In-Class5

Author

Abhishek Singh

Published

May 13, 2023

Modified

June 18, 2023

pacman::p_load(igraph, tidygraph, ggraph, 
               visNetwork, lubridate, clock,
               tidyverse, graphlayouts,jsonlite)

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))

glimpse(GAStech_edges)

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…

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,…

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
#
# 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

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

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()

MC1 <- fromJSON("data/MC1.json")

MC1_nodes <- as.tibble(MC1$nodes) %>%
  select(id,type,country)

MC1_edges <- as.tibble(MC1$links) %>%
  select(source,target,type,weight,key)