v0.0.0.9008

New features

• New parameter: n_sgd_threads, which controls the number of threads used in the stochastic gradient descent. By default this is now single-threaded and should result in reproducible results when using set.seed. To get back the old, less consistent (but faster) settings, set n_sgd_threads = "auto".
• API change for consistency with Python UMAP:
  • alpha is now learning_rate.
  • gamma is now repulsion_strength.
• Default spectral initialization now looks for disconnected components and initializes them separately (also applies to laplacian and normlaplacian).
• New init options: sspectral, snormlaplacian and slaplacian. These are like spectral, normlaplacian, laplacian respectively, but scaled so that each dimension has a standard deviation of 1e-4. This is like the difference between the pca and spca options.

Bug fixes and minor improvements

• Hamming distance support (was actually using Euclidean distance).
• Smooth knn/perplexity calibration results had a small dependency on the number of threads used.
• Anomalously long spectral intialization times should now be reduced.
• Internal changes and fixes thanks to a code review by @LTLA.