Metrics

Metrics do not modify the object. Each returns a tidy frame with metric, representation, key and value, so results from several calls stack.

metrics.silhouette_label(adata, label_key[, ...])	How well separated the biological labels are, rescaled to [0, 1].
metrics.silhouette_batch(adata, label_key, ...)	How well mixed the batches are within each biological label.
metrics.lisi(adata, key[, use_rep, ...])	Median LISI over rows [Korsunsky et al., 2019].
metrics.pc_regression(adata, key[, use_rep, ...])	Variance-weighted R^2 of the principal components on key.
metrics.batch_variance_explained(adata, keys)	pc_regression() for several covariates, stacked into one frame.
metrics.known_relationships(adata, net[, ...])	Share of annotated pairs that land in either tail of the similarity distribution [Celik et al., 2024].
metrics.evaluate_correction(adata, *[, ...])	Run every metric for every representation and stack the results.
metrics.diagnose_testing(adata[, groupby, ...])	Check whether differential testing is calibrated on this screen.