ash_model.measures.star_profile_entropy

ash_model.measures.star_profile_entropy(h, node_id, tid, method='aggregate')

Returns the entropy of the star profile of a node, i.e., the entropy of the attribute values for each attribute in the profiles of the nodes in the star of the given node. If method is ‘aggregate’, it is computed by first aggregating each hyperedge into a single profile (see hyperedge_aggregate_node_profile). Else if method is ‘collapse’, all the node’s neighbors are considered.

Parameters:

• h (ASH) – ASH instance

• node_id (int) – Specify the node for which we want to calculate the star profile entropy

• tid (int) – Specify the temporal id

• method (str) – Specify the method to be used in calculating the star profile entropy. Options are ‘aggregate’ or ‘collapse’.

Returns:

A dictionary with the entropy of each attribute

Return type:

dict

Examples

Compute the star-profile entropy for a node (aggregate method) on tid=0 with the dataset above:

>>> import numpy as np, networkx as nx
>>> from ash_model.utils.networkx import from_networkx_maximal_cliques_list
>>> Gs = [nx.barabasi_albert_graph(100, 3, seed=i) for i in range(10)]
>>> rng = np.random.default_rng(42)
>>> for G in Gs:
...     for n in G.nodes():
...         G.nodes[n]['color'] = 'red' if rng.integers(0, 2) == 0 else 'blue'
>>> h = from_networkx_maximal_cliques_list(Gs)
>>> tid = 0
>>> node0 = next(iter(h.nodes(start=tid, end=tid)))
>>> star_profile_entropy(h, node0, tid, method='aggregate')
{'color': np.float64(0.7706290693639405)}