In-Class Exercise 5

VAST Challenge Project & GAStech

Getting started with VAST

1. Using p_load() of pacman package to load the required libraries

pacman :: p_load (jsonlite, tidygraph, ggraph, visNetwork, tidyverse)

2. Importing data

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

Create Tibble Dataframe

MC1_nodes <-as_tibble(MC1$nodes) %>%
  select(id,type, country)

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

Getting started with GAStech

1. Using p_load() of pacman package to load the required libraries

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

2. Importing data

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

Refer to Hands-on Exercise 5

1. Wrangling Time

GAStech_edges <- GAStech_edges %>%
  mutate(SendDate = dmy(SentDate)) %>%
  mutate(Weekday = wday(SentDate,
                        label = TRUE,
                        abbr = FALSE))

2. Wrangling attributes

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

3. Using tbl_graph() to build tidygraph data model

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

4. Changing the active object

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

5. Plotting basic network graph

ggraph(GAStech_graph) +
  geom_edge_link() +
  geom_node_point()