Metadata-Version: 2.4
Name: cybooster
Version: 0.1.3
Summary: A high-performance gradient boosting implementation using Cython
Home-page: https://github.com/Techtonique/cybooster
Author: T. Moudiki
Author-email: thierry.moudiki@gmail.com
License: BSD-3-Clause
Keywords: gradient boosting cython machine learning
Platform: Linux
Platform: MacOS
Platform: Windows
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: BSD License
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Operating System :: OS Independent
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: cython>=0.29.0
Requires-Dist: numpy>=1.20.0
Requires-Dist: jax>=0.3.0
Requires-Dist: jaxlib>=0.3.0
Requires-Dist: scipy>=1.6.0
Requires-Dist: scikit-learn>=0.24.0
Requires-Dist: tqdm>=4.50.0
Requires-Dist: pandas>=1.1.0
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: license-file
Dynamic: platform
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary


# `CyBooster`: A Gradient Boosting Library

`CyBooster` is a high-performance generic gradient boosting (any based learner can be used) library designed for classification and regression tasks. It is built on Cython for speed and efficiency, making it suitable for large datasets and complex models.

Each base learner is augmented with a randomized neural network (a generalization of [https://www.researchgate.net/publication/346059361_LSBoost_gradient_boosted_penalized_nonlinear_least_squares](https://www.researchgate.net/publication/346059361_LSBoost_gradient_boosted_penalized_nonlinear_least_squares) to any base learner), which allows the model to learn complex patterns in the data. The library supports both classification and regression tasks, making it versatile for various machine learning applications.

`CyBooster` is born from `mlsauce`, that might be difficult to install on some systems. This version will also be more GPU friendly, thanks to JAX. 


## Installation

To install `CyBooster`, you can use pip:

```bash
pip install cybooster --verbose
```

From GitHub:

```bash
pip install git+https://github.com/Techtonique/cybooster.git --verbose
```

## Usage

```python 
from cybooster import BoosterClassifier, BoosterRegressor
from sklearn.datasets import load_iris, load_diabetes, load_breast_cancer, load_digits, load_wine
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, mean_squared_error, root_mean_squared_error
from sklearn.linear_model import LinearRegression
from time import time 


# Regression Example
X, y = load_diabetes(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
regressor = BoosterRegressor(obj=LinearRegression(), n_estimators=100, learning_rate=0.1,
                             n_hidden_features=10, verbose=1, seed=42)
start = time()
regressor.fit(X_train, y_train)
y_pred = regressor.predict(X_test)
print(f"Elapsed: {time() - start} s")
rmse = root_mean_squared_error(y_test, y_pred)
print(f"RMSE for regression: {rmse:.4f}")

# Classification Example
X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
classifier = BoosterClassifier(obj=LinearRegression(), n_estimators=100, learning_rate=0.1,
                               n_hidden_features=10, verbose=1, seed=42)
start = time()
try: 
    classifier.fit(X_train, y_train)
except Exception as e: # this is for Windows users
    y_train = y_train.astype('int32')
    classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
print(f"Elapsed: {time() - start} s")
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy for classification: {accuracy:.4f}")

X, y = load_wine(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
classifier = BoosterClassifier(obj=LinearRegression(), n_estimators=100, learning_rate=0.1,
                               n_hidden_features=10, verbose=1, seed=42)
start = time()
try:
    classifier.fit(X_train, y_train)
except Exception as e: # this is for Windows users
    y_train = y_train.astype('int32')
    classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
print(f"Elapsed: {time() - start} s")
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy for classification: {accuracy:.4f}")

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
classifier = BoosterClassifier(obj=LinearRegression(), n_estimators=100, learning_rate=0.1,
                               n_hidden_features=10, verbose=1, seed=42)
start = time()
try: 
    classifier.fit(X_train, y_train)
except Exception as e: # this is for Windows users
    y_train = y_train.astype('int32')
    classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
print(f"Elapsed: {time() - start} s")
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy for classification: {accuracy:.4f}")

X, y = load_digits(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
classifier = BoosterClassifier(obj=LinearRegression(), n_estimators=100, learning_rate=0.1,
                               n_hidden_features=10, verbose=1, seed=42)
start = time()
try: 
    classifier.fit(X_train, y_train)
except Exception as e: # this is for Windows users
    y_train = y_train.astype('int32')
    classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
print(f"Elapsed: {time() - start} s")
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy for classification: {accuracy:.4f}")
```
