In [1]:

    

getwd()


    

    





'/home/jonathanmorgan/work/django/research/work/phd_work/methods/network_analysis/statnet'

In [2]:

    

# code files (in particular SNA function library, modest though it may be)
code_directory <- "/home/jonathanmorgan/work/django/research/context_analysis/R/sna"
sna_function_file_path <- paste( code_directory, "/", 'functions-sna.r', sep = "" )

# home directory
home_directory <- getwd()
home_directory <- "/home/jonathanmorgan/work/django/research/work/phd_work/methods"

# data directories
data_directory <- paste( home_directory, "/data", sep = "" )
workspace_file_name <- "statnet-grp_month.RData"
workspace_file_path <- paste( data_directory, "/", workspace_file_name )


    

In [3]:

    

# set working directory to data directory for now.
setwd( data_directory )
getwd()


    

    





'/home/jonathanmorgan/work/django/research/work/phd_work/methods/data'

In [4]:

    

source( sna_function_file_path )


    

In [5]:

    

# statnet/sna functions
# - /home/jonathanmorgan/work/django/research/context_analysis/R/sna/stanet/functions-statnet.r
statnetFunctionFilePath <- paste( code_directory, "/statnet/", 'functions-statnet.r', sep = "" )


    

In [6]:

    

source( statnetFunctionFilePath )


    

    




Loading required package: statnet.common

Attaching package: ‘statnet.common’

The following object is masked from ‘package:base’:

    order

Loading required package: network
network: Classes for Relational Data
Version 1.13.0.1 created on 2015-08-31.
copyright (c) 2005, Carter T. Butts, University of California-Irvine
                    Mark S. Handcock, University of California -- Los Angeles
                    David R. Hunter, Penn State University
                    Martina Morris, University of Washington
                    Skye Bender-deMoll, University of Washington
 For citation information, type citation("network").
 Type help("network-package") to get started.

sna: Tools for Social Network Analysis
Version 2.4 created on 2016-07-23.
copyright (c) 2005, Carter T. Butts, University of California-Irvine
 For citation information, type citation("sna").
 Type help(package="sna") to get started.

In [7]:

    

# assumes that you've already set working directory above to the
#     working directory.
setwd( data_directory )
load( workspace_file_name )


    

In [5]:

    

# initialize variables
gmAutomatedDataFolder <- paste( data_directory, "/network/grp_month", sep = "" )
gmAutomatedDataFile <- "sourcenet_data-20171205-022551-grp_month-automated.tab"
gmAutomatedDataPath <- paste( gmAutomatedDataFolder, "/", gmAutomatedDataFile, sep = "" )


    

In [6]:

    

gmAutomatedDataPath


    

    





'/home/jonathanmorgan/work/django/research/work/phd_work/methods/data/network/grp_month/sourcenet_data-20171205-022551-grp_month-automated.tab'

In [7]:

    

# tab-delimited:
gmAutomatedDataDF <- read.delim( gmAutomatedDataPath, header = TRUE, row.names = 1, check.names = FALSE )


    

In [8]:

    

# get count of rows...
gmAutomatedRowCount <- nrow( gmAutomatedDataDF )
paste( "grp_month automated row count = ", gmAutomatedRowCount, sep = "" )

# ...and columns
gmAutomatedColumnCount <- ncol( gmAutomatedDataDF )
paste( "grp_month automated column count = ", gmAutomatedColumnCount, sep = "" )


    

    





'grp_month automated row count = 1167'






    





'grp_month automated column count = 1169'

In [9]:

    

# the below syntax returns only as many columns as there are rows, so
#     omitting any trait columns that lie in columns on the right side
#     of the file.
gmAutomatedNetworkDF <- gmAutomatedDataDF[ , 1 : gmAutomatedRowCount ]
#str( gmAutomatedNetworkDF )


    

In [10]:

    

# convert to a matrix
gmAutomatedNetworkMatrix <- as.matrix( gmAutomatedNetworkDF )
# str( gmAutomatedNetworkMatrix )


    

