R Notebook

The following chunk reads the data into the program

HP_nodes <- read_csv("HP_nodes.csv")

Rows: 65 Columns: 3-- Column specification -------------------------------------------------------------------------------------------------
Delimiter: ","
chr (2): name, bio
dbl (1): id
i Use `spec()` to retrieve the full column specification for this data.
i Specify the column types or set `show_col_types = FALSE` to quiet this message.

HP_links <- read_csv("HP_links.csv")

Rows: 356 Columns: 2-- Column specification -------------------------------------------------------------------------------------------------
Delimiter: ","
dbl (2): from, to
i Use `spec()` to retrieve the full column specification for this data.
i Specify the column types or set `show_col_types = FALSE` to quiet this message.

This next chunk then creates the network in igraph

HP_network <- graph_from_data_frame(HP_links, 
                                           vertices = HP_nodes, 
                                           directed = F)

The following chunk determines the density of the network which divides the number of connections by the total possible connections.

HP_network %>% 
  edge_density()

[1] 0.1711538

This chunk then converts the data into a histogram displaying the distances in the network

HP_network %>% 
  distances() %>% 
  as.vector() %>%              # these two lines convert the distances matrix
  as_tibble() %>%              # to something plotly can graph
  plot_ly(x = ~value) %>% 
  add_histogram()

This chunk then gives the diameter of the network which is the longest of the distances.

HP_network %>% 
  get_diameter() %>% 
  length()

[1] 7

This then mutates and adds a label, title, and degree set to value.

HP_nodes <- HP_nodes %>% 
  mutate(label = name) %>%
  mutate(title = name) %>%
  mutate(value = degree(HP_network))
  

To mutate further, this adds a column for betweenness set to value.

HP_links %>% 
  mutate(betweenness = edge_betweenness(HP_network)) %>% 
  mutate(value = betweenness)

Finally, the diagram is created with a title and set to highlight the nearest connection to whichever character the dot represents.It also gives a menu option to find a certain character.

visNetwork(HP_nodes, 
           HP_links, 
           main = "Network of HP characters") %>% 
  visIgraphLayout(layout = "layout_nicely") %>% 
  visOptions(highlightNearest = T, nodesIdSelection = T)

This next chunk finds the communities within the network which also means the characters that are most related and connected to one another.

HP_network %>% 
  infomap.community()

IGRAPH clustering infomap, groups: 24, mod: 0.17
+ groups:
  $`1`
  [1] "Regulus Arcturus Black" "Vincent Crabbe Sr."     "Vincent Crabbe"        
  
  $`2`
  [1] "Sirius Black"      "Albus Dumbledore"  "Nicolas Flamel"    "Olympe Maxime"     "Quirinus Quirrell"
  
  $`3`
  [1] "Lavender Brown"  "Cho Chang"       "Cedric Diggory"  "Seamus Finnigan"
  
  $`4`
  + ... omitted several groups/vertices

This chunk then puts the data into their group membership

HP_nodes <- HP_nodes %>% 
  mutate(group = membership(infomap.community(HP_network)))

HP_nodes %>% 
  datatable()

Finally, this network is complete with not only the above network’s title and highlighting, but also color coded to show which characters belong to each group.

visNetwork(HP_nodes, 
           HP_links, 
           main = "Network of HP Characters") %>% 
  visIgraphLayout(layout = "layout_nicely") %>% 
  visOptions(highlightNearest = T, nodesIdSelection = T)