Enable a configureable benchmark mode for flaml
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 565
- Avg merge
- 5d 8m
- Merged PRs (30d)
- 17
Description
_benchmark_ here refers to the [openml AutoML benchmark ](https://github.com/openml/automlbenchmark), which supports flaml.
Currently, under the two installation modes "pip install flaml" and "pip install flaml[benchmark]", flaml is using different settings to do automl.
TODO:
1. Make the benchmark setting configurable in flaml.automl such that users who installed using "pip install flaml[benchmark]" can also use the vanilla setting. This change will also make it possible to update the benchmark automl setting in flaml and automatically reflects the change in the openml AuotML benchmark.
2. Once the change is made in flaml, we need to update flaml's setup file in openml AutoML benchmark via [this PR ](https://github.com/openml/automlbenchmark/pull/414).
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.