A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
MIT License
Published by sonichi over 2 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.9.6...v0.9.7
Published by sonichi over 2 years ago
_BackwardsCompatibleNumpyRng
if possible by @Yard1 in https://github.com/microsoft/FLAML/pull/421
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.9.5...v0.9.6
Published by sonichi almost 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.9.4...v0.9.5
Published by sonichi almost 3 years ago
This release enables regression models for time series forecasting. It also fixes bugs in nlp tasks, such as serialization of transformer models and automatic metrics.
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.9.3...v0.9.4
Published by sonichi almost 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.9.2...v0.9.3
Published by sonichi almost 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.9.1...v0.9.2
Published by sonichi almost 3 years ago
This release contains several feature improvements and bug fixes. For example,
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.9.0...v0.9.1
Published by qingyun-wu almost 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.8.2...v0.9.0
Published by sonichi almost 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.8.1...v0.8.2
Published by sonichi almost 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.8.0...v0.8.1
Published by sonichi almost 3 years ago
In this release, we add two nlp tasks: sequence classification and sequence regression to flaml.AutoML
, using transformer-based neural networks. Previously the nlp module was detached from flaml.AutoML
with a separate API. We redesigned the API such that the nlp tasks can be accessed from the same API as other tasks, and adding more nlp tasks in future would be easy. Thanks for the hard work @liususan091219 !
We've also continued to make more performance & feature improvements. Examples:
max_depth
. It includes the default configuration from XGBoost library. The new search space leads to significantly better performance for some regression datasets.flaml.AutoML
to be passed to the constructor. This enables multioutput regression by combining sklearn's MultioutputRegressor and flaml's AutoML.Full Changelog: https://github.com/microsoft/FLAML/compare/v0.7.1...v0.8.0
Published by sonichi almost 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.7.0...v0.7.1
Published by sonichi almost 3 years ago
New feature: multivariate time series forecasting.
_create_condition
if all candidate start points didn't return yet by @Yard1 in https://github.com/microsoft/FLAML/pull/263
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.6.9...v0.7.0
Published by sonichi about 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.6.8...v0.6.9
Published by sonichi about 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.6.7...v0.6.8
Published by sonichi about 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.6.0...v0.6.7
Published by sonichi about 3 years ago
Full Changelog: https://github.com/microsoft/FLAML/compare/v0.6.0...v0.6.6
Published by sonichi about 3 years ago
In this release, we added support for time series forecasting task and NLP model fine tuning. Also, we have made a large number of feature & performance improvements.
AutoML.fit()
API.AutoML.fit()
by using previously found start points.Minor updates
Contributors
Published by sonichi over 3 years ago
Major update:
Minor updates:
Published by sonichi over 3 years ago
Support for general config constraints and metric constraints in hyperparameter tuning