In [11]:

    

# make sure you've loaded the statnet library
# install.packages( "statnet" )
library( statnet )


    

    




Loading required package: tergm
Loading required package: statnet.common

Attaching package: ‘statnet.common’

The following object is masked from ‘package:base’:

    order

Loading required package: ergm
Loading required package: network
network: Classes for Relational Data
Version 1.13.0 created on 2015-08-31.
copyright (c) 2005, Carter T. Butts, University of California-Irvine
                    Mark S. Handcock, University of California -- Los Angeles
                    David R. Hunter, Penn State University
                    Martina Morris, University of Washington
                    Skye Bender-deMoll, University of Washington
 For citation information, type citation("network").
 Type help("network-package") to get started.


ergm: version 3.8.0, created on 2017-08-18
Copyright (c) 2017, Mark S. Handcock, University of California -- Los Angeles
                    David R. Hunter, Penn State University
                    Carter T. Butts, University of California -- Irvine
                    Steven M. Goodreau, University of Washington
                    Pavel N. Krivitsky, University of Wollongong
                    Martina Morris, University of Washington
                    with contributions from
                    Li Wang
                    Kirk Li, University of Washington
                    Skye Bender-deMoll, University of Washington
Based on "statnet" project software (statnet.org).
For license and citation information see statnet.org/attribution
or type citation("ergm").

NOTE: Versions before 3.6.1 had a bug in the implementation of the bd()
constriant which distorted the sampled distribution somewhat. In
addition, Sampson's Monks datasets had mislabeled vertices. See the
NEWS and the documentation for more details.

Loading required package: networkDynamic

networkDynamic: version 0.9.0, created on 2016-01-12
Copyright (c) 2016, Carter T. Butts, University of California -- Irvine
                    Ayn Leslie-Cook, University of Washington
                    Pavel N. Krivitsky, University of Wollongong
                    Skye Bender-deMoll, University of Washington
                    with contributions from
                    Zack Almquist, University of California -- Irvine
                    David R. Hunter, Penn State University
                    Li Wang
                    Kirk Li, University of Washington
                    Steven M. Goodreau, University of Washington
                    Jeffrey Horner
                    Martina Morris, University of Washington
Based on "statnet" project software (statnet.org).
For license and citation information see statnet.org/attribution
or type citation("networkDynamic").


tergm: version 3.4.1, created on 2017-09-12
Copyright (c) 2017, Pavel N. Krivitsky, University of Wollongong
                    Mark S. Handcock, University of California -- Los Angeles
                    with contributions from
                    David R. Hunter, Penn State University
                    Steven M. Goodreau, University of Washington
                    Martina Morris, University of Washington
                    Nicole Bohme Carnegie, New York University
                    Carter T. Butts, University of California -- Irvine
                    Ayn Leslie-Cook, University of Washington
                    Skye Bender-deMoll
                    Li Wang
                    Kirk Li, University of Washington
Based on "statnet" project software (statnet.org).
For license and citation information see statnet.org/attribution
or type citation("tergm").

Loading required package: ergm.count

ergm.count: version 3.2.2, created on 2016-03-29
Copyright (c) 2016, Pavel N. Krivitsky, University of Wollongong
                    with contributions from
                    Mark S. Handcock, University of California -- Los Angeles
                    David R. Hunter, Penn State University
Based on "statnet" project software (statnet.org).
For license and citation information see statnet.org/attribution
or type citation("ergm.count").

NOTE: The form of the term ‘CMP’ has been changed in version 3.2 of
‘ergm.count’. See the news or help('CMP') for more information.

Loading required package: sna
sna: Tools for Social Network Analysis
Version 2.4 created on 2016-07-23.
copyright (c) 2005, Carter T. Butts, University of California-Irvine
 For citation information, type citation("sna").
 Type help(package="sna") to get started.


statnet: version 2016.9, created on 2016-08-29
Copyright (c) 2016, Mark S. Handcock, University of California -- Los Angeles
                    David R. Hunter, Penn State University
                    Carter T. Butts, University of California -- Irvine
                    Steven M. Goodreau, University of Washington
                    Pavel N. Krivitsky, University of Wollongong
                    Skye Bender-deMoll
                    Martina Morris, University of Washington
Based on "statnet" project software (statnet.org).
For license and citation information see statnet.org/attribution
or type citation("statnet").


