2.2.0

What's Changed

• Fix issues arising from working with a low number of genes by @daemontus in #2
• Don't fail when KDE bandwidth is 0 by @daemontus in #3

New Contributors

• @daemontus made their first contribution in #2

Full Changelog: v2.1.0...v2.2.0

Enhanced UX (easier integration with scanpy)

Added a decorator to force transform_output="pandas" when calling scBoolSeq().fit(X) / scBoolSeq().transform(X) / scBoolSeq().binarize(X).

This means that scBoolSeq can now be effortlessly integrated in scRNA-seq pipelines currently using scanpy, without using with sklearn.config_context(transform_output="pandas").

Parallel processing is now performed using sklearn.model_selection.KFold(n_workers, shuffle=False).split(df), rather than numpy.array_split(df) which would raise a FutureWarning, and won't be fixed as explained in numpy issue #24889.

2.0.1

• fix sample_counts method when there are more threads than genes

2.0: Pure python implementation

Major rework to remove R dependencies

0.8.3

:boom: Refactor simulation_fit()

Add calculation of exponential decay parameters. Recompute parameters for all genes, not only zero-inflated.

0.8.2

:heavy_minus_sign: Remove matplotlib dependency

replace it by explicit scipy dep. which is essential to the module's functionality

0.8.1

v0.8.1

Update README.md

0.8 - initial release

Update README.md

finished minimal examples