R Intro- SNA
Chris Julien
10/4/2022
2 Setup
library("knitr")
knitr::opts_chunk$set(echo = TRUE, results='hold', root.dir = "C:/Users/Julie/Dropbox/Sociology/Current Projects/Diane Work/SNA Course- Teaching R")installAndLoad <- function(x) {
if(!suppressWarnings(require(x, character.only=TRUE, quietly=TRUE, warn.conflicts=FALSE))) {
paste("Didn't find ", x, ". Installing it.")
install.packages(x)
invisible(require(x, character.only=TRUE, warn.conflicts=FALSE))
}
invisible(TRUE)
}
# if(interactive() &&
# installAndLoad("rstudioapi") && rstudioapi::isAvailable() &&
# as.integer(substr(rstudioapi::versionInfo()$version, 1,1)) >= 1)
# setwd(dirname(rstudioapi::getActiveDocumentContext()$path))2.1 Loading Packages
installAndLoad("ggplot2")
installAndLoad("igraph")
installAndLoad("ggraph")
installAndLoad("igraph")
installAndLoad("sna")##
## Attaching package: 'statnet.common'## The following objects are masked from 'package:base':
##
## attr, order##
## 'network' 1.17.1 (2021-06-12), part of the Statnet Project
## * 'news(package="network")' for changes since last version
## * 'citation("network")' for citation information
## * 'https://statnet.org' for help, support, and other information##
## Attaching package: 'network'## The following objects are masked from 'package:igraph':
##
## %c%, %s%, add.edges, add.vertices, delete.edges, delete.vertices,
## get.edge.attribute, get.edges, get.vertex.attribute, is.bipartite,
## is.directed, list.edge.attributes, list.vertex.attributes,
## set.edge.attribute, set.vertex.attribute## sna: Tools for Social Network Analysis
## Version 2.6 created on 2020-10-5.
## copyright (c) 2005, Carter T. Butts, University of California-Irvine
## For citation information, type citation("sna").
## Type help(package="sna") to get started.installAndLoad("network")
installAndLoad("statnet")##
## 'ergm' 4.2.2 (2022-06-01), part of the Statnet Project
## * 'news(package="ergm")' for changes since last version
## * 'citation("ergm")' for citation information
## * 'https://statnet.org' for help, support, and other information## 'ergm' 4 is a major update that introduces some backwards-incompatible
## changes. Please type 'news(package="ergm")' for a list of major
## changes.##
## Attaching package: 'ergm'## The following object is masked from 'package:statnet.common':
##
## snctrl##
## 'networkDynamic' 0.11.2 (2022-05-04), part of the Statnet Project
## * 'news(package="networkDynamic")' for changes since last version
## * 'citation("networkDynamic")' for citation information
## * 'https://statnet.org' for help, support, and other information## Registered S3 method overwritten by 'tergm':
## method from
## simulate_formula.network ergm##
## 'tergm' 4.1.0 (2022-06-22), part of the Statnet Project
## * 'news(package="tergm")' for changes since last version
## * 'citation("tergm")' for citation information
## * 'https://statnet.org' for help, support, and other information##
## Attaching package: 'tergm'## The following object is masked from 'package:ergm':
##
## snctrl## The following object is masked from 'package:statnet.common':
##
## snctrl##
## 'ergm.count' 4.1.1 (2022-05-24), part of the Statnet Project
## * 'news(package="ergm.count")' for changes since last version
## * 'citation("ergm.count")' for citation information
## * 'https://statnet.org' for help, support, and other information##
## 'statnet' 2019.6 (2019-06-13), part of the Statnet Project
## * 'news(package="statnet")' for changes since last version
## * 'citation("statnet")' for citation information
## * 'https://statnet.org' for help, support, and other information## unable to reach CRANinstallAndLoad("tidyverse")## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v tibble 3.1.5 v dplyr 1.0.7
## v tidyr 1.1.4 v stringr 1.4.0
## v readr 2.0.2 v forcats 0.5.1
## v purrr 0.3.4## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## 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 dplyr::filter() masks stats::filter()
## x dplyr::groups() masks igraph::groups()
## x dplyr::lag() masks stats::lag()
## x purrr::simplify() masks igraph::simplify()set.seed(10051990)
setwd("C:/Users/Julie/Dropbox/Sociology/Current Projects/Diane Work/SNA Course- Teaching R")
getwd()
# Note: in R the direction of your slash matters (compared to in Stata where it doesn't). All file directories need to have a forward slash in order to work. You will note that if you copy and paste your file directory it contains back slashes, rather than forward slashes. As a result, you will need to change all of these back slashes to forward slashes.
