simpleml-auronss 0.1.0__tar.gz

simpleml_auronss-0.1.0/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2026 Serge Auronss Gbaguidi
+
+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.

simpleml_auronss-0.1.0/PKG-INFO

@@ -0,0 +1,276 @@
+Metadata-Version: 2.4
+Name: simpleml-auronss
+Version: 0.1.0
+Summary: A lightweight, educational scikit-learn-like machine learning library
+Author: Serge Auronss Gbaguidi
+License: MIT
+Project-URL: Homepage, https://github.com/auronssms/simpleml
+Project-URL: Repository, https://github.com/auronssms/simpleml
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.19.0
+Provides-Extra: dev
+Requires-Dist: pytest>=6.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=2.10.0; extra == "dev"
+Dynamic: license-file
+
+# simpleml
+
+A lightweight, educational implementation of a scikit-learn-like machine learning library in pure Python and NumPy.
+
+## Features
+
+- **Classification Models**: Logistic Regression, Decision Trees, Random Forests, Naive Bayes, Support Vector Classifiers
+- **Regression Models**: Linear Regression, Decision Tree Regression, Random Forest Regression, Support Vector Regression
+- **Clustering Algorithms**: K-Means, DBSCAN
+- **Preprocessing**: StandardScaler, MinMaxScaler, OneHotEncoder
+- **Model Selection**: K-Fold Cross-Validation, Grid Search, Cross-Validation
+- **Metrics**: Accuracy, Precision, Recall, F1-Score, Confusion Matrix, MSE, MAE, R² Score
+- **Consistent API**: Inspired by scikit-learn's fit-predict interface
+
+## Installation
+
+```bash
+git clone https://github.com/sergeauronss01/simpleml.git
+cd simpleml
+pip install -r requirements.txt
+```
+
+## Quick Start
+
+### Basic Classification
+
+```python
+from simpleml.linear_model import LogisticRegression
+from simpleml.preprocessing import StandardScaler
+from simpleml.model_selection import train_test_split
+from simpleml.metrics import accuracy_score
+import numpy as np
+
+# Generate sample data
+X = np.random.randn(100, 5)
+y = np.random.randint(0, 2, 100)
+
+# Split data
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Preprocess
+scaler = StandardScaler()
+X_train = scaler.fit_transform(X_train)
+X_test = scaler.transform(X_test)
+
+# Train model
+clf = LogisticRegression(n_iterations=1000)
+clf.fit(X_train, y_train)
+
+# Evaluate
+y_pred = clf.predict(X_test)
+print(f"Accuracy: {accuracy_score(y_test, y_pred)}")
+```
+
+### Decision Tree Classifier
+
+```python
+from simpleml.tree import DecisionTreeClassifier
+
+X = np.array([[0, 0], [1, 1], [0, 1], [1, 0]])
+y = np.array([0, 1, 1, 0])
+
+clf = DecisionTreeClassifier(max_depth=3)
+clf.fit(X, y)
+predictions = clf.predict(X)
+```
+
+### Random Forest
+
+```python
+from simpleml.ensemble import RandomForestClassifier
+
+clf = RandomForestClassifier(n_estimators=10, random_state=42)
+clf.fit(X_train, y_train)
+predictions = clf.predict(X_test)
+```
+
+### K-Means Clustering
+
+```python
+from simpleml.cluster import KMeans
+
+kmeans = KMeans(n_clusters=3, random_state=42)
+kmeans.fit(X)
+labels = kmeans.predict(X_new)
+```
+
+### Cross-Validation
+
+```python
+from simpleml.model_selection import cross_validate
+
+scores = cross_validate(clf, X, y, cv=5)
+print(f"Mean test score: {scores['mean_test_score']}")
+```
+
+### Grid Search
+
+```python
+from simpleml.model_selection import GridSearchCV
+
+param_grid = {
+    'learning_rate': [0.01, 0.1],
+    'n_iterations': [100, 500],
+}
+
+gs = GridSearchCV(clf, param_grid, cv=5)
+gs.fit(X_train, y_train)
+print(f"Best parameters: {gs.best_params_}")
+```
+
+## Module Structure
+
+```
+simpleml/
+├── __init__.py              # Package initialization
+├── base.py                  # Base classes (BaseEstimator, ClassifierMixin, etc.)
+├── linear_model.py          # Linear regression and classification
