In-Class Exercise 05

Author

Leonard Lee

Published

May 13, 2023

Modified

July 6, 2023

Lesson 5: Network Data Visualisation and Analysis

Load the Packages

Show me the good stuff 
pacman::p_load(igraph, tidygraph, ggraph, 
               visNetwork, lubridate, clock,
               tidyverse, graphlayouts, jsonlite)

Import the Data

Show me the good stuff 
MC1 <- fromJSON("data/MC1.json")
GAStech_nodes <- read_csv("data/GAStech_email_node.csv")
GAStech_edges <- read_csv("data/GAStech_email_edge-v2.csv")
Show me the good stuff 
MC1_nodes <- as_tibble(MC1$nodes) %>%
  select(id, type, country) #using select function to reorganise into desired order of columns
Show me the good stuff 
MC1_edges <- as_tibble(MC1$links) %>%
  select(source, target, type, weight, key)

Review the Imported Data

Show me the good stuff 
glimpse(GAStech_edges)
Rows: 9,063
Columns: 8
$ source      <dbl> 43, 43, 44, 44, 44, 44, 44, 44, 44, 44, 44, 44, 26, 26, 26…
$ target      <dbl> 41, 40, 51, 52, 53, 45, 44, 46, 48, 49, 47, 54, 27, 28, 29…
$ SentDate    <chr> "6/1/2014", "6/1/2014", "6/1/2014", "6/1/2014", "6/1/2014"…
$ SentTime    <time> 08:39:00, 08:39:00, 08:58:00, 08:58:00, 08:58:00, 08:58:0…
$ Subject     <chr> "GT-SeismicProcessorPro Bug Report", "GT-SeismicProcessorP…
$ MainSubject <chr> "Work related", "Work related", "Work related", "Work rela…
$ sourceLabel <chr> "Sven.Flecha", "Sven.Flecha", "Kanon.Herrero", "Kanon.Herr…
$ targetLabel <chr> "Isak.Baza", "Lucas.Alcazar", "Felix.Resumir", "Hideki.Coc…

Wrangling Time

Show me the good stuff 
GAStech_edges <- GAStech_edges %>%
  mutate(SendDate = dmy(SentDate)) %>%
  mutate(Weekday = wday(SentDate,
                        label = TRUE,
                        abbr = FALSE))


glimpse(GAStech_edges) #Review data
Rows: 9,063
Columns: 10
$ source      <dbl> 43, 43, 44, 44, 44, 44, 44, 44, 44, 44, 44, 44, 26, 26, 26…
$ target      <dbl> 41, 40, 51, 52, 53, 45, 44, 46, 48, 49, 47, 54, 27, 28, 29…
$ SentDate    <chr> "6/1/2014", "6/1/2014", "6/1/2014", "6/1/2014", "6/1/2014"…
$ SentTime    <time> 08:39:00, 08:39:00, 08:58:00, 08:58:00, 08:58:00, 08:58:0…
$ Subject     <chr> "GT-SeismicProcessorPro Bug Report", "GT-SeismicProcessorP…
$ MainSubject <chr> "Work related", "Work related", "Work related", "Work rela…
$ sourceLabel <chr> "Sven.Flecha", "Sven.Flecha", "Kanon.Herrero", "Kanon.Herr…
$ targetLabel <chr> "Isak.Baza", "Lucas.Alcazar", "Felix.Resumir", "Hideki.Coc…
$ SendDate    <date> 2014-01-06, 2014-01-06, 2014-01-06, 2014-01-06, 2014-01-0…
$ Weekday     <ord> Friday, Friday, Friday, Friday, Friday, Friday, Friday, Fr…

Wrangling Attributes

Show me the good stuff 
GAStech_edges_aggregated <- GAStech_edges %>%
  filter(MainSubject == "Work related") %>%
  group_by(source, target, Weekday) %>%
    summarise(Weight = n()) %>%
  filter(source!=target) %>%
  filter(Weight > 1) %>%
  ungroup()

glimpse(GAStech_edges_aggregated)
Rows: 1,372
Columns: 4
$ source  <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
$ target  <dbl> 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 6,…
$ Weekday <ord> Sunday, Monday, Tuesday, Wednesday, Friday, Sunday, Monday, Tu…
$ Weight  <int> 5, 2, 3, 4, 6, 5, 2, 3, 4, 6, 5, 2, 3, 4, 6, 5, 2, 3, 4, 6, 5,…

Creating Network Object using Tidygraph

Build tidygraph data model using tbl_graph()

