Fresi_2016_Makeover_2
Fresi.2016
11/18/2019
#install the necessary packages
packages = c('igraph', 'tidygraph', 'ggraph', 'visNetwork', 'lubridate', 'tidyverse', 'ggrepel')
for(p in packages){library
if(!require(p, character.only = T)){
install.packages(p)
}
library(p, character.only = T)
}## Loading required package: igraph##
## Attaching package: 'igraph'## The following objects are masked from 'package:stats':
##
## decompose, spectrum## The following object is masked from 'package:base':
##
## union## Loading required package: tidygraph##
## Attaching package: 'tidygraph'## The following object is masked from 'package:igraph':
##
## groups## The following object is masked from 'package:stats':
##
## filter## Loading required package: ggraph## Loading required package: ggplot2## Loading required package: visNetwork## Loading required package: lubridate##
## Attaching package: 'lubridate'## The following object is masked from 'package:igraph':
##
## %--%## The following object is masked from 'package:base':
##
## date## Loading required package: tidyverse## -- Attaching packages ---------------------------------------------------------------- tidyverse 1.2.1 --## v tibble 2.1.3 v purrr 0.3.2
## v tidyr 1.0.0 v dplyr 0.8.3
## v readr 1.3.1 v stringr 1.4.0
## v tibble 2.1.3 v forcats 0.4.0## -- Conflicts ------------------------------------------------------------------- tidyverse_conflicts() --
## x lubridate::%--%() masks igraph::%--%()
## x lubridate::as.difftime() masks base::as.difftime()
## x dplyr::as_data_frame() masks tibble::as_data_frame(), igraph::as_data_frame()
## x purrr::compose() masks igraph::compose()
## x tidyr::crossing() masks igraph::crossing()
## x lubridate::date() masks base::date()
## x dplyr::filter() masks tidygraph::filter(), stats::filter()
## x dplyr::groups() masks tidygraph::groups(), igraph::groups()
## x lubridate::intersect() masks base::intersect()
## x dplyr::lag() masks stats::lag()
## x lubridate::setdiff() masks base::setdiff()
## x purrr::simplify() masks igraph::simplify()
## x lubridate::union() masks igraph::union(), base::union()## Loading required package: ggrepel#upload both file data
GAStech_nodes <- read_csv("data/GAStech_email_node.csv")## Parsed with column specification:
## cols(
## id = col_double(),
## label = col_character(),
## Department = col_character(),
## Title = col_character()
## )GAStech_edges <- read_csv("data/GAStech_email_edge-v2.csv")## Parsed with column specification:
## cols(
## source = col_double(),
## target = col_double(),
## SentDate = col_character(),
## SentTime = col_time(format = ""),
## Subject = col_character(),
## MainSubject = col_character(),
## sourceLabel = col_character(),
## targetLabel = col_character()
## )#change SentDate attribute from chr to date format
GAStech_edges$SentDate = dmy(GAStech_edges$SentDate)
#create a new attribute called Weekday
GAStech_edges$Weekday = wday(GAStech_edges$SentDate, label = TRUE, abbr = FALSE)#aggregate the individual data by date, senders, receivers, main subject, and the day of the week
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_edges_aggregated## # A tibble: 1,456 x 4
## source target Weekday Weight
## <dbl> <dbl> <ord> <int>
## 1 1 2 Monday 4
## 2 1 2 Tuesday 3
## 3 1 2 Wednesday 5
## 4 1 2 Friday 8
## 5 1 3 Monday 4
## 6 1 3 Tuesday 3
## 7 1 3 Wednesday 5
## 8 1 3 Friday 8
## 9 1 4 Monday 4
## 10 1 4 Tuesday 3
## # ... with 1,446 more rows# create the network objects by using the tbl_graph function
GAStech_graph <- tbl_graph(nodes = GAStech_nodes, edges = GAStech_edges_aggregated, directed = TRUE)
GAStech_graph## # A tbl_graph: 54 nodes and 1456 edges
## #
## # A directed multigraph with 1 component
## #
## # Node Data: 54 x 4 (active)
## 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
## # ... with 48 more rows
## #
## # Edge Data: 1,456 x 4
## from to Weekday Weight
## <int> <int> <ord> <int>
## 1 1 2 Monday 4
## 2 1 2 Tuesday 3
## 3 1 2 Wednesday 5
## # ... with 1,453 more rows#re-arrange the rows in the GAStech_graph from the highest weight
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#original code for Network 6.1
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() + labs(title = "Centralitiy Indices")## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family not
## found in Windows font database
## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family not
## found in Windows font database## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family not
## found in Windows font database## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
Task 1: Static Organisation 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.
Identify three aspects of the graph visualisation in Section 6.1 that can be improved.
