cellflow.metrics.compute_metrics

cellflow.metrics.compute_metrics(x, y)

Compute a set of metrics between two distributions x and y.

Parameters:

• x (Union[Array, ndarray, bool, number, bool, int, float, complex]) – An array of shape [num_samples, num_features].

• y (Union[Array, ndarray, bool, number, bool, int, float, complex]) – An array of shape [num_samples, num_features].

Return type:

dict[str, float]

Returns:

: A dictionary containing the following computed metrics:

• the r squared score.

• the sinkhorn divergence with epsilon = 1.0.

• the sinkhorn divergence with epsilon = 10.0.

• the sinkhorn divergence with epsilon = 100.0.

• the energy distance value.

• the mean maximum discrepancy loss