sg.bern.subgraph_classifier: Bernoulli Subgraph Classifier

In neurodata/wssg: Signal Subgraphs and Extensions

Description

sg.bern.subgraph_classifier classifies arbitrary data given the estimators of a subgraph.

Usage

sg.bern.subgraph_classifier(test, edges, p, pi, classes)

Arguments

test	the test array to generate labels for. - if test is a list, then it should have s elements of dimensions [n x n]. - if test is an array, then it should be of dimensions [n x n x s].
p	[n x n x c] the probability per edge of being connected per class for c classes.
pi	[c] the pi vector probability of each class occuring.
classes	the labels for the classes as ordered in the pi and p arrays.

Value

edges [e] the edges present in the subgraph.

Yhat [s] the predicted class for each test example.

See Also

sg.bern.compute_graph_statistics

neurodata/wssg documentation built on May 16, 2019, 10:05 a.m.