## This is the more typical way to install and load packages ##
# install.packages("ggplot2") # for first-time downloading, then:
# library(ggplot2) # run every time, to "load" the package into the R session## [1] "C:/Users/Julie/Dropbox/Sociology/Current Projects/Diane Work/SNA Course- Teaching R"3 General Help in R
Writing “?” before a function opens the help page for that function, in the bottom-righthand side of the interface. For example: ?library(), ?readRDS()
You can also access the help page by highlighting the function in your code and pressing the F1 key.
If the package of the function is loaded, the help page for the function will open.
If the package of the function is not loaded, in the help window it will say, “Help for topic [function_name] is not in any loaded package but can be found in the following packages:” and then it will list the package(s) where the function can be found. In other words, if this happens, you haven’t loaded the package for the function that you’re trying to use. More on types of data in R can be found here: https://r-lang.com/r-data-types-vector-list-matrix-array-and-data-frame/
4 Load your Data
data <- read.csv(file = "grey_nodes.csv", header = TRUE)
## Remove objects in your environment with the function rm([object_name])
# rm(data)
# Read in Matrix .txt File
## transform data into a vector
data_vector <- as.vector(data)
## pull the names attribute from the data
data_names <- data_vector$name
## This accesses the variable "name" in the dataframe "data"
data_matrix <- matrix(scan("grey_adjacency.txt", n=44*44), 44, 44, byrow = TRUE, dimnames = list(data_names, data_names))
# Transform Matrix into Network Object
data_network <- graph_from_adjacency_matrix(data_matrix, mode = "directed")
plot(data_network)
# see "graph_from_" for full list of functions for creating graph objects
# Assign Attributes to Vertices
igraph::set.vertex.attribute(data_network, "sex", value = data_vector$sex)
igraph::set.vertex.attribute(data_network, "race", value = data_vector$race)
igraph::set.vertex.attribute(data_network, "birthyear", value = data_vector$birthyear)
igraph::set.vertex.attribute(data_network, "position", value = data_vector$position)
igraph::set.vertex.attribute(data_network, "season", value = data_vector$season)
igraph::set.vertex.attribute(data_network, "sign", value = data_vector$sign)
# Alternative Method of assigning attributes to Vertices
V(data_network)$sex <- data_vector$sex
V(data_network)$race <- data_vector$race
V(data_network)$birthyear <- data_vector$birthyear
V(data_network)$position <- data_vector$position
V(data_network)$season <- data_vector$season
V(data_network)$sign <- data_vector$sign
## The same can be done with edges: E(data_network) <- ...## IGRAPH 2f2111a DN-- 44 92 --
## + attr: name (v/c), sex (v/c)
## + edges from 2f2111a (vertex names):
## [1] addison ->derek addison ->karev addison ->sloan
## [4] adele ->chief altman ->burton altman ->owen
## [7] altman ->perkins altman ->sloan amelia ->sloan
## [10] arizona ->torres ava ->karev avery ->kepner
## [13] avery ->lexi bailey ->ben bailey ->lloyd
## [16] bailey ->tucker ben ->bailey burton ->altman
## [19] catherine->chief chief ->adele chief ->catherine
## [22] chief ->ellis grey colin ->yang denny ->izzie
## + ... omitted several edges
## IGRAPH 2f2111a DN-- 44 92 --
## + attr: name (v/c), race (v/c)
## + edges from 2f2111a (vertex names):
## [1] addison ->derek addison ->karev addison ->sloan
## [4] adele ->chief altman ->burton altman ->owen
## [7] altman ->perkins altman ->sloan amelia ->sloan
## [10] arizona ->torres ava ->karev avery ->kepner
## [13] avery ->lexi bailey ->ben bailey ->lloyd
## [16] bailey ->tucker ben ->bailey burton ->altman
## [19] catherine->chief chief ->adele chief ->catherine
## [22] chief ->ellis grey colin ->yang denny ->izzie
## + ... omitted several edges
## IGRAPH 2f2111a DN-- 44 92 --
## + attr: name (v/c), birthyear (v/n)
## + edges from 2f2111a (vertex names):
## [1] addison ->derek addison ->karev addison ->sloan
## [4] adele ->chief altman ->burton altman ->owen
## [7] altman ->perkins altman ->sloan amelia ->sloan
## [10] arizona ->torres ava ->karev avery ->kepner
## [13] avery ->lexi bailey ->ben bailey ->lloyd
## [16] bailey ->tucker ben ->bailey burton ->altman
## [19] catherine->chief chief ->adele chief ->catherine
## [22] chief ->ellis grey colin ->yang denny ->izzie
## + ... omitted several edges
## IGRAPH 2f2111a DN-- 44 92 --
## + attr: name (v/c), position (v/c)
## + edges from 2f2111a (vertex names):
## [1] addison ->derek addison ->karev addison ->sloan
## [4] adele ->chief altman ->burton altman ->owen
## [7] altman ->perkins altman ->sloan amelia ->sloan
## [10] arizona ->torres ava ->karev avery ->kepner
## [13] avery ->lexi bailey ->ben bailey ->lloyd
## [16] bailey ->tucker ben ->bailey burton ->altman
## [19] catherine->chief chief ->adele chief ->catherine
## [22] chief ->ellis grey colin ->yang denny ->izzie
## + ... omitted several edges
## IGRAPH 2f2111a DN-- 44 92 --
## + attr: name (v/c), season (v/n)
## + edges from 2f2111a (vertex names):
## [1] addison ->derek addison ->karev addison ->sloan
## [4] adele ->chief altman ->burton altman ->owen
## [7] altman ->perkins altman ->sloan amelia ->sloan
## [10] arizona ->torres ava ->karev avery ->kepner
## [13] avery ->lexi bailey ->ben bailey ->lloyd
## [16] bailey ->tucker ben ->bailey burton ->altman
## [19] catherine->chief chief ->adele chief ->catherine
## [22] chief ->ellis grey colin ->yang denny ->izzie
## + ... omitted several edges
## IGRAPH 2f2111a DN-- 44 92 --
## + attr: name (v/c), sign (v/c)
## + edges from 2f2111a (vertex names):
## [1] addison ->derek addison ->karev addison ->sloan
## [4] adele ->chief altman ->burton altman ->owen
## [7] altman ->perkins altman ->sloan amelia ->sloan
## [10] arizona ->torres ava ->karev avery ->kepner
## [13] avery ->lexi bailey ->ben bailey ->lloyd
## [16] bailey ->tucker ben ->bailey burton ->altman
## [19] catherine->chief chief ->adele chief ->catherine
## [22] chief ->ellis grey colin ->yang denny ->izzie
## + ... omitted several edges5 Network Statistics
summary(data_network) # Get an overall summary
gsize(data_network) # How many edges are present?
gorder(data_network) # How many nodes are present?
distance_table(data_network, directed = TRUE) # geodesics
edge_density(data_network, loops = TRUE) # graph density
transitivity(data_network, type = c("average"), isolates = c("zero")) # transitivity
reciprocity(data_network, ignore.loops = TRUE) # reciprocity; reciprocity of 1 makes sense for a dating network...
igraph::components(data_network) # components
centr_degree(data_network) # degree centralization
centr_betw(data_network) # betweenness centralization
centr_eigen(data_network) # eigenvector centralization
centr_degree_res <- centr_degree(data_network)$res
view(centr_degree_res)
# Actor Centrality Measures
igraph::degree(data_network) # What is each actor's degree?
mean(igraph::degree(data_network)) # What is the average degree in the whole network?