+├── tree.py                  # Decision tree models
+├── ensemble.py              # Ensemble methods
+├── cluster.py               # Clustering algorithms
+├── naive_bayes.py           # Naive Bayes classifiers
+├── svm.py                   # Support Vector Machines
+├── preprocessing.py         # Data preprocessing
+├── model_selection.py       # Model selection and evaluation
+├── metrics.py               # Evaluation metrics
+└── utils.py                 # Utility functions
+```
+
+## Available Models
+
+### Supervised Learning
+
+#### Classification
+- `LogisticRegression`: Binary logistic regression with gradient descent
+- `DecisionTreeClassifier`: Decision tree with Gini/Entropy splits
+- `RandomForestClassifier`: Ensemble of decision trees
+- `GaussianNaiveBayes`: Gaussian Naive Bayes classifier
+- `MultinomialNaiveBayes`: Multinomial Naive Bayes for discrete features
+- `LinearSVC`: Linear Support Vector Classifier
+
+#### Regression
+- `LinearRegression`: Ordinary least squares regression
+- `DecisionTreeRegressor`: Decision tree regression
+- `RandomForestRegressor`: Ensemble regression
+- `SVR`: Support Vector Regression
+
+### Unsupervised Learning
+
+#### Clustering
+- `KMeans`: K-Means clustering algorithm
+- `DBSCAN`: Density-based clustering
+
+### Preprocessing
+
+- `StandardScaler`: Standardization (zero mean, unit variance)
+- `MinMaxScaler`: Min-Max scaling to a fixed range
+- `OneHotEncoder`: One-hot encoding for categorical features
+
+### Model Selection
+
+- `KFold`: K-Fold cross-validator
+- `cross_validate()`: Cross-validation scoring
+- `GridSearchCV`: Exhaustive grid search
+
+## Metrics
+
+All metrics are available in `simpleml.metrics`:
+
+- `accuracy_score`: Classification accuracy
+- `precision_score`: Precision for binary classification
+- `recall_score`: Recall for binary classification
+- `f1_score`: F1-Score for binary classification
+- `confusion_matrix`: Confusion matrix
+- `mean_squared_error`: Mean squared error
+- `mean_absolute_error`: Mean absolute error
+- `r2_score`: R² coefficient of determination
+
+## Testing
+
+Run the test suite:
+
+```bash
+pytest tests/ -v
+```
+
+Run tests with coverage:
+
+```bash
+pytest tests/ --cov=simpleml
+```
+
+## Documentation
+
+Each module is thoroughly documented with docstrings following NumPy style. Use `help()` in Python:
+
+```python
+from simpleml.linear_model import LogisticRegression
+help(LogisticRegression)
+```
+
+## Design Philosophy
+
+This library is designed to:
+
+1. **Educate**: Clear, understandable implementations without external ML dependencies
+2. **Mirror scikit-learn**: Familiar API for users of scikit-learn
+3. **Be extensible**: Easy to add new models and algorithms
+4. **Be tested**: Comprehensive test coverage
+
+## Limitations
+
+- No support for neural networks or deep learning
+- No GPU acceleration
+- Limited to basic algorithms (no advanced techniques like stacking, boosting beyond basic implementation)
+- Not optimized for large-scale datasets
+
+## Performance
+
+This library is for educational purposes. For production use and performance-critical applications, use scikit-learn or similar production libraries.
+
+## Contributing
+
+To contribute:
+
+1. Fork the repository
+2. Create a feature branch
+3. Write tests for new functionality
+4. Ensure all tests pass
+5. Submit a pull request
+
+## License
+
+MIT License
+
+## Author
+
+Serge Auronss Gbaguidi
+
+## References
+
+- Scikit-learn documentation: https://scikit-learn.org
+- NumPy documentation: https://numpy.org
+- Machine Learning fundamentals
+
+---
+
+**Note**: This is an educational project created to understand machine learning algorithms and best practices for library design. For production machine learning work, please use [scikit-learn](https://scikit-learn.org/).

