graphical_models.classes.dags.dag.DAG.confusion_matrix

DAG.confusion_matrix(other, rates_only=False)

Return the “confusion matrix” associated with estimating the CPDAG of other instead of the CPDAG of this DAG.

Parameters

• other – The DAG against which to compare.

• rates_only – if True, the dictionary of results only contains the false positive rate, true positive rate, and precision.

Returns

Dictionary of results

• false_positive_arcs:

  the arcs in the CPDAG of other which are not arcs or edges in the CPDAG of this DAG.

• false_positive_edges:

  the edges in the CPDAG of other which are not arcs or edges in the CPDAG of this DAG.

• false_negative_arcs:

  the arcs in the CPDAG of this graph which are not arcs or edges in the CPDAG of other.

• true_positive_arcs:

  the arcs in the CPDAG of other which are arcs in the CPDAG of this DAG.

• reversed_arcs:

  the arcs in the CPDAG of other whose reversals are arcs in the CPDAG of this DAG.

• mistaken_arcs_for_edges:

  the arcs in the CPDAG of other whose reversals are arcs in the CPDAG of this DAG.

• false_negative_edges:

  the edges in the CPDAG of this DAG which are not arcs or edges in the CPDAG of other.

• true_positive_edges:

  the edges in the CPDAG of other which are edges in the CPDAG of this DAG.

• mistaken_edges_for_arcs:

  the edges in the CPDAG of other which are arcs in the CPDAG of this DAG.

• num_false_positives:

  the total number of: false_positive_arcs, false_positive_edges

• num_false_negatives:

  the total number of: false_negative_arcs, false_negative_edges, mistaken_arcs_for_edges, and reversed_arcs

• num_true_positives:

  the total number of: true_positive_arcs, true_positive_edges, and mistaken_edges_for_arcs

• num_true_negatives:

  the total number of missing arcs/edges in other which are actually missing in this DAG.

• fpr:

  the false positive rate, i.e., num_false_positives/(num_false_positives+num_true_negatives). If this DAG is fully connected, defaults to 0.

• tpr:

  the true positive rate, i.e., num_true_positives/(num_true_positives+num_false_negatives). If this DAG is empty, defaults to 1.

• precision:

  the precision, i.e., num_true_positives/(num_true_positives+num_false_positives). If other is empty, defaults to 1.

Return type

dict

Examples

>>> from graphical_models import DAG
>>> d1 = DAG(arcs={(0, 1), (1, 2)})
>>> d2 = DAG(arcs={(0, 1), (2, 1)})
>>> cm = d1.confusion_matrix(d2)
>>> cm["mistaken_edges_for_arcs"]
{frozenset({0, 1}), frozenset({1, 2})},
>>> cm = d2.confusion_matrix(d1)
>>> cm["mistaken_arcs_for_edges"]
{(0, 1), (2, 1)}