Put the weights of several measures side by side, with their ranks

Joins a named list of edge tables (for instance the result of compute_couplings()) by pair of nodes, with one column of weights per element, and, by default, the rank of each pair under each measure and the gap between the ranks of two measures. It is the table behind the other comparison functions, and the tool to inspect the pairs on which two measures disagree.

Usage

merge_weights(
  edges,
  rank = TRUE,
  rank_gap = NULL,
  ties = c("average", "min", "max", "first")
)

Arguments

edges: A named list of edge tables, each with the columns Source, Target and weight. The tables are not modified.
rank: Logical. If TRUE (default), adds one rank_<name> column per element of edges.
rank_gap: Character vector of two names of edges, or NULL (default). If given, adds the rank_gap column, rank_<second> - rank_<first>. If NULL and edges has exactly two elements, the gap between them (second minus first) is computed. It requires rank = TRUE.
ties: How ties are ranked, as in data.table::frank() ("average" by default).

Value

A data.table with Source, Target, one column of weights per element of edges and, according to the arguments, the rank_<name> columns and rank_gap. A pair absent from a table (for instance because tables were built with different thresholds) gets NA.

Details

Weights of different measures do not have the same scale, but their ranks do: rank 1 is the strongest pair of the measure. A pair with a high weight for one measure and a low weight for another has a large gap between the two ranks. The gap is

$$\mathrm{rank\_gap}_{AB} = \mathrm{rank}_{2}(A, B) - \mathrm{rank}_{1}(A, B)$$

with 1 and 2 the first and second elements of rank_gap: it is positive when the second measure ranks the pair lower (as less close) than the first one, negative when it ranks it higher. Sorting the table on the gap (decreasing, then increasing) gives the pairs on which the measures disagree the most.

Ranks are computed on the pairs present in all the tables, so that they are comparable: the pairs that a measure does not have (for instance those of coupling_descriptive(), which links documents that share no reference) get NA ranks.

Examples

library(biblionetwork)
edges <- compute_couplings(Ref_stagflation, "Citing_ItemID_Ref", "ItemID_Ref",
                           methods = c("angle", "strength"), weight_threshold = 2)
merged <- merge_weights(edges)
head(merged)
#> Key: <Source, Target>
#>     Source   Target      angle    strength rank_angle rank_strength rank_gap
#>      <int>    <int>      <num>       <num>      <num>         <num>    <num>
#> 1:  214927  2207578 0.14605935 0.020008623      315.5           138   -177.5
#> 2:  214927  8456979 0.09733285 0.011939901      703.0           316   -387.0
#> 3:  214927 10729971 0.29848100 0.047267549       20.0            23      3.0
#> 4:  214927 19627977 0.11202241 0.011401148      558.0           342   -216.0
#> 5:  214927 60300900 0.08944272 0.013267952      797.0           266   -531.0
#> 6: 1021902  8456979 0.06362848 0.005376741     1132.5           850   -282.5

# The pairs that the angle ranks high and the strength ranks low
head(merged[order(-rank_gap)])
#>      Source     Target     angle    strength rank_angle rank_strength rank_gap
#>       <int>      <int>     <num>       <num>      <num>         <num>    <num>
#> 1: 12824456  106566088 0.1616904 0.005202959      228.0           877    649.0
#> 2: 12824456   20533251 0.1519474 0.004992118      279.5           909    629.5
#> 3: 12824456   95433988 0.1025978 0.002810660      648.0          1260    612.0
#> 4: 20533251 1111111147 0.1264279 0.004107403      439.0          1039    600.0
#> 5: 12824456 1111111130 0.1378164 0.004683245      359.0           949    590.0
#> 6: 12824456  101777013 0.1111111 0.003452918      567.0          1150    583.0