uniport.metrics.silhouette

uniport.metrics.silhouette(X, cell_type, metric='euclidean', scale=True)[source]
Wrapper for sklearn silhouette function values range from [-1, 1] with

1 being an ideal fit 0 indicating overlapping clusters and -1 indicating misclassified cells

By default, the score is scaled between 0 and 1. This is controlled scale=True

Parameters:

  • group_key – key in adata.obs of cell labels

  • embed – embedding key in adata.obsm, default: ‘X_pca’

  • scale – default True, scale between 0 (worst) and 1 (best)