There are updates for the following statnet packages on CRAN:






    




        Installed ReposVer   Built  
network "1.13.0"  "1.13.0.1" "3.4.2"






    




Restart R and use "statnet::update_statnet()" to get the updates.

In [12]:

    

# If you have a data frame of attributes (each attribute is a column, with
#     attribute name the column name), you can associate those attributes
#     when you create the network.
# attribute help: http://www.inside-r.org/packages/cran/network/docs/loading.attributes

# load attributes from a file:
#tab_attribute_test1 <- read.delim( "tab-test1-attribute_data.txt", header = TRUE, row.names = 1, check.names = FALSE )

# or create DataFrame by just grabbing the attribute columns
gmAutomatedNetworkAttributeDF <- gmAutomatedDataDF[ , 1168:1169 ]

# convert matrix to statnet network object instance.
gmAutomatedNetworkStatnet <- network( gmAutomatedNetworkMatrix, matrix.type = "adjacency", directed = FALSE, vertex.attr = gmAutomatedNetworkAttributeDF )

# look at information now.
gmAutomatedNetworkStatnet

# Network attributes:
#  vertices = 314
#  directed = FALSE
#  hyper = FALSE
#  loops = FALSE
#  multiple = FALSE
#  bipartite = FALSE
#  total edges= 309
#    missing edges= 0
#    non-missing edges= 309
#
# Vertex attribute names:
#    person_type vertex.names
#
# No edge attributes


    

    






 Network attributes:
  vertices = 1167 
  directed = FALSE 
  hyper = FALSE 
  loops = FALSE 
  multiple = FALSE 
  bipartite = FALSE 
  total edges= 1152 
    missing edges= 0 
    non-missing edges= 1152 

 Vertex attribute names: 
    person_id person_type vertex.names 

 Edge attribute names not shown 

In [13]:

    

# calais - include ties Greater than or equal to 0 (GE0)
gmAutomatedMeanTieWeightGE0Vector <- apply( gmAutomatedNetworkMatrix, 1, calculateListMean )
gmAutomatedDataDF$meanTieWeightGE0 <- gmAutomatedMeanTieWeightGE0Vector

# calais - include ties Greater than or equal to 1 (GE1)
gmAutomatedMeanTieWeightGE1Vector <- apply( gmAutomatedNetworkMatrix, 1, calculateListMean, minValueToIncludeIN = 1 )
gmAutomatedDataDF$meanTieWeightGE1 <- gmAutomatedMeanTieWeightGE1Vector

# automated - Max tie weight?
gmAutomatedMaxTieWeightVector <- apply( gmAutomatedNetworkMatrix, 1, calculateListMax )
gmAutomatedDataDF$maxTieWeight <- gmAutomatedMaxTieWeightVector


    

In [14]:

    

# assuming that our statnet network object is in reference test1_statnet.

# Use the degree function in the sna package to create vector of degree values
#    for each node.  Make sure to pass the gmode parameter to tell it that the
#    graph is not directed (gmode = "graph", instead of "digraph").
# Doc: http://www.inside-r.org/packages/cran/sna/docs/degree
#degree_vector <- degree( test1_statnet, gmode = "graph" )

# If you have other libraries loaded that also implement a degree function, you
#    can also call this with package name:
gmAutomatedDegreeVector <- sna::degree( gmAutomatedNetworkStatnet, gmode = "graph" )

# output the vector
gmAutomatedDegreeVector

# want more info on the degree function?  You can get to it eventually through
#    the following:
#help( package = "sna" )
#??sna::degree

