English | 简体中文
What-is-AutoX?
AutoX is an efficient AutoML tool, and it is designed for the tabular data modelling for real-world datasets.
Its features include:
- SOTA: AutoX outperforms other solutions in many competition datasets(see Evaluation).
- Easy to use: The design of interfaces is similar to sklearn.
- Generic & Universal: Supporting tabular data, including binary classification, multi-class classification and regression problems.
- Auto: Fully automated pipeline without human-intervention.
- Out of the box: Providing flexible modules which can be used alone.
- Summary of magics: Organize and publish magics of competitions.
What-does-AutoX-contain?
- autox_competition: mainly for tabular table data mining competitions
- autox_server: automl service for online deployment
- autox_interpreter: machine learning interpretable function
How-to-contribute-to-AutoX?
how to contribute
Table-of-Contents
Installation
github repository installation
1. git clone https://github.com/4paradigm/autox.git
2. cd autox
3. python setup.py install
pip install
## The pip installation package may not be updated in time. It is recommended to install the latest version using the github installation method.
!pip install automl-x -i https://www.pypi.org/simple/
Quick-Start
Car sales forecast
Competition case
see demo folder
Comparison to other AutoML frameworks
Percentage improvement under different tasks
data_type |
Compare To AutoGluon |
Compare To H2o |
binary classification |
20.44% |
2.98% |
regression |
37.54% |
39.66% |
time-series |
28.40% |
32.46% |
Evaluation
Detailed dataset comparison
AutoX Achievements
Enterprise support
Competition winning
TODO
After the function development is completed, release the corresponding demo
If there are other functions that you want AutoX to support, please submit an issue!
Welcome to fill in the user survey questionnaire to make AutoX better!
Troubleshooting