dagma.utils.count_accuracy¶

dagma.utils.count_accuracy(B_true: numpy.ndarray, B_est: numpy.ndarray) → dict¶

Compute various accuracy metrics for B_est.

true positive = predicted association exists in condition in correct direction

reverse = predicted association exists in condition in opposite direction

false positive = predicted association does not exist in condition

Parameters:¶

B_true : np.ndarray¶

\([d, d]\) ground truth graph, \(\{0, 1\}\).

B_est : np.ndarray¶

\([d, d]\) estimate, \(\{0, 1, -1\}\), -1 is undirected edge in CPDAG.

Returns:¶

fdr: (reverse + false positive) / prediction positive

tpr: (true positive) / condition positive

fpr: (reverse + false positive) / condition negative

shd: undirected extra + undirected missing + reverse

nnz: prediction positive

Return type:¶

dict