# what is the average (mean) degree?
gmAutomatedAvgDegree <- mean( gmAutomatedDegreeVector )
paste( "average degree = ", gmAutomatedAvgDegree, sep = "" )

# subset vector to get only those that are above mean
gmAutomatedAboveMeanVector <- gmAutomatedDegreeVector[ gmAutomatedDegreeVector > gmAutomatedAvgDegree ]

# Take the degree and associate it with each node as a node attribute.
#    (%v% is a shortcut for the get.vertex.attribute command)
gmAutomatedNetworkStatnet %v% "degree" <- gmAutomatedDegreeVector

# also add degree vector to original data frame
gmAutomatedDataDF$degree <- gmAutomatedDegreeVector


    

    






	
30
	
1
	
39
	
1
	
34
	
1
	
1
	
50
	
26
	
1
	
29
	
1
	
47
	
1
	
1
	
93
	
46
	
29
	
47
	
71
	
2
	
9
	
1
	
1
	
2
	
1
	
35
	
0
	
2
	
2
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
42
	
1
	
0
	
1
	
2
	
2
	
1
	
5
	
1
	
0
	
1
	
43
	
5
	
1
	
14
	
1
	
1
	
2
	
2
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
0
	
2
	
4
	
1
	
1
	
32
	
1
	
1
	
3
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
7
	
1
	
1
	
1
	
9
	
2
	
1
	
1
	
1
	
1
	
1
	
2
	
5
	
0
	
0
	
0
	
0
	
1
	
1
	
1
	
0
	
1
	
1
	
2
	
0
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
35
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
19
	
1
	
1
	
1
	
1
	
1
	
1
	
27
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
4
	
1
	
1
	
32
	
49
	
1
	
2
	
0
	
1
	
1
	
44
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
2
	
1
	
1
	
4
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
2
	
2
	
0
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
4
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
2
	
1
	
15
	
1
	
0
	
1
	
1
	
2
	
2
	
2
	
2
	
2
	
2
	
4
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
2
	
2
	
2
	
2
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
0
	
2
	
0
	
1
	
2
	
3
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
0
	
1
	
72
	
22
	
46
	
3
	
1
	
1
	
1
	
10
	
8
	
2
	
1
	
1
	
2
	
1
	
1
	
2
	
1
	
2
	
2
	
1
	
1
	
1
	
1
	
0
	
0
	
0
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
0
	
1
	
1
	
0
	
0
	
1
	
1
	
0
	
0
	
1
	
1
	
1
	
3
	
2
	
15
	
1
	
1
	
1
	
1
	
0
	
2
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
2
	
1
	
1
	
1
	
0
	
1
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
0
	
1
	
7
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
0
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
3
	
2
	
4
	
2
	
1
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
0
	
1
	
1
	
1
	
1
	
2
	
1
	
4
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
2
	
1
	
0
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
4
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
5
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
2
	
2
	
0
	
2
	
2
	
0
	
1
	
1
	
1
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
4
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
1
	
0
	
0
	
1
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
2
	
1
	
0
	
1
	
0
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
0
	
2
	
2
	
2
	
2
	
2
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
0
	
1
	
0
	
0
	
1
	
1
	
0
	
1
	
3
	
2
	
1
	
1
	
1
	
2
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
0
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
0
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
6
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
0
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
0
	
2
	
2
	
2
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
2
	
2
	
2
	
2
	
2
	
2
	
2
	
1
	
1
	
1
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
1
	
1
	
2
	
0
	
1
	
0
	
1








    





'average degree = 1.97429305912596'

In [15]:

    

# average author degree (person types 2 and 4)
gmAutomatedAverageAuthorDegree2And4 <- calcAuthorMeanDegree( dataFrameIN = gmAutomatedDataDF, includeBothIN = TRUE )
paste( "average author degree (2 and 4) = ", gmAutomatedAverageAuthorDegree2And4, sep = "" )

