_leaf': [1, 2, 4],
+            'max_features': ['sqrt', 'log2', None],
+            'criterion': ['gini', 'entropy']
+        },
+        'GaussianNB': {
+            'var_smoothing': [1e-9, 1e-8, 1e-7, 1e-6]
+        },
+        'BernoulliNB': {
+            'alpha': [0.1, 0.5, 1.0],
+            'binarize': [0.0, 0.5, None],
+            'fit_prior': [True, False]
+        },
+        'MultinomialNB': {
+            'alpha': [0.1, 0.5, 1.0],
+            'fit_prior': [True, False]
+        },
+        'MLPClassifier': {
+            'hidden_layer_sizes': [(50,), (100,), (50, 50), (100, 50)],
+            'activation': ['relu', 'tanh'],
+            'solver': ['adam', 'sgd'],
+            'alpha': [0.0001, 0.001, 0.01],
+            'learning_rate': ['constant', 'adaptive'],
+            'max_iter': [1000, 2000]
+        },
+        'LinearDiscriminantAnalysis': {
+            'solver': ['svd', 'lsqr', 'eigen'],
+            'shrinkage': [None, 'auto', 0.1, 0.5, 0.9]
+        },
+        'QuadraticDiscriminantAnalysis': {
+            'reg_param': [0.0, 0.1, 0.2],
+            'tol': [1e-4, 1e-3, 1e-2]
+        }
+    }
+
+    if additional_params:
+        if model_name not in param_grids:
+            raise ValueError(f"Model '{model_name}' üçün parametrlər tapılmadı.")
+        param_grids[model_name].update(additional_params)
+
+    if model_name not in param_grids:
+        raise ValueError(f"Model adı '{model_name}' düzgün deyil. Mövcud modellər: {', '.join(param_grids.keys())}.")
+
+    return param_grids[model_name]
+
+def perform_grid_search(
+    model_name: str, 
+    X_train: ArrayLike, 
+    y_train: ArrayLike, 
+    additional_params: Optional[Dict[str, Any]] = None, 
+    cv_folds: int = 5,
+    scoring: Optional[Union[str, callable]] = None,
+    verbose: int = 0,
+    n_jobs: int = -1
+) -> Tuple[Dict[str, Any], float, GridSearchCV]:
+    """
+    Seçilən model adı ilə GridSearchCV tətbiq edir və ən yaxşı hiperparametrləri tapır.
+    
+    Args:
+        model_name (str): Modelin adı.
+        X_train (array-like): Təlim verilənlərinin xüsusiyyətləri.
+        y_train (array-like): Təlim verilənlərinin hədəf dəyişəni.
+        additional_params (dict, optional): Əlavə parametrlər.
+        cv_folds (int): Cross-validation üçün fold sayı.
+        scoring (str or callable, optional): Qiymətləndirmə metrikası.
+        verbose (int): Əlavə məlumatların çap edilməsi səviyyəsi.
+        n_jobs (int): Paralel işləmə üçün prosessor nüvələri sayı.
+
+    Returns:
+        tuple: Ən yaxşı parametrlər, ən yaxşı skor və GridSearchCV obyekti.
+    """
+    model = globals()[model_name]()  # Model adı ilə müvafiq modeli çağırır
+    param_grid = get_param_grid(model_name, additional_params)
+
+    grid_search = GridSearchCV(
+        estimator=model,
+        param_grid=param_grid,
+        cv=cv_folds,
+        scoring=scoring,
+        verbose=verbose,
+        n_jobs=n_jobs
+    )
+
+    grid_search.fit(X_train, y_train)
+
+    return grid_search.best_params_, grid_search.best_score_, grid_search

GridSearchHelper/models.py

@@ -0,0 +1,25 @@
+# models.py
+
+from sklearn.ensemble import (
+    RandomForestClassifier,
+    GradientBoostingClassifier,
+    AdaBoostClassifier,
+    ExtraTreesClassifier,
+    BaggingClassifier,
+    HistGradientBoostingClassifier,
+)
+from sklearn.svm import SVC, LinearSVC
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.linear_model import (
+    LogisticRegression,
+    RidgeClassifier,
+    SGDClassifier,
+    PassiveAggressiveClassifier,
+)
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.naive_bayes import GaussianNB, BernoulliNB, MultinomialNB
+from sklearn.neural_network import MLPClassifier
+from sklearn.discriminant_analysis import (
+    LinearDiscriminantAnalysis,
+    QuadraticDiscriminantAnalysis,
+)

LICENCE.txt

@@ -0,0 +1,24 @@
+
+### `LICENSE`
+```text
+MIT License
+
+Copyright (c) 2025
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.