SNA

Transitivity:

### TRANSITIVITY ####
doTransitivity = function(network) {
  trs = transitivity(network, type = 'local', vids = V(network)$name)
  V(network)$transitivity = trs
  return(V(network)$transitivity)
}

mynet = doNetwork(node, edge)
doGraph(mynet, 'discipline_classification')

# doTransitivity(mynet)

# Visualizing Transitivity
trs1 = round(transitivity(mynet, type='local'), 5)
trs_top25 = head(sort(trs1, decreasing=TRUE), length(trs1)*.25)
plot(trs_top25, 
     main='Transitivity Top 25 Percentile',
     xlab='Nodes (Descending)',
     ylab='Transitivity',
     pch=19,
     col = wes_palette('Zissou1')
     )

trs_top50 = head(sort(trs1,decreasing=TRUE),length(trs1)*.50)
plot(trs_top50, 
     main='Transitivity Top 50 Percentile',
     xlab='Nodes (Descending)',
     ylab='Transitivity',
     pch=19,
     col = wes_palette('GrandBudapest2', n=4)
     )

Triad Census:

# Triad Census
# Triad Census
triads=as.array(graph.motifs(mynet,size=3)[-2][-1])
print(paste("Triads:",triads))

## [1] "Triads: 12564" "Triads: 774"

Degree Distribution:

# Degree Distribution
mynet.degrees = degree(mynet)
# Let's count the frequencies of each degree
mynet.degree.histogram <- as.data.frame(table(mynet.degrees))

# Need to convert the first column to numbers, otherwise
# the log-log thing will not work (that's fair...)
mynet.degree.histogram[,1] <- as.numeric(mynet.degree.histogram[,1])


# Now, plot it!
ggplot(mynet.degree.histogram, aes(x = mynet.degrees, y = Freq)) +
  geom_point() +
  scale_x_continuous("Degree\n(nodes with this amount of connections)",
                     breaks = c(1, 3, 10, 30, 100, 300),
                     trans = "log10") +
  scale_y_continuous("Frequency\n(how many of them)",
                     breaks = c(1, 3, 10, 30, 100, 300, 1000),
                     trans = "log10") +
  ggtitle("Degree Distribution (log-log)") +
  geom_point()

Subgroup Analysis: Cliques

#### SUBGROUP ANALYSIS: 
cliques = largest.cliques(mynet)
cliques1 = cliques[[1]]
cliques_color = wes_palette('GrandBudapest2')
mynetCliques = induced.subgraph(graph=mynet, vids=cliques1)
degree(mynetCliques)

## Harrison, Stephen C    Chazin, Walter J   Anderson, Karen S 
##                   8                   9                   8 
## Blacklow, Stephen C     Rapoport, Tom A Otwinowski, Zbyszek 
##                  10                   8                  10 
##    Rosen, Michael K      Eck, Michael J             Wu, Hao 
##                  11                  11                   9

plot(mynetCliques,
     main='Network Cliques',
     vertex.color=cliques_color,
     layout=layout.fruchterman.reingold(mynetCliques),
     vertex.size=V(mynetCliques)*6
     )

clust = cluster.distribution(mynet)