# average author degree (person type 2 only)
gmAutomatedAverageAuthorDegreeOnly2 <- calcAuthorMeanDegree( dataFrameIN = gmAutomatedDataDF, includeBothIN = FALSE )
paste( "average author degree (only 2) = ", gmAutomatedAverageAuthorDegreeOnly2, sep = "" )

# average source degree (person types 3 and 4)
gmAutomatedAverageSourceDegree3And4 <- calcSourceMeanDegree( dataFrameIN = gmAutomatedDataDF, includeBothIN = TRUE )
paste( "average source degree (3 and 4) = ", gmAutomatedAverageSourceDegree3And4, sep = "" )

# average source degree (person type 3 only)
gmAutomatedAverageSourceDegreeOnly3 <- calcSourceMeanDegree( dataFrameIN = gmAutomatedDataDF, includeBothIN = FALSE )
paste( "average source degree (only 3) = ", gmAutomatedAverageSourceDegreeOnly3, sep = "" )


    

    





'average author degree (2 and 4) = 24.7872340425532'






    





'average author degree (only 2) = 24.8478260869565'






    





'average source degree (3 and 4) = 1.161'






    





'average source degree (only 3) = 1.14014014014014'

In [16]:

    

# Links:
# - manual (PDF): http://cran.r-project.org/web/packages/sna/sna.pdf
# - good notes: http://www.shizukalab.com/toolkits/sna/node-level-calculations

# Also, be advised that statnet and igraph don't really play nice together.
#    If you'll be using both, best idea is to have a workspace for each.

#==============================================================================#
# statnet
#==============================================================================#

# make sure you've loaded the statnet library (includes sna)
# install.packages( "statnet" )
#library( statnet )

#==============================================================================#
# NODE level
#==============================================================================#

# what is the standard deviation of the degrees?
gmAutomatedDegreeSd <- sd( gmAutomatedDegreeVector )
paste( "degree SD = ", gmAutomatedDegreeSd, sep = "" )

# what is the variance of the degrees?
gmAutomatedDegreeVar <- var( gmAutomatedDegreeVector )
paste( "degree variance = ", gmAutomatedDegreeVar, sep = "" )

# what is the max value among the degrees?
gmAutomatedDegreeMax <- max( gmAutomatedDegreeVector )
paste( "degree max = ", gmAutomatedDegreeMax, sep = "" )

# calculate and plot degree distributions
gmAutomatedDegreeFrequenciesTable <- table( gmAutomatedDegreeVector )
paste( "degree frequencies = ", gmAutomatedDegreeFrequenciesTable, sep = "" )
gmAutomatedDegreeFrequenciesTable

# node-level undirected betweenness
gmAutomatedBetweenness <- sna::betweenness( gmAutomatedNetworkStatnet, gmode = "graph", cmode = "undirected" )

#paste( "betweenness = ", gmAutomatedBetweenness, sep = "" )
# associate with each node as a node attribute.
#    (%v% is a shortcut for the get.vertex.attribute command)
gmAutomatedNetworkStatnet %v% "betweenness" <- gmAutomatedBetweenness

# also add degree vector to original data frame
gmAutomatedDataDF$betweenness <- gmAutomatedBetweenness

#==============================================================================#
# NETWORK level
#==============================================================================#

# graph-level degree centrality
gmAutomatedDegreeCentrality <- sna::centralization( gmAutomatedNetworkStatnet, sna::degree, mode = "graph" )
paste( "degree centrality = ", gmAutomatedDegreeCentrality, sep = "" )

# graph-level betweenness centrality
gmAutomatedBetweennessCentrality <- sna::centralization( gmAutomatedNetworkStatnet, sna::betweenness, mode = "graph", cmode = "undirected" )
paste( "betweenness centrality = ", gmAutomatedBetweennessCentrality, sep = "" )

# graph-level connectedness
gmAutomatedConnectedness <- sna::connectedness( gmAutomatedNetworkStatnet )
paste( "connectedness = ", gmAutomatedConnectedness, sep = "" )

# graph-level transitivity
gmAutomatedTransitivity <- sna::gtrans( gmAutomatedNetworkStatnet, mode = "graph" )
paste( "transitivity = ", gmAutomatedTransitivity, sep = "" )

