dodiscover.metrics.confusion_matrix_networks(true_graph, pred_graph, labels=None, normalize=None)[source]#

Compute the confusion matrix comparing a predicted graph from the true graph.

Converts the graphs into an undirected graph, and then compares their adjacency matrix, which are symmetric.

true_graphinstance of causal graph

The true graph.

pred_graphinstance of causal graph

The predicted graph. The predicted graph and true graph must be the same type.

labelsarray_like of shape (n_classes), default=None

List of labels to index the matrix. This may be used to reorder or select a subset of labels. If None is given, those that appear at least once in y_true or y_pred are used in sorted order.

normalize{‘true’, ‘pred’, ‘all’}, default=None

Normalizes confusion matrix over the true (rows), predicted (columns) conditions or all the population. If None, confusion matrix will not be normalized.

cmnp.ndarray of shape (2, 2)

The confusion matrix.


This function only compares the graph’s adjacency structure, which does not take into consideration the directionality of edges.