基于 Spark 的分布式机器学习库,把 LightGBM、深度学习、认知服务等算法封装成易用 API,让大数据场景下的训练和推理可以直接在集群上跑。
本地部署的 AI 量化投资研究平台,集成回测、机器学习选股与自动交易,帮个人开发者搭建从策略研究到实盘的完整量化流程。
用遗传编程自动搜索并优化机器学习流水线,涵盖特征工程、模型选择和超参数调优,省去手工试错。
三行代码就能完成训练和调参的 AutoML 框架,自动搞定表格、图像、文本和时间序列任务,省去手动选模型和调超参的麻烦。
…changed vs 4.0.0a0 Removed from core dependencies lightgbm , cloudpickle , psutil , xxhash , matplotlib , kaleido , nbformat , ipywidgets — all lazy-imported with gracefu
…rained exclusively on real data. 2. Added TabPrep-LightGBM, a LightGBM model with custom preprocessing logic including target mean encoding and feature crossing. 3. Added
…</code - <b <a href="https://github.com/microsoft/LightGBM" LightGBM</a </b (🥈42 · ⭐ 18K · 📈) - A fast, distributed, high performance gradient boosting (GBT, GBDT,.. <c
Add tweedie objective to LightGBM options [ 722](https://github.com/onnx/onnxmltools/pull/722) Support for "huber" objective in the LGBM Booster [ 705](https://github.com
…enders/pull/1608 Remove early stopping round from LightGBM example notebook in https://github.com/microsoft/recommenders/pull/1620 Other features Enable Python 3.8 and 3.
…hms or improvements Improve algos visibility 1542 LightGBM test improvement 1531 Fix Surprise and Python 3.7 1540 TF-IDF runtime enhancement changes 1571 Add Spark 3.x su