Nick Becker comments

Results 180 comments of


                                            Nick Becker

[BUG] Large memory requirements for SimpleImputer strategy median

This was resolved by https://github.com/rapidsai/cuml/pull/4817 . We now generally require less memory than the CPU scikit-learn version. Closing. ```python %load_ext gpu_memory_profiler %load_ext memory_profiler from sklearn.impute import SimpleImputer as skl_SimpleImputer from...

[BUG] terminate called after throwing an instance of 'raft::cuda_error'

We've made a variety of updates to HDBSCAN since v22.02. Does this error present if you use cuML 23.02?

[BUG] terminate called after throwing an instance of 'raft::cuda_error'

Duplicates can to some extent be seen as sample weights and and removing them might move your analysis farther away from the underlying ground truth data distribution from which your...

[BUG] terminate called after throwing an instance of 'raft::cuda_error'

@preet2312 , do you have any information about your environment (library versions) and system platforms with which you experienced this issue?

[BUG] terminate called after throwing an instance of 'raft::cuda_error'

Thanks for testing in 23.02 and creating a minimal reproducible example. I can reproduce this behavior. The underlying error appears to be that a single linkage solution can't be found...

[BUG] terminate called after throwing an instance of 'raft::cuda_error'

Thanks for the suggestions. I agree that the error is clear, but it's uncaught and causes a segfault. Python user code should ideally not cause a segfault, even if rare...

[DOC] HDBSCAN metric doc is incorrect

Closing as resolved

[BUG] Output of UMAP fit_transform() and fit().transform() should be the same

Following up from https://github.com/rapidsai/cuml/issues/5188, tagging this as a good first issue (implementing hash_input=True)

[BUG] Output of UMAP fit_transform() and fit().transform() should be the same

We'd welcome a contribution for this @Zekrom-7780 . Thanks!

TPOT stuck at 75th generation with no errors

If the maintainers are open to it, perhaps we could open a PR that validates the `n_jobs` parameter when the cuML configuration is used.