library(readr)
## Warning: 程辑包'readr'是用R版本4.3.2 来建造的
library(tidyverse)
## Warning: 程辑包'tidyverse'是用R版本4.3.3 来建造的
## Warning: 程辑包'ggplot2'是用R版本4.3.3 来建造的
## Warning: 程辑包'forcats'是用R版本4.3.2 来建造的
## Warning: 程辑包'lubridate'是用R版本4.3.2 来建造的
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ purrr 1.0.2
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.5.0 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(igraph)
## Warning: 程辑包'igraph'是用R版本4.3.3 来建造的
##
## 载入程辑包：'igraph'
##
## The following objects are masked from 'package:lubridate':
##
## %--%, union
##
## The following objects are masked from 'package:dplyr':
##
## as_data_frame, groups, union
##
## The following objects are masked from 'package:purrr':
##
## compose, simplify
##
## The following object is masked from 'package:tidyr':
##
## crossing
##
## The following object is masked from 'package:tibble':
##
## as_data_frame
##
## The following objects are masked from 'package:stats':
##
## decompose, spectrum
##
## The following object is masked from 'package:base':
##
## union
df = read_csv("C:/Users/tsong/Downloads/Basic_LinkedInDataExport_03-14-2024/Connections.csv", skip = 3, show_col_types = FALSE)
str(df)
## spc_tbl_ [2,420 × 7] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ First Name : chr [1:2420] "Rémi" "Lynn" "Bianca" "Jay" ...
## $ Last Name : chr [1:2420] "Nore" "Mark" "Iacobacci" "Tan, CFA" ...
## $ URL : chr [1:2420] "https://www.linkedin.com/in/reminore" "https://www.linkedin.com/in/lynnmark" "https://www.linkedin.com/in/bianca-iacobacci" "https://www.linkedin.com/in/jay-tan-cfa-aa682867" ...
## $ Email Address: chr [1:2420] NA NA NA NA ...
## $ Company : chr [1:2420] "Air France" "McGill University - Desautels Faculty of Management" "MAVRIK CORP." "LionGuard Capital Management Inc." ...
## $ Position : chr [1:2420] "Corporate Finance Manager" "Manager, Alumni Programs" "Investment Analyst" "Portfolio Manager" ...
## $ Connected On : chr [1:2420] "14 Mar 2024" "13 Mar 2024" "13 Mar 2024" "13 Mar 2024" ...
## - attr(*, "spec")=
## .. cols(
## .. `First Name` = col_character(),
## .. `Last Name` = col_character(),
## .. URL = col_character(),
## .. `Email Address` = col_character(),
## .. Company = col_character(),
## .. Position = col_character(),
## .. `Connected On` = col_character()
## .. )
## - attr(*, "problems")=<externalptr>
contacts_by_company <- df %>% group_by(Company) %>% summarise(Count = n()) %>% arrange(desc(Count))
total_contacts = df %>% summarise(Total_Count = n())
print(contacts_by_company)
## # A tibble: 1,646 × 2
## Company Count
## <chr> <int>
## 1 <NA> 81
## 2 McGill University - Desautels Faculty of Management 45
## 3 McGill University 30
## 4 Desautels Capital Management 21
## 5 Self-employed 19
## 6 Deloitte 18
## 7 EDHEC Business School 18
## 8 RBC 17
## 9 BNP Paribas 16
## 10 EY 14
## # ℹ 1,636 more rows
print(total_contacts)
## # A tibble: 1 × 1
## Total_Count
## <int>
## 1 2420
edges <- df %>%
select(Company, Position, `Connected On`) %>%
distinct() %>%
group_by(Company, Position) %>%
summarise(Count = n_distinct(`Connected On`), .groups = 'drop') %>%
filter(Count > 1) %>%
mutate(Position = as.character(Position),
Position = paste(Company, Position, sep = ": ")) %>%
select(-Count) %>%
arrange(Position) %>%
distinct()
graph = graph_from_data_frame(edges,directed = TRUE)
## Warning in graph_from_data_frame(edges, directed = TRUE): In `d' `NA' elements
## were replaced with string "NA"
plot(graph, edge.arrow.size=0.5, vertex.size =5,vertex.label.dist = 2, vertex.label.cex = 0.8)
# Create a label for nodes (using First Name and 1 letter of Last Name)
df <- df %>%rename(First_Name = "First Name", Last_Name = "Last Name")%>%
mutate(Label = paste(First_Name, substr(Last_Name, 1, 1), sep = " "))
# Get unique contacts as nodes
nodes <- df %>%
distinct(Label, Company) %>%
mutate(ID = row_number())
# Rename columns as needed
nodes <- nodes %>%
select(ID, Label, Company)
# Print nodes data frame
print(nodes)
## # A tibble: 2,384 × 3
## ID Label Company
## <int> <chr> <chr>
## 1 1 Rémi N Air France
## 2 2 Lynn M McGill University - Desautels Faculty of Management
## 3 3 Bianca I MAVRIK CORP.
## 4 4 Jay T LionGuard Capital Management Inc.
## 5 5 Weiting Z Susallwave
## 6 6 Vladimir D Chess Federation of Canada
## 7 7 Drishti J Desautels Capital Management
## 8 8 Wei L Fiera Capital
## 9 9 Emma P Medisca
## 10 10 Ziyuan W PwC Canada
## # ℹ 2,374 more rows
edges <- df %>%
distinct(Label, Company) %>%
mutate(ID = row_number())%>%inner_join(nodes, by = c("Company" = "Company"))%>%filter(ID.x != ID.y) %>%
select(from = ID.x, to = ID.y)%>% distinct()
## Warning in inner_join(., nodes, by = c(Company = "Company")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 2 of `x` matches multiple rows in `y`.
## ℹ Row 17 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.
edges
## # A tibble: 9,826 × 2
## from to
## <int> <int>
## 1 2 126
## 2 2 151
## 3 2 170
## 4 2 179
## 5 2 210
## 6 2 212
## 7 2 218
## 8 2 230
## 9 2 231
## 10 2 242
## # ℹ 9,816 more rows
# Create graph
graph <- graph_from_data_frame(d = edges, vertices = nodes, directed = TRUE)
# Plot the graph
plot(graph, edge.arrow.size = 0.5, vertex.size = 5, vertex.label.dist = 2, vertex.label.cex = 0.8)
myself <- data.frame(ID = max(nodes$ID) + 1, Label = "Myself", Company = "McGill University")
nodes <- bind_rows(nodes, myself)
nodes$color <- ifelse(nodes$Label == "Myself", "red", "green")
nodes$shape <- ifelse(nodes$Label == "Myself", "square", "circle")
nodes$size <- ifelse(nodes$Label == "Myself", 10, 1)
graph <- graph_from_data_frame(d = edges, vertices = nodes, directed = TRUE)
V(graph)$color <-nodes$color
V(graph)$shape <-nodes$shape
V(graph)$size <-nodes$size
plot(graph, vertex.color=V(graph)$color,vertex.shapes=V(graph)$shape, vertex.size = V(graph)$size, vertex.label.dist = 10, vertex.label.cex = 0.8, edge.arrow.size = 0.5)
library(tidygraph)
## Warning: 程辑包'tidygraph'是用R版本4.3.3 来建造的
##
## 载入程辑包：'tidygraph'
## The following object is masked from 'package:igraph':
##
## groups
## The following object is masked from 'package:stats':
##
## filter
graph <- tbl_graph(nodes = nodes, edges = edges, directed = FALSE)
library(ggraph)
## Warning: 程辑包'ggraph'是用R版本4.3.3 来建造的
ggraph(graph, layout = "fr") +
geom_edge_link() +
geom_node_point(aes(color = color, size = size, shape = shape)) +
scale_color_identity() +
scale_size_continuous(range = c(2, 10)) +
theme_void()
