hands-on exercise 9

Author

Xu Lin

Published

March 15, 2024

Modified

March 15, 2024

pacman::p_load(igraph, tidygraph, ggraph, 
               visNetwork, lubridate, clock,
               tidyverse, graphlayouts)
GAStech_nodes <- read_csv("data/GAStech_email_node.csv")
GAStech_edges <- read_csv("data/GAStech_email_edge-v2.csv")
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…
GAStech_edges <- GAStech_edges %>%
  mutate(SendDate = dmy(SentDate)) %>%
  mutate(Weekday = wday(SentDate,
                        label = TRUE,
                        abbr = FALSE))
GAStech_edges_aggregated <- GAStech_edges %>%
  filter(MainSubject == "Work related") %>%
  group_by(source, target, Weekday) %>%
    summarise(Weight = n()) %>%
  filter(source!=target) %>%
  filter(Weight > 1) %>%
  ungroup()
GAStech_graph <- tbl_graph(nodes = GAStech_nodes,
                           edges = GAStech_edges_aggregated, 
                           directed = TRUE)
GAStech_graph
# A tbl_graph: 54 nodes and 1372 edges
#
# A directed multigraph with 1 component
#
# Node Data: 54 × 4 (active)
      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 Mana…
 6     6 Carla.Forluniau     Administration Assistant to IT Group Manager       
 7     7 Cornelia.Lais       Administration Assistant to Security Group Manager 
 8    44 Kanon.Herrero       Security       Badging Office                      
 9    45 Varja.Lagos         Security       Badging Office                      
10    46 Stenig.Fusil        Security       Building Control                    
# ℹ 44 more rows
#
# Edge Data: 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
GAStech_graph %>%
  activate(edges) %>%
  arrange(desc(Weight))
# A tbl_graph: 54 nodes and 1372 edges
#
# A directed multigraph with 1 component
#
# Edge Data: 1,372 × 4 (active)
    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
 7    40    43 Saturday       9
 8    41    40 Monday         9
 9    19    15 Wednesday      8
10    35    38 Tuesday        8
# ℹ 1,362 more rows
#
# Node Data: 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
ggraph(GAStech_graph) +
  geom_edge_link() +
  geom_node_point()

g <- ggraph(GAStech_graph) + 
  geom_edge_link(aes()) +
  geom_node_point(aes())

g + theme_graph()

g <- ggraph(GAStech_graph) + 
  geom_edge_link(aes(colour = 'grey50')) +
  geom_node_point(aes(colour = 'grey40'))

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

g <- ggraph(GAStech_graph, 
            layout = "fr") +
  geom_edge_link(aes()) +
  geom_node_point(aes())

g + theme_graph()

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

g + theme_graph()

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()

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)

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)

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')

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')

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()

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()

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()
visNetwork(GAStech_nodes, 
           GAStech_edges_aggregated)
visNetwork(GAStech_nodes,
           GAStech_edges_aggregated) %>%
  visIgraphLayout(layout = "layout_with_fr") 
GAStech_nodes <- GAStech_nodes %>%
  rename(group = Department) 
visNetwork(GAStech_nodes,
           GAStech_edges_aggregated) %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visLegend() %>%
  visLayout(randomSeed = 123)
visNetwork(GAStech_nodes,
           GAStech_edges_aggregated) %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visEdges(arrows = "to", 
           smooth = list(enabled = TRUE, 
                         type = "curvedCW")) %>%
  visLegend() %>%
  visLayout(randomSeed = 123)
visNetwork(GAStech_nodes,
           GAStech_edges_aggregated) %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visOptions(highlightNearest = TRUE,
             nodesIdSelection = TRUE) %>%
  visLegend() %>%
  visLayout(randomSeed = 123)