In class Exercise 5

Author

Huynh Minh Phuong

Published

May 13, 2023

Modified

May 19, 2023

Revision hands-on 5

Install and launch packages

pacman::p_load(igraph, tidygraph, ggraph, 
               visNetwork, lubridate, clock,
               tidyverse, graphlayouts)
package 'igraph' successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\User\AppData\Local\Temp\RtmpmkSHaR\downloaded_packages
package 'tidygraph' successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\User\AppData\Local\Temp\RtmpmkSHaR\downloaded_packages
package 'polyclip' successfully unpacked and MD5 sums checked
package 'ggforce' successfully unpacked and MD5 sums checked
package 'graphlayouts' successfully unpacked and MD5 sums checked
package 'ggraph' successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\User\AppData\Local\Temp\RtmpmkSHaR\downloaded_packages
package 'visNetwork' successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\User\AppData\Local\Temp\RtmpmkSHaR\downloaded_packages
package 'tzdb' successfully unpacked and MD5 sums checked
package 'cpp11' successfully unpacked and MD5 sums checked
package 'clock' successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\User\AppData\Local\Temp\RtmpmkSHaR\downloaded_packages

Load data

GAStech_nodes <- read_csv("data/GAStech_email_node.csv")
GAStech_edges <- read_csv("data/GAStech_email_edge-v2.csv")

Examine data structure

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

Data type SentDate should be converted to date. Get information of the day in the week that emails are sent by using wday()

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…

Wrangling attributes

Filter work related subjects Exclude emails sent to self Count the numbers of emails as weight

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,…

Build graph

Visualize

Graph is directed from source to target

Visualize with ggplot

Create a graph object

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

Visualize with visNetwork

Data Preparation

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()

Force directed graph: with forces pushing nodes apart and links pulling connected nodes together

visNetwork(GAStech_nodes,
           GAStech_edges_aggregated)