boosters#

boosters is a high-performance gradient boosting library for Python and Rust.

⚡ Fast · Rust core | 🔌 Compatible · sklearn API | 🎯 Flexible · GBDT & GBLinear | 🔍 Explainable · SHAP values |

Installation#

pip

pip install boosters

uv

uv pip install boosters

From source

git clone https://github.com/egordm/booste-rs
cd booste-rs
pip install -e packages/boosters-python

Quick Example#

from boosters.sklearn import GBDTRegressor

model = GBDTRegressor(n_estimators=100, max_depth=6)
model.fit(X_train, y_train)
predictions = model.predict(X_test)

Learn#

How to use boosters?

Installation — Installation
Choosing an API — sklearn vs Core API
User Guide — All guides

Hands-on examples

Tutorial 01: Basic GBDT Training — Your first model
Tutorial 03: Binary Classification — Classification
Tutorials — All tutorials

Reference#

API Documentation

Python API — Python API
Rust API — Rust API (docs.rs)

Research & Design

Research — Algorithm deep dives
RFCs — Design documents
Full Benchmark Report — Benchmarks

Community#

Contributing

Development Setup — Development setup
Architecture — Architecture overview

Tools

boosters-eval — Evaluation framework