Show me the good stuff 
GAStech_graph <- tbl_graph(nodes = GAStech_nodes,
                           edges = GAStech_edges_aggregated, 
                           directed = TRUE)
GAStech_graph #Review Graph
# A tbl_graph: 54 nodes and 1372 edges
#
# A directed multigraph with 1 component
#
# A tibble: 54 × 4
     id label               Department     Title                                
  <dbl> <chr>               <chr>          <chr>                                
1     1 Mat.Bramar          Administration Assistant to CEO                     
2     2 Anda.Ribera         Administration Assistant to CFO                     
3     3 Rachel.Pantanal     Administration Assistant to CIO                     
4     4 Linda.Lagos         Administration Assistant to COO                     
5     5 Ruscella.Mies.Haber Administration Assistant to Engineering Group Manag…
6     6 Carla.Forluniau     Administration Assistant to IT Group Manager        
# ℹ 48 more rows
#
# A tibble: 1,372 × 4
   from    to Weekday Weight
  <int> <int> <ord>    <int>
1     1     2 Sunday       5
2     1     2 Monday       2
3     1     2 Tuesday      3
# ℹ 1,369 more rows

Change the Active Object

Show me the good stuff 
GAStech_graph %>%
  activate(edges) %>%
  arrange(desc(Weight))
# A tbl_graph: 54 nodes and 1372 edges
#
# A directed multigraph with 1 component
#
# A tibble: 1,372 × 4
   from    to Weekday  Weight
  <int> <int> <ord>     <int>
1    40    41 Saturday     13
2    41    43 Monday       11
3    35    31 Tuesday      10
4    40    41 Monday       10
5    40    43 Monday       10
6    36    32 Sunday        9
# ℹ 1,366 more rows
#
# A tibble: 54 × 4
     id label           Department     Title           
  <dbl> <chr>           <chr>          <chr>           
1     1 Mat.Bramar      Administration Assistant to CEO
2     2 Anda.Ribera     Administration Assistant to CFO
3     3 Rachel.Pantanal Administration Assistant to CIO
# ℹ 51 more rows

Plotting Static Network Graphs with ggraph package

Plotting a basic network graph

Show me the good stuff 
ggraph(GAStech_graph) +
  geom_edge_link() +
  geom_node_point()

The basic plotting function is ggraph(), which takes the data to be used for the graph and the type of layout desired. Both of the arguments for ggraph() are built around igraph. Therefore, ggraph() can use either an igraph object or a tbl_graph object.

Changing the default network graph theme

Show me the good stuff 
g <- ggraph(GAStech_graph) + 
  geom_edge_link(aes()) +
  geom_node_point(aes())

g + theme_graph()

Changing the coloring of the plot

Show me the good stuff 
g <- ggraph(GAStech_graph) + 
  geom_edge_link(aes(colour = 'grey50')) +
  geom_node_point(aes(colour = 'grey40'))

g + theme_graph(background = 'grey10',
                text_colour = 'white')

Many models

Fruchterman and Reingold layout

Show me the good stuff 
g <- ggraph(GAStech_graph, 
            layout = "fr") +
  geom_edge_link(aes()) +
  geom_node_point(aes())

g + theme_graph()

Modifying Network Nodes

Show me the good stuff 
g <- ggraph(GAStech_graph, 
            layout = "nicely") + 
  geom_edge_link(aes()) +
  geom_node_point(aes(colour = Department, 
                      size = 3))

g + theme_graph()

geom_node_point is equivalent in functionality to geo_point of ggplot2. It allows for simple plotting of nodes in different shapes, colours and sizes. In the codes chnuks above colour and size are used.

Modifying Edges

Show me the good stuff 
g <- ggraph(GAStech_graph, 
            layout = "nicely") +
  geom_edge_link(aes(width=Weight), 
                 alpha=0.2) +
  scale_edge_width(range = c(0.1, 5)) +
  geom_node_point(aes(colour = Department), 
                  size = 3)

g + theme_graph()

Creating Facet Graphs

There are three functions in ggraph to implement faceting, they are:

facet_nodes() whereby edges are only draw in a panel if both terminal nodes are present here, facet_edges() whereby nodes are always drawn in al panels even if the node data contains an attribute named the same as the one used for the edge facetting, and facet_graph() faceting on two variables simultaneously.

Working with facet_edges()

Show me the good stuff 
set_graph_style()

g <- ggraph(GAStech_graph, 
            layout = "nicely") + 
  geom_edge_link(aes(width=Weight), 
                 alpha=0.2) +
  scale_edge_width(range = c(0.1, 5)) +
  geom_node_point(aes(colour = Department), 
                  size = 2)

g + facet_edges(~Weekday)

Show me the good stuff 
set_graph_style()

g <- ggraph(GAStech_graph, 
            layout = "nicely") + 
  geom_edge_link(aes(width=Weight), 
                 alpha=0.2) +
  scale_edge_width(range = c(0.1, 5)) +
  geom_node_point(aes(colour = Department), 
                  size = 2) +
  theme(legend.position = 'bottom')
  
g + facet_edges(~Weekday)