simpleml_auronss-0.1.0/README.md

@@ -0,0 +1,248 @@
+# simpleml
+
+A lightweight, educational implementation of a scikit-learn-like machine learning library in pure Python and NumPy.
+
+## Features
+
+- **Classification Models**: Logistic Regression, Decision Trees, Random Forests, Naive Bayes, Support Vector Classifiers
+- **Regression Models**: Linear Regression, Decision Tree Regression, Random Forest Regression, Support Vector Regression
+- **Clustering Algorithms**: K-Means, DBSCAN
+- **Preprocessing**: StandardScaler, MinMaxScaler, OneHotEncoder
+- **Model Selection**: K-Fold Cross-Validation, Grid Search, Cross-Validation
+- **Metrics**: Accuracy, Precision, Recall, F1-Score, Confusion Matrix, MSE, MAE, R² Score
+- **Consistent API**: Inspired by scikit-learn's fit-predict interface
+
+## Installation
+
+```bash
+git clone https://github.com/sergeauronss01/simpleml.git
+cd simpleml
+pip install -r requirements.txt
+```
+
+## Quick Start
+
+### Basic Classification
+
+```python
+from simpleml.linear_model import LogisticRegression
+from simpleml.preprocessing import StandardScaler
+from simpleml.model_selection import train_test_split
+from simpleml.metrics import accuracy_score
+import numpy as np
+
+# Generate sample data
+X = np.random.randn(100, 5)
+y = np.random.randint(0, 2, 100)
+
+# Split data
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Preprocess
+scaler = StandardScaler()
+X_train = scaler.fit_transform(X_train)
+X_test = scaler.transform(X_test)
+
+# Train model
+clf = LogisticRegression(n_iterations=1000)
+clf.fit(X_train, y_train)
+
+# Evaluate
+y_pred = clf.predict(X_test)
+print(f"Accuracy: {accuracy_score(y_test, y_pred)}")
+```
+
+### Decision Tree Classifier
+
+```python
+from simpleml.tree import DecisionTreeClassifier
+
+X = np.array([[0, 0], [1, 1], [0, 1], [1, 0]])
+y = np.array([0, 1, 1, 0])
+
+clf = DecisionTreeClassifier(max_depth=3)
+clf.fit(X, y)
+predictions = clf.predict(X)
+```
+
+### Random Forest
+
+```python
+from simpleml.ensemble import RandomForestClassifier
+
+clf = RandomForestClassifier(n_estimators=10, random_state=42)
+clf.fit(X_train, y_train)
+predictions = clf.predict(X_test)
+```
+
+### K-Means Clustering
+
+```python
+from simpleml.cluster import KMeans
+
+kmeans = KMeans(n_clusters=3, random_state=42)
+kmeans.fit(X)
+labels = kmeans.predict(X_new)
+```
+
+### Cross-Validation
+
+```python
+from simpleml.model_selection import cross_validate
+
+scores = cross_validate(clf, X, y, cv=5)
+print(f"Mean test score: {scores['mean_test_score']}")
+```
+
+### Grid Search
+
+```python
+from simpleml.model_selection import GridSearchCV
+
+param_grid = {
+    'learning_rate': [0.01, 0.1],
+    'n_iterations': [100, 500],
+}
+
+gs = GridSearchCV(clf, param_grid, cv=5)
+gs.fit(X_train, y_train)
+print(f"Best parameters: {gs.best_params_}")
+```
+
+## Module Structure
+
+```
+simpleml/
+├── __init__.py              # Package initialization
+├── base.py                  # Base classes (BaseEstimator, ClassifierMixin, etc.)
+├── linear_model.py          # Linear regression and classification
+├── tree.py                  # Decision tree models
+├── ensemble.py              # Ensemble methods
+├── cluster.py               # Clustering algorithms
+├── naive_bayes.py           # Naive Bayes classifiers
+├── svm.py                   # Support Vector Machines
+├── preprocessing.py         # Data preprocessing
+├── model_selection.py       # Model selection and evaluation
+├── metrics.py               # Evaluation metrics
+└── utils.py                 # Utility functions
+```
+
+## Available Models
+
+### Supervised Learning
+
+#### Classification
+- `LogisticRegression`: Binary logistic regression with gradient descent
+- `DecisionTreeClassifier`: Decision tree with Gini/Entropy splits
+- `RandomForestClassifier`: Ensemble of decision trees
+- `GaussianNaiveBayes`: Gaussian Naive Bayes classifier
+- `MultinomialNaiveBayes`: Multinomial Naive Bayes for discrete features
+- `LinearSVC`: Linear Support Vector Classifier
+
+#### Regression
+- `LinearRegression`: Ordinary least squares regression
+- `DecisionTreeRegressor`: Decision tree regression
+- `RandomForestRegressor`: Ensemble regression
+- `SVR`: Support Vector Regression
+
+### Unsupervised Learning
+
+#### Clustering
+- `KMeans`: K-Means clustering algorithm
+- `DBSCAN`: Density-based clustering
+
+### Preprocessing
+
+- `StandardScaler`: Standardization (zero mean, unit variance)
+- `MinMaxScaler`: Min-Max scaling to a fixed range
+- `OneHotEncoder`: One-hot encoding for categorical features
+
+### Model Selection
+
+- `KFold`: K-Fold cross-validator
+- `cross_validate()`: Cross-validation scoring
+- `GridSearchCV`: Exhaustive grid search
+
+## Metrics
+
+All metrics are available in `simpleml.metrics`:
+
+- `accuracy_score`: Classification accuracy
+- `precision_score`: Precision for binary classification
+- `recall_score`: Recall for binary classification
+- `f1_score`: F1-Score for binary classification
+- `confusion_matrix`: Confusion matrix
+- `mean_squared_error`: Mean squared error
+- `mean_absolute_error`: Mean absolute error
+- `r2_score`: R² coefficient of determination
+
+## Testing
+
+Run the test suite:
+
+```bash
+pytest tests/ -v
+```
+
+Run tests with coverage:
+
+```bash
+pytest tests/ --cov=simpleml
+```
+
+## Documentation
+
+Each module is thoroughly documented with docstrings following NumPy style. Use `help()` in Python:
+
+```python
+from simpleml.linear_model import LogisticRegression
+help(LogisticRegression)
+```
+
+## Design Philosophy
+
+This library is designed to:
+
+1. **Educate**: Clear, understandable implementations without external ML dependencies
+2. **Mirror scikit-learn**: Familiar API for users of scikit-learn
+3. **Be extensible**: Easy to add new models and algorithms
+4. **Be tested**: Comprehensive test coverage
+
+## Limitations
+
+- No support for neural networks or deep learning
+- No GPU acceleration
+- Limited to basic algorithms (no advanced techniques like stacking, boosting beyond basic implementation)
+- Not optimized for large-scale datasets
+
+## Performance
+
+This library is for educational purposes. For production use and performance-critical applications, use scikit-learn or similar production libraries.
+
+## Contributing
+
+To contribute:
+
+1. Fork the repository
+2. Create a feature branch
+3. Write tests for new functionality
+4. Ensure all tests pass
+5. Submit a pull request
+
+## License
+
+MIT License
+
+## Author
+
+Serge Auronss Gbaguidi
+
+## References
+
+- Scikit-learn documentation: https://scikit-learn.org
+- NumPy documentation: https://numpy.org
+- Machine Learning fundamentals
+
+---
+
+**Note**: This is an educational project created to understand machine learning algorithms and best practices for library design. For production machine learning work, please use [scikit-learn](https://scikit-learn.org/).

