popari.tl.compute_silhouette_scores

popari.tl.compute_silhouette_scores#

popari.tl.compute_silhouette_scores(dataset, labels, embeddings, silhouette_key='silhouette')#

Compute silhouette score for a clustering based on Popari embeddings.

Useful for assessing clustering validity. ARI score is computed per dataset.

Parameters:

  • dataset (PopariDataset) – dataset to process

  • labels (str) – the key in the .obs dataframe for the label data.

  • predictions – the key in the .obs dataframe for the predictions data.

  • ari_key – the key in the .uns dictionary where the ARI score will be stored.

  • embeddings (str)

  • silhouette_key (str)

Contents