IS444 - Data Visualization Assignment 2

Setting up environment

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)
}

TASK 1

Improve the code chunk (Section 6.1) used to create the organisation network graph by using the latest functions provided in ggraph2.0.

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

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

qgraph(
  graphData, 
  node_colour = closeness_centrality, 
  node_size = betweenness_centrality
)

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

Problem: Colours used for the edges makes it difficult to the nodes when the nodes have a darker shade. Solution: Use different colours for the nodes and use a different colour for the edges
Problem: No indication of which node refering to people from which Job Title or Role Solution: USe labels to tell users the role in the network diagram
Problem: No indication of which node refering to people from which Department Solution: Use outlines of nodes to identify which node has higher betweenness centrality and higher closeness centrality

Provide the sketch of your alternative design.

Using appropriate ggraph 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 %>%
  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

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

ggraph(graphData) +
  geom_edge_link(colour = "white") +
  geom_node_circle(aes(fill = closeness_centrality, r = log(betweenness_centrality)/50, col = Department), size = 2) +
  geom_node_text(aes(label = Title), colour = "gray48", size = 4) + 
  ggtitle("Betweenness (Size of circles) and closeness (shade of blue) centrality of each nodes")

TASK 2

Improve the design of the graph (Section 7.4) by highlighting the selected nodes and label both selected and connected nodes when clicking on the node or selecting from the drop down list.

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

visNetwork(GAStech_nodes, GAStech_edges_aggregated, height = "700px", width = "100%") %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  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

Problem: Don’t know how strong or how frequently the 2 nodes interact with each other. Solution: Add weightage to each relationship by adding thickness of the edge
Problem: Do not know how 2 nodes interact with each other. Is it a uni-directional oe bidirectional relationship. Solution: Add edges with arrows and labels to show the direction and weightage of the relationship
Problem: Lack of flexibility to see how people within the group interact with each other. Solution: Add highlight by group to show relationship within the group itself
Problem: No labels to show job title of each node to better understand the relationship. Solution: Add job title to each nodes to allow users to better understand the relationship between each node
Problem: Due to having too many nodes and relationships, it is difficult to see patterns between nodes. Solution: Allow users to drag each node to a different position. This helps users to get a clearer view as there are many nodes and can become difficult to see.
Problem: Difficult to zoom in and out. Solution: Added navigation buttons for making it easier to zoom in and out

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, height = "700px", width = "100%") %>%
  visIgraphLayout(layout = "layout_with_fr") %>%
  visEdges(
    arrows = list(
      to = list(enabled = TRUE), 
      from = list(enabled = TRUE)
    )
  ) %>%
  visOptions(
    manipulation = TRUE,
    selectedBy = "group",
    highlightNearest = list(
      degree = list(from = 1, to = 1),
      enabled = TRUE
    ), 
    nodesIdSelection = TRUE
  ) %>%
  visInteraction(navigationButtons = TRUE)

IS444 - Data Visualization Assignment 2

Ng Kai Ling Bernice

11/9/2019

Setting up environment

TASK 1

TASK 2