mutual_information_matrix_fit: Calculates the mutual information between the probability...

In Fagan-Lab/constructnet: Network reconstruction from time series

Description

Calculates the mutual information between the probability distributions of the (binned) values of the time series of pairs of nodes. First, the mutual information is computed between each pair of vertices. Then, a thresholding condition is applied to obtain edges. The results dictionary also stores the weight matrix as ''weights_matrix'' and the thresholded version of the weight matrix as ''thresholded_matrix''.

Usage

mutual_information_matrix_fit(TS, nbins = 10, threshold_type = "degree", ...)

Arguments

TS	Matrix consisting of :math:'L' observations from :math:'N' sensors.
nbins	number of bins for the pre-processing step (to yield a discrete probability distribution)
threshold_type	Which thresholding function to use on the matrix of weights.
...	arguments

Value

A reconstructed graph with :math:'N' nodes.

Fagan-Lab/constructnet documentation built on Feb. 19, 2021, 12:12 a.m.