Combine multiple-relationship networks into a single weighted network. The approach is similar to factor analysis in the that contribution from each constituent network varies so as to maximize the information gleaned from the multiple-relationship networks. This implementation uses Principal Component Analysis calculated using 'prcomp' with bootstrap subsampling. Missing links are imputed using the method of Chen et al. (2012).
|Author||Stephen R. Haptonstahl|
|Date of publication||2013-11-25 21:23:02|
|Maintainer||Stephen R. Haptonstahl <email@example.com>|
|License||MIT + file LICENSE|
AdjacencyFromEdgelist: Convert an edgelist to an adjacency matrix
dils-package: Data-Informed Link Strength. Combine multiple-relationship...
EdgelistFill: Ensure an edgelist has all dyads and a column of weights.
EdgelistFromAdjacency: Convert an adjacency matrix to filled edgelist.
EdgelistFromIgraph: Convert an igraph to filled edgelist
GenerateDilsNetwork: Combine multiple networks into a single weighted network.
GetSampleFromDataFrame: Randomly select rows from a data.frame.
GetSampleFromDb: Sample from the rows of a (possibly large) database table...
GetSampleFromFile: Sample from the rows of a (possibly large) text file (NOT...
IgraphFromEdgelist: Convert an edgelist to an igraph
MeasureNetworkInformation: Measure how much a network informs a particular network...
MergeEdgelists: Combine edgelists into a single data.frame
RelationStrengthSimilarity: Calculate the RSS from one node to another.
RelativeNetworkInformation: Compare how much two networks inform a particular network...
RssCell: Calculate the RSS from one node to another.
RssSuggestedNetwork: Suggest a network with imputed links
RssThisRadius: Calculate part of the RSS from one node to another.
ScalablePCA: Perform Principal Component Analysis on a large data set