# graph-level density
gmAutomatedDensity <- sna::gden( gmAutomatedNetworkStatnet, mode = "graph" )
paste( "density = ", gmAutomatedDensity, sep = "" )


    

    





'degree SD = 6.42460087405331'






    





'degree variance = 41.2754963908866'






    





'degree max = 93'






    






	
'degree frequencies = 122'
	
'degree frequencies = 891'
	
'degree frequencies = 100'
	
'degree frequencies = 6'
	
'degree frequencies = 9'
	
'degree frequencies = 4'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'








    






gmAutomatedDegreeVector
  0   1   2   3   4   5   6   7   8   9  10  14  15  19  22  26  27  29  30  32 
122 891 100   6   9   4   1   2   1   2   1   1   2   1   1   1   1   2   1   2 
 34  35  39  42  43  44  46  47  49  50  71  72  93 
  1   2   1   1   1   1   2   2   1   1   1   1   1 






    





'degree centrality = 0.0782006640213782'






    





'betweenness centrality = 0.206660606881935'






    





'connectedness = 0.588270050752468'






    




Warning message in sna::gtrans(gmAutomatedNetworkStatnet, mode = "graph"):
“gtrans called with use.adjacency=TRUE, but your data looks too large for that to work well.  Overriding to edgelist method.”





    





'transitivity = 0.00893353450329548'






    





'density = 0.00169321874710632'

In [17]:

    

#==============================================================================#
# output attributes to data frame
#==============================================================================#

# if you want to just work with the traits of the nodes/vertexes, you can
#    combine the attribute vectors into a data frame.

# first, output network object to see what attributes you have
gmAutomatedNetworkStatnet

# then, combine them into a data frame.
gmAutomatedNodeAttrDF <- data.frame( id = gmAutomatedNetworkStatnet %v% "vertex.names",
                                     person_id = gmAutomatedNetworkStatnet %v% "person_id",
                                     person_type = gmAutomatedNetworkStatnet %v% "person_type",
                                     degree = gmAutomatedNetworkStatnet %v% "degree",
                                     betweenness = gmAutomatedNetworkStatnet %v% "betweenness" )


    

    






 Network attributes:
  vertices = 1167 
  directed = FALSE 
  hyper = FALSE 
  loops = FALSE 
  multiple = FALSE 
  bipartite = FALSE 
  total edges= 1152 
    missing edges= 0 
    non-missing edges= 1152 

 Vertex attribute names: 
    betweenness degree person_id person_type vertex.names 

 Edge attribute names not shown 

In [18]:

    

# initialize variables
gmHumanDataFolder <- paste( data_directory, "/network/grp_month", sep = "" )
gmHumanDataFile <- "sourcenet_data-20171115-043102-grp_month-human.tab"
gmHumanDataPath <- paste( gmHumanDataFolder, "/", gmHumanDataFile, sep = "" )


    

In [19]:

    

gmHumanDataPath


    

    





'/home/jonathanmorgan/work/django/research/work/phd_work/methods/data/network/grp_month/sourcenet_data-20171115-043102-grp_month-human.tab'

In [20]:

    

# tab-delimited:
gmHumanDataDF <- read.delim( gmHumanDataPath, header = TRUE, row.names = 1, check.names = FALSE )


    

In [21]:

    

# get count of rows...
gmHumanRowCount <- nrow( gmHumanDataDF )
paste( "grp_month automated row count = ", gmHumanRowCount, sep = "" )

# ...and columns
gmHumanColumnCount <- ncol( gmHumanDataDF )
paste( "grp_month automated column count = ", gmHumanColumnCount, sep = "" )


    

    





'grp_month automated row count = 1167'






    





'grp_month automated column count = 1169'

In [22]:

    

# the below syntax returns only as many columns as there are rows, so
#     omitting any trait columns that lie in columns on the right side
#     of the file.
gmHumanNetworkDF <- gmHumanDