muspan.networks#

The muspan.networks module provides tools for working with networks in the MuSpAn package. This module includes the following submodules:

Network generation and manipulation

`generate_network`	Generate network using the domain objects.
`add_similarity_weight_to_edges`	Adds edge weight to all connected nodes that is valued as a similarity of node features.
`add_dissimilarity_weight_to_edges`	Adds edge weight to all connected nodes that is valued as a dissimilarity of node features.

Neighbourhood analysis methods

`cluster_neighbourhoods`	The function generates a network of objects and finds the neighbourhoods, calculates the composition of labels within the neighbourhoods, and clusters the neighbourhoods based on the label composition.
`khop_neighbourhood`	For a given network, find the k-hop neighbourhood of a set of source objects.
`knn_label_count`	Counts the number of each label within proximity of a source object using KNN networks.

Network-based point pattern analysis

Test the correlation between adjacency labels in a network, also referred to as neighbourhood enrichment.

Network metrics

`alpha_index`	A measure of connectivity which evaluates the number of cycles in a graph in comparison with the maximum number of cycles.
`centrality`	Calculate centrality measures for a given network within a domain and optionally add the results as labels to objects.
`compactness`	Provides an index [0,1] of how compact the network is in terms of its area and length of edges.
`cyclomatic_number`	Calculate the cyclomatic number of a network.
`edge_orientation_distribution`	Computes the symmetric distribution of edge orientations for a network.
`gamma_index`	A measure of connectivity that considers the relationship between the number of observed links and the number of possible links A value close to 0 indicates poor connectivity, with relatively few connections.
`node_degree`	Computes the degree for each node.

Network clustering

Community detection on a provided network.

Network comparison methods

Calculate the distance between two networks providing a quantitative measure of the similarity between them.