In-Class Exercise 05

MC 01

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

kg <- fromJSON("data/MC1_graph.json")

Inspect structure

str(kg, max.level =1)

List of 5
 $ directed  : logi TRUE
 $ multigraph: logi TRUE
 $ graph     :List of 2
 $ nodes     :'data.frame': 17412 obs. of  10 variables:
 $ links     :'data.frame': 37857 obs. of  4 variables:

Extract and inspect

nodes_tbl <- as_tibble(kg$nodes)
edges_tbl <- as_tibble(kg$links)

Initial EDA

ggplot(data = edges_tbl, aes(y = `Edge Type`)) + 
  geom_bar()

Creating knowledge graph

Step 1: Mapping from node id to row index

id_map <- tibble(id = nodes_tbl$id, index = seq_len(nrow(nodes_tbl)))

Step 2: Map source and target IDs to row indices

edges_tbl <- edges_tbl %>%
  left_join(id_map, by = c("source" = "id"), suffix = c("", "_source")) %>%
  rename(from = index) %>%
  left_join(id_map, by = c("target" = "id"), suffix = c("", "_target")) %>%
  rename(to = index)

Step 3

edges_tbl <- edges_tbl %>%
  filter(!is.na(from), !is.na(to))

Step 4: Creating the graph

graph <- tbl_graph(nodes = nodes_tbl, edges = edges_tbl, 
                   directed = kg$directed)

Visualizing the knowledge graph

set.seed(1234)

Visualizing the whole Graph

ggraph(graph, layout = "fr") + 
  geom_edge_link(alpha = 0.3, colour = "gray") +
  geom_node_point(aes(color = `Node Type`), size = 4) +
  geom_node_text(aes(label = name), repel = TRUE, size = 2.5) +
  theme_void()

Step 1: Filter edges to only “MemberOf”

graph_memberof <- graph %>%
  activate(edges) %>%
  filter(`Edge Type` == "MemberOf")

Step 2: Extract only connected nodes (ie. used in these edges)

used_node_indices <- graph_memberof %>%
  activate(edges) %>%
  as_tibble() %>%
  select(from, to) %>%
  unlist() %>%
  unique()

Step 3: Keep only those nodes

graph_memberof <- graph_memberof %>%
  activate(nodes) %>%
  mutate(row_id = row_number()) %>%
  filter(row_id %in% used_node_indices) %>%
  select(-row_id)  #optional cleanup

Plot the sub-graph

ggraph(graph_memberof, layout = "fr") + 
  geom_edge_link(alpha = 0.5, colour = "gray") +
  geom_node_point(aes(color = `Node Type`), size = 1) +
  geom_node_text(aes(label = name), repel = TRUE, size = 2.5) +
  theme_void()