IS428 - DataViz Makeover 2

Importing Packages for DataViz Makeover 2

packages = c('igraph', 'tidygraph', 'ggraph', 'visNetwork', 'lubridate', 'tidyverse')

for(p in packages){library
  if(!require(p, character.only = T)){
    install.packages(p)
  }
  library(p, character.only = T)
}

1 - Task 1: Static Organizational Graph

Importing Data

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

GAStech_edges$SentDate  = dmy(GAStech_edges$SentDate)
GAStech_edges$Weekday = wday(GAStech_edges$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 %>%
  activate(edges) %>%
  arrange(desc(Weight))

## # A tbl_graph: 54 nodes and 1456 edges
## #
## # A directed multigraph with 1 component
## #
## # Edge Data: 1,456 x 4 (active)
##    from    to Weekday Weight
##   <int> <int> <ord>    <int>
## 1    40    41 Tuesday     23
## 2    40    43 Tuesday     19
## 3    41    43 Tuesday     15
## 4    41    40 Tuesday     14
## 5    42    41 Tuesday     13
## 6    42    40 Tuesday     12
## # ... with 1,450 more rows
## #
## # Node Data: 54 x 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
## # ... with 51 more rows

#Inital Sketch Graph
g <- GAStech_graph %>%
  mutate(betweenness_centrality = centrality_betweenness()) %>%
  mutate(closeness_centrality = centrality_closeness()) %>%
  ggraph(layout = "nicely") + 
  geom_edge_link(aes()) +
  geom_node_point(aes(colour = closeness_centrality, size=betweenness_centrality))

g + theme_graph()

With reference to the organisation network graph in Section 6.1 of Hands-on Exercise 10, you are required to complete the following tasks:

Improve the code chunk used to create the organisation network graph by using the latest functions provided in ggraph2.0.

gg2 <- ggraph(GAStech_edges_aggregated, layout = "nicely") + 
  geom_edge_link() + 
  geom_node_point(aes(colour = centrality_closeness(),size = centrality_betweenness()))
  
gg2 + theme_graph()

Identify three aspects of the graph visualisation in Section 6.1 that can be improved.

1. Problem: Unclear which node is linked to which title
   Solution: Label the titles to respective nodes
   
2. Problem: Unclear which node is linked to which department
   Solution: Highlight highest betweenness centrality and highest closeness centrality
   
3. Problem: Color used for edges and nodes were confusing
   Solution: Variate the colors used for edges and nodes
   

Provide the sketch of your alternative design.
Using appropriate ggraph functions, plot the alternative design.

retrievedGraph <- GAStech_graph %>%
  mutate(betweenness_centrality = centrality_betweenness()) %>%
  mutate(closeness_centrality = centrality_closeness())

ggraph(retrievedGraph) +
  geom_edge_link(colour = "Grey70") +
  geom_node_circle(aes(fill = closeness_centrality, 
                       col = Department,
                       r = log(betweenness_centrality)/50),
                  size = 2)  + 
  geom_node_text(aes(label = Title), colour = "Black", size = 2, repel = TRUE)

2 - Task 2: Interactive Organisation Graph

With reference to the organisation network graph in Section 7.4 of Hands-on Exercise 10, you are required to complete the following tasks:

Improve the design of the graph by incorporating the following interactivity:

1. When a name is selected from the drop-down list, the corresponding node will not only be highlighted but also will be labelled. Furthermore, all the linked nodes of the selected node will also be labelled too.
2. When a node of the interactive graph is selected, the node will not only be highlighted but also will be labelled. Furthermore, all the linked nodes of the selected node will be labelled as well.
   

#Importing data from files
GAStech_nodes <- read_csv("data/GAStech_email_node.csv")
GAStech_edges <- read_csv("data/GAStech_email_edge-v2.csv")

#Wrangling Time
GAStech_edges$SentDate  = dmy(GAStech_edges$SentDate)
GAStech_edges$Weekday = wday(GAStech_edges$SentDate, label = TRUE, abbr = FALSE)

#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()

GAStech_nodes <- GAStech_nodes %>%
  rename(group = Department)

#Working with Layout
visNetwork(GAStech_nodes, GAStech_edges_aggregated, height = "650px", width = "100%") %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
#Task 2
  visOptions(
    highlightNearest = list(
      degree = list(from = 1, to = 1),
      enabled = TRUE
    ), 
    nodesIdSelection = TRUE
  )

Identify three aspects of the graph visualisation in Section 7.4 that can be improved.

1. Problem: No weightage or direction displayed in each relationship
   Solution: Adding arrows and labels to show direction and weightage of each relationship
   
2. Problem: Unable to select the group of interaction in each relationship
   Solution: Highlight the relationship based on the group selected
   
3. Problem: Lack of information to allow users understand the relationship better
   Solution: Add Job Title into the relationship
   

Provide the sketch of your alternative design.

Using appropriate visNetwork functions, plot the alternative design.

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

GAStech_edges$SentDate  = dmy(GAStech_edges$SentDate)
GAStech_edges$Weekday = wday(GAStech_edges$SentDate, label = TRUE, abbr = FALSE)

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()

GAStech_edges_aggregated <- rename(GAStech_edges_aggregated, value = weight)

GAStech_nodes <- GAStech_nodes %>%
  rename(group = Department)

GAStech_nodes$title <- paste0("<p>Job Title: ", GAStech_nodes$Title, "</p>")
GAStech_edges_aggregated$label <- GAStech_edges_aggregated$value

visNetwork(GAStech_nodes, GAStech_edges_aggregated, main = "Interactive Network Graph") %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visEdges(
    arrows = list(
      to = list(enabled = TRUE), 
      from = list(enabled = TRUE)
    )
  ) %>%
  visPhysics(stabilization = FALSE) %>%
  visInteraction(
    dragNodes = TRUE, 
    dragView = TRUE, 
    zoomView = FALSE) %>%
  visNodes(shape="box", 
           labelHighlightBold = TRUE, 
           font = list(size=20)) %>%

  visOptions(
    selectedBy = "group",
    highlightNearest = list(
      degree = list(enabled = T, degree = list(from = 1, to = 1), hover = F),
      enabled = TRUE
    ), 
    nodesIdSelection = list(enabled = TRUE)
  )