Whole Network Analysis

To analyse the whole network, use the analyse_network method and provide the required data and settings arguments.

results = network_analysis.analyse_network(settings=settings,
                                           data=data)

The algorithm will loop over all processes in the network and first analyse each of them separately as a target. The results will finally be combined in a Results object. By default, an FDR correction will be performed when combining the results from different targets (Benjamini, 1995, J Royal Stat Soc B, 57(1)). In order to skip the FDR correction, refer to the tutorial on Statistical Significance Tests.

Restricting the target set

The optional argument targets can be passed to the analyse_network method in order to restrict the analysis to a specific list of target processes.

results = network_analysis.analyse_network(settings=settings,
                                           data=data,
                                           targets=[0, 2, 3])

Restricting the potential sources set

The optional argument sources can be passed to the analyse_network method in order to restrict the analysis to a specific list of potential sources.

results = network_analysis.analyse_network(settings=settings,
                                           data=data,
                                           targets=[0, 2, 3],
                                           sources=[1, 4])

If the list of potential sources is different for every target, the argument sources must be a list of lists (one list per target).

results = network_analysis.analyse_network(settings=settings,
                                           data=dat,
                                           targets=[0, 2, 3],
                                           sources=[[1, 2, 3], [1], [0, 1, 2, 4]])