Show me the good stuff 
set_graph_style() 

g <- ggraph(GAStech_graph, 
            layout = "nicely") + 
  geom_edge_link(aes(width=Weight), 
                 alpha=0.2) +
  scale_edge_width(range = c(0.1, 5)) +
  geom_node_point(aes(colour = Department), 
                  size = 2)
  
g + facet_edges(~Weekday) +
  th_foreground(foreground = "grey80",  
                border = TRUE) +
  theme(legend.position = 'bottom')

Working with facet_nodes()

Show me the good stuff 
set_graph_style()

g <- ggraph(GAStech_graph, 
            layout = "nicely") + 
  geom_edge_link(aes(width=Weight), 
                 alpha=0.2) +
  scale_edge_width(range = c(0.1, 5)) +
  geom_node_point(aes(colour = Department), 
                  size = 2)
  
g + facet_nodes(~Department)+
  th_foreground(foreground = "grey80",  
                border = TRUE) +
  theme(legend.position = 'bottom')

Network Metric Analysis

Computing centrality indices

Centrality measures are a collection of statistical indices use to describe the relative important of the actors are to a network. There are four well-known centrality measures, namely: degree, betweenness, closeness and eigenvector.

Show me the good stuff 
g <- GAStech_graph %>%
  mutate(betweenness_centrality = centrality_betweenness()) %>%
  ggraph(layout = "fr") + 
  geom_edge_link(aes(width=Weight), 
                 alpha=0.2) +
  scale_edge_width(range = c(0.1, 5)) +
  geom_node_point(aes(colour = Department,
            size=betweenness_centrality))
g + theme_graph()

Visualising network metrics

Show me the good stuff 
g <- GAStech_graph %>%
  ggraph(layout = "fr") + 
  geom_edge_link(aes(width=Weight), 
                 alpha=0.2) +
  scale_edge_width(range = c(0.1, 5)) +
  geom_node_point(aes(colour = Department, 
                      size = centrality_betweenness()))
g + theme_graph()

Visualising Community

Show me the good stuff 
g <- GAStech_graph %>%
  mutate(community = as.factor(group_edge_betweenness(weights = Weight, directed = TRUE))) %>%
  ggraph(layout = "fr") + 
  geom_edge_link(aes(width=Weight), 
                 alpha=0.2) +
  scale_edge_width(range = c(0.1, 5)) +
  geom_node_point(aes(colour = community))  

g + theme_graph()

Building Interactive Network Graph with visNetwork

visNetwork() is a R package for network visualization, using vis.js javascript library.

visNetwork() function uses a nodes list and edges list to create an interactive graph.

The nodes list must include an “id” column, and the edge list must have “from” and “to” columns. The function also plots the labels for the nodes, using the names of the actors from the “label” column in the node list. The resulting graph is fun to play around with.

You can move the nodes and the graph will use an algorithm to keep the nodes properly spaced. You can also zoom in and out on the plot and move it around to re-center it.

Data Prep

Show me the good stuff 
GAStech_edges_aggregated <- GAStech_edges %>%
  left_join(GAStech_nodes, by = c("sourceLabel" = "label")) %>%
  rename(from = id) %>%
  left_join(GAStech_nodes, by = c("targetLabel" = "label")) %>%
  rename(to = id) %>%
  filter(MainSubject == "Work related") %>%
  group_by(from, to) %>%
    summarise(weight = n()) %>%
  filter(from!=to) %>%
  filter(weight > 1) %>%
  ungroup()

Plotting the first interactive network graph

Show me the good stuff 
visNetwork(GAStech_nodes, 
           GAStech_edges_aggregated)

Working with layout

Show me the good stuff 
visNetwork(GAStech_nodes,
           GAStech_edges_aggregated) %>%
  visIgraphLayout(layout = "layout_with_fr")

Working with visual attributes - Nodes

visNetwork() looks for a field called “group” in the nodes object and colour the nodes according to the values of the group field.

The code chunk below rename Department field to group.

Show me the good stuff 
GAStech_nodes <- GAStech_nodes %>%
  rename(group = Department)

When we rerun the code chunk below, visNetwork shades the nodes by assigning unique colour to each category in the group field.

Show me the good stuff 
visNetwork(GAStech_nodes,
           GAStech_edges_aggregated) %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visLegend() %>%
  visLayout(randomSeed = 123)

Working with visual attributes - Edges

In the code run below visEdges() is used to symbolise the edges. - The argument arrows is used to define where to place the arrow. - The smooth argument is used to plot the edges using a smooth curve.

Show me the good stuff 
visNetwork(GAStech_nodes,
           GAStech_edges_aggregated) %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visEdges(arrows = "to", 
           smooth = list(enabled = TRUE, 
                         type = "curvedCW")) %>%
  visLegend() %>%
  visLayout(randomSeed = 123)

Interactivity

Show me the good stuff 
visNetwork(GAStech_nodes,
           GAStech_edges_aggregated) %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visOptions(highlightNearest = TRUE,
             nodesIdSelection = TRUE) %>%
  visLegend() %>%
  visLayout(randomSeed = 123)