v0.8.1

Bugfixes

• fixed rsc.tl.neighbors for rapids-23.08 #55

Testing

• switched testing to rapids-23.08 with cuda-11.8

v0.8.0

Features

• added support for UMAP #47
• added support for neighbors #50

Fixes

• Fixed filter_highly_variable #51

v0.7.5

Fixes

• Fixed a bug with where larger datasets would crash for Harmony GPU #35
• Adds a dedicated Class for Sparse Matrix based PCA #36

Improvements

• adds in ruff for pre-commit #36
• adds CI and automated testing #33
• adopted a newer theme for docs #31

Misc

Rapids-singlecell is now under the scverse umbrella as comunity package.

v0.7.2

v0.7.2

Added support for Rapids-23.06:

• added a_min to cp.clip for .pp.scale
• changed default n_iterations for leiden to 100

v0.7.1

v0.7.1

Bugfixes

• fixes a bug with _inplace_subset_obs

Changes

• removed tests from distributions

v0.7.0

v0.7.0

cunnData

• added _inplace_subset_var & _inplace_subset_obs
• added var_vector & obs_vector
• made cunnData more robust
• made slicing more robust
• enforced cp.float32 dtype

Fixes

• Replaced deprecated cp.sparse with cpx.scipy.sparse

Tests

• added tests for cunnData
• added test for decoupler_gpu
• added test for gr.ligrec

v0.6.3

v0.6.3

Bugfixes and Improvements:

• updates and bugfixes for cunnData
• switched to one PCA - function for cudata and adata
• added random_state to PCA
• added layer support for batched hvg-flavors seurat and cell_ranger
• warning for cell_ranger n_top_genes > dispersion_norm.size
• added settings dict for and minor bugfix for normalize_pearson_residuals
• bugfix for calculate_qc_metrics
• bugfix hvg-flavors pearson_residuals
• made max_value clipping optional for pp.scale
• added checks to gr.ligrec
• forces float32 for gr.spatial_autocorr and fix for n_perms = 0
• bugfix for _check_nonnegative_integers

v0.6.2

v0.6.2

New Function

• added .gr.ligrec from squidpy

Updates

• removed pp.calc_gene_qc
• switched pp.calculate_qc_metrics to cp.RawKernel. Includes functionality from pp.calc_gene_qc
• switched pp.highly_variable_genes with flavor='pearson_residuals' to cp.RawKernel
• switched pp.normalize_pearson_residuals to cp.RawKernel
• added checks cundata.X and cunndata.layers for .nnz < 2**31-1 because of Cupy's indptr being locked to 32bit ints.

Other

• added .pre-commit-config.yaml
• added coding-style black

v0.6.1

Changes:

• added missing dependency
• changes to typing in squidpy_gpu

v0.6.0

Changes:

• Added support for spatial autocorrelation (spatial_autocorr) with Moran's I and Geary's C.
• changed some import to be more lightweight