Mimic the behavior of LightGBM for sparse array inputs
Open
- Dominant language
- C++
- Stars
- 830
- Forks
- 112
- Avg merge
- 1d 12h
- Merged PRs (30d)
- 18
Description
When given a sparse array (`scipy.sparse.csr_matrix`), LightGBM assigns value 0 to all features that are not present in the sparse array. Currently, Treelite converts non-present features into NaNs. We will need to add a flag to indicate that non-present features should be converted into zeros instead.
Related: https://github.com/microsoft/LightGBM/pull/4468#issuecomment-883859996
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.