simpleml_auronss-0.1.0/pyproject.toml

@@ -0,0 +1,50 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "simpleml-auronss"
+version = "0.1.0"
+description = "A lightweight, educational scikit-learn-like machine learning library"
+readme = "README.md"
+requires-python = ">=3.7"
+license = {text = "MIT"}
+authors = [
+    { name = "Serge Auronss Gbaguidi" },
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.7",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Education",
+    "Intended Audience :: Developers",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "numpy>=1.19.0",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/auronssms/simpleml"
+"Repository" = "https://github.com/auronssms/simpleml"
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=6.0.0",
+    "pytest-cov>=2.10.0",
+]
+
+[tool.setuptools.packages.find]
+where = ["."]
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+addopts = "-ra -q --cov=simpleml"
+testpaths = [
+    "tests",
+]

simpleml_auronss-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

simpleml_auronss-0.1.0/simpleml/__init__.py

@@ -0,0 +1,41 @@
+"""
+sklearn-lite: A lightweight machine learning library inspired by scikit-learn.
+
+Modules:
+    tree: Decision tree models
+    linear_model: Linear regression and classification models
+    svm: Support Vector Machines
+    ensemble: Ensemble methods
+    naive_bayes: Naive Bayes classifiers
+    cluster: Clustering algorithms
+    preprocessing: Data preprocessing utilities
+    model_selection: Model selection and evaluation tools
+    metrics: Metrics for model evaluation
+"""
+
+__version__ = "0.1.0"
+__author__ = "sergeauronss01"
+
+from . import (
+    tree,
+    linear_model,
+    svm,
+    ensemble,
+    naive_bayes,
+    cluster,
+    preprocessing,
+    model_selection,
+    metrics,
+)
+
+__all__ = [
+    "tree",
+    "linear_model",
+    "svm",
+    "ensemble",
+    "naive_bayes",
+    "cluster",
+    "preprocessing",
+    "model_selection",
+    "metrics",
+]