- First, the lines (geom_edge_link) that connect the nodes are too thick. All the lines have similar thickness and making it hard to spot how frequent the relationship between one node to another node. For the line, the thickness should be depending on the weight which represent how many times one node interacts with another node.
- Second, the node colour (geom_node_point) is not helping in visualizing the difference value of closeness_centrality. In fact, some nodes with low value of closeness_centrality have darker shade of blue similar to the black colour of edges. We should use 2 colour tones to represent high and low value of the closeness_centrality.
- Last, we know there are four nodes with high closeness_centrality and betweenness_centrality value yet we are unable to see who they are. Label should be given to these 4 nodes. The other alternative is to create a facet by weekday and department to find out the important node (person) in each department and analyse the network patterns each workday per department.
Provide the sketch of your alternative design.
Sketch for Task 1: 
- Using appropriate ggraph functions, plot the alternative design.
#Modification to question 1 with recommendation 1 and 2 implemented
g <- GAStech_graph %>%
mutate(betweenness_centrality = centrality_betweenness()) %>%
mutate(closeness_centrality = centrality_closeness()) %>%
ggraph(layout = "nicely") +
geom_edge_link(aes(width=Weight), alpha=0.1) +
geom_node_point(aes(colour = closeness_centrality, size=betweenness_centrality))+
scale_color_gradient(low='red', high='blue') +
geom_label_repel(aes(x=ifelse(closeness_centrality > 0.015, x, 0),
y=ifelse(closeness_centrality > 0.015, y, 0),
label=ifelse(closeness_centrality > 0.015, label, "")),
fontface = 'bold', color = 'black',
size = 3,
box.padding = 0.80, point.padding = 0.5,
segment.colour = "white",
na.rm=TRUE)
g + theme_graph() + labs(title = "Centralitiy Indices")## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
# Modification to question 1 with recommendation 3 being implemented (the facet by weekday and department)
g <- GAStech_graph %>%
mutate(betweenness_centrality = centrality_betweenness()) %>%
mutate(closeness_centrality = centrality_closeness()) %>%
ggraph(layout = "nicely") +
geom_edge_link(aes(width=Weight), alpha=0.1) +
geom_node_point(aes(colour = closeness_centrality, size=betweenness_centrality, alpha = 0.5)) +
scale_color_gradient(low='red', high='blue') +
geom_text_repel(aes(x=ifelse(closeness_centrality > 0.015, x, 0),
y=ifelse(closeness_centrality > 0.015, y, 0),
label=ifelse(closeness_centrality > 0.015, label, "")),
fontface = 'bold', color = 'black',
size = 3,
box.padding = 0.80, point.padding = 0.5,
segment.colour = "white",
na.rm=TRUE)
#g + theme_graph() + labs(title = "Centralitiy Indices")
g + facet_graph(Weekday ~ Department, labeller = label_wrap_gen(width=10))
# Processing the data for interactive graph 2
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)#original code for graph 7.4
visNetwork(GAStech_nodes, GAStech_edges_aggregated) %>%
visIgraphLayout(layout = "layout_with_fr") %>%
visOptions(highlightNearest = TRUE, nodesIdSelection = TRUE)Task 2: Interactive Organization 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:
- 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.
- 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.
- Identify three aspects of the graph visualisation in Section 7.4 that can be improved.
- First, there is a lack of information about what the color of the nodes mean in this network. There should be a legend with color code information.Also, there is no label on the node to indicate who does the node belong to, unless user zooms in on the node. This is not user-friendly. A name label should be display on the node.
- Second, there is no direction on the edge to tell user whether the relationship is one way or two ways. Therefore, we are missing the connection of node as whether they are directed or unidrected. An arror on the edges will be useful to solve this problem.
- Third, when user select a random node, only the unrelated nodes will be grey-shaded yet the edges are not. I feel the edges of the unrelated chosen nodes should also be grey-shaded to highligh the network of the chosen node.
- Provide the sketch of your alternative design.
Sketch for Task 2:
- Using appropriate visNetwork functions, plot the alternative design.
#revised code for interactive design 2
visNetwork(GAStech_nodes, GAStech_edges_aggregated,
main = "Task 2")%>%
visIgraphLayout(layout = "layout_with_fr") %>%
visEdges(arrows = "to", smooth = FALSE) %>%
visPhysics(stabilization = FALSE) %>%
visInteraction(dragNodes = TRUE, dragView = FALSE, zoomView = TRUE) %>%
visNodes(labelHighlightBold = TRUE, font = list(size=30), scaling = list(label=list(Threshold=30, maxVisible=60))) %>%
visOptions(highlightNearest = list(enabled = TRUE, hover = FALSE, algorithm = "hierarchical"),
nodesIdSelection = list(enabled = TRUE, values = unique(GAStech_nodes$id))) %>%
visLegend(zoom = FALSE)