# Alternative Coding to the above computation of the average degree
data_network %>%
igraph::degree() %>% # This is the magrittr pipe, heavily used in the Tidyverse
mean()
hist(igraph::degree(data_network), right = FALSE, xlab = "Degree", main = "Grey's Anatomy") # Plot the degree distribution in a histogram
data_network$degree <- igraph::degree(data_network) # Create a column in the attribute file with each actor's corresponding degree
deg <- igraph::degree(data_network) # Create a separate value object in R which contains the degree of each node
deg # See what is stored in the value object you just created
saveRDS(data_network, file = "data_network_v1.0.RDS") # Save your R object## IGRAPH 2f2111a DN-- 44 92 --
## + attr: name (v/c), sex (v/c), race (v/c), birthyear (v/n), position
## | (v/c), season (v/n), sign (v/c)
## [1] 92
## [1] 44
## $res
## [1] 92 204 246 186 132 66 36 16
##
## $unconnected
## [1] 914
##
## [1] 0.04752066
## [1] 0
## [1] 1
## $membership
## addison adele altman amelia arizona ava
## 1 2 1 1 1 1
## avery bailey ben burton catherine chief
## 1 3 3 1 2 2
## colin denny derek ellis grey finn grey
## 1 1 1 2 1 1
## hahn hank izzie karev kepner lexi
## 1 1 1 1 1 1
## lloyd lucy megan mostow mrs. seabury nancy
## 3 1 4 4 1 1
## olivia o'malley owen perkins pierce preston
## 1 1 1 1 4 1
## reed sloan steve susan grey thatch grey torres
## 1 1 1 2 2 1
## tucker yang
## 3 1
##
## $csize
## [1] 31 6 4 3
##
## $no
## [1] 4
##
## $res
## [1] 6 2 8 2 2 2 4 6 2 2 2 6 2 2 4 4 2 8 2 2 8 18 4 6 2
## [26] 2 4 2 2 2 4 8 4 2 2 2 2 14 2 2 4 10 2 6
##
## $centralization
## [1] 0.1644132
##
## $theoretical_max
## [1] 3698
##
## $res
## [1] 145.13333 0.00000 306.00000 0.00000 0.00000 0.00000 6.50000
## [8] 6.00000 0.00000 0.00000 0.00000 14.00000 0.00000 0.00000
## [15] 50.70000 12.00000 0.00000 122.40000 0.00000 0.00000 128.50476
## [22] 350.38095 14.59048 103.74286 0.00000 0.00000 2.00000 0.00000
## [29] 0.00000 0.00000 14.50476 148.70000 162.00000 0.00000 0.00000
## [36] 0.00000 0.00000 465.71905 0.00000 0.00000 8.00000 265.12381
## [43] 0.00000 114.00000
##
## $centralization
## [1] 0.2324505
##
## $theoretical_max
## [1] 77658
##
## $vector
## [1] 5.024923e-01 8.525957e-17 2.326524e-01 1.800718e-01 1.831075e-01
## [6] 2.702897e-01 2.281153e-01 8.147959e-17 7.664961e-17 6.288357e-02
## [11] 6.677966e-17 8.063959e-17 5.883552e-03 1.261075e-01 1.928699e-01
## [16] 1.335593e-16 5.705135e-02 2.110748e-01 1.831075e-01 1.261075e-01
## [21] 4.665641e-01 1.000000e+00 3.319470e-01 5.120188e-01 6.719966e-17
## [26] 2.702897e-01 6.184469e-17 3.548982e-17 2.702897e-01 1.800718e-01
## [31] 3.983930e-01 4.739479e-01 6.876712e-02 6.288357e-02 5.491472e-17
## [36] 5.883552e-03 1.800718e-01 6.662177e-01 5.705135e-02 5.018975e-17
## [41] 9.953950e-17 6.774490e-01 6.572967e-17 2.176757e-02
##
## $value
## [1] 7.399467
##
## $options
## $options$bmat
## [1] "I"
##
## $options$n
## [1] 44
##
## $options$which
## [1] "LA"
##
## $options$nev
## [1] 1
##
## $options$tol
## [1] 0
##
## $options$ncv
## [1] 0
##
## $options$ldv
## [1] 0
##
## $options$ishift
## [1] 1
##
## $options$maxiter
## [1] 1000
##
## $options$nb
## [1] 1
##
## $options$mode
## [1] 1
##
## $options$start
## [1] 1
##
## $options$sigma
## [1] 0
##
## $options$sigmai
## [1] 0
##
## $options$info
## [1] 0
##
## $options$iter
## [1] 2
##
## $options$nconv
## [1] 1
##
## $options$numop
## [1] 30
##
## $options$numopb
## [1] 0
##
## $options$numreo
## [1] 20
##
##
## $centralization
## [1] 0.8522517
##
## $theoretical_max
## [1] 42
##
## addison adele altman amelia arizona ava
## 6 2 8 2 2 2
## avery bailey ben burton catherine chief
## 4 6 2 2 2 6
## colin denny derek ellis grey finn grey
## 2 2 4 4 2 8
## hahn hank izzie karev kepner lexi
## 2 2 8 18 4 6
## lloyd lucy megan mostow mrs. seabury nancy
## 2 2 4 2 2 2
## olivia o'malley owen perkins pierce preston
## 4 8 4 2 2 2
## reed sloan steve susan grey thatch grey torres
## 2 14 2 2 4 10
## tucker yang
## 2 6
## [1] 4.181818
## [1] 4.181818
## addison adele altman amelia arizona ava
## 6 2 8 2 2 2
## avery bailey ben burton catherine chief
## 4 6 2 2 2 6
## colin denny derek ellis grey finn grey
## 2 2 4 4 2 8
## hahn hank izzie karev kepner lexi
## 2 2 8 18 4 6
## lloyd lucy megan mostow mrs. seabury nancy
## 2 2 4 2 2 2
## olivia o'malley owen perkins pierce preston
## 4 8 4 2 2 2
## reed sloan steve susan grey thatch grey torres
## 2 14 2 2 4 10
## tucker yang
## 2 66 Network Graphs
data_network <- readRDS("data_network_v1.0.RDS") # Load the previously saved R object
plot(data_network) # Generic Plot
# Graph 1
ggraph(data_network, layout = "fr") +
geom_edge_link(aes()) +
geom_node_point() +
geom_node_text(aes(label = name)) +
theme_void()
# Graph 2
arrow_1 <- grid::arrow(angle = 30, ends = "last", type = "closed", length = unit(.08, "inches")) # Setting what the arrows look like
graph_2 <- ggraph(data_network, layout = "fr") +
geom_edge_link(aes(),
show.legend = TRUE,
end_cap = circle(.05, 'inches'),
arrow = arrow_1) +
geom_node_point(color = "lightblue",
size = 3) +
geom_node_text(aes(label = name),
repel = TRUE,
size = 5) +
labs(title = "Graph 2") +
theme_void()
graph_2
# png(filename = "C:/Users/Julie/Dropbox/Sociology/Current Projects/Diane Work/SNA Course- Teaching R/Graph 1 v1.0.png", 500, 500)
# graph_2
# dev.off()
# Graph 3, nodes sized by degree
graph_3 <- ggraph(data_network, layout = "fr") +
geom_edge_link(aes(),
show.legend = TRUE,
end_cap = circle(.05, 'inches'),
arrow = arrow_1) +
geom_node_point(color = "lightblue",
size = data_network$degree) +
geom_node_text(aes(label = name),
repel = TRUE,
size = 5) +
labs(title = "Graph 3: Nodes sized by Degree") +
theme_void()
graph_3
# Alternative Plotting:
plot(data_network,
vertex.size = data_network$degree,
vertex.color = adjustcolor("lightblue"),
vertex.label = data_network$name,
edge.arrow = arrow_1,
layout = layout_with_fr(data_network))
# Plotting Communities
data_network_betw <- data_network %>%
cluster_edge_betweenness()
plot(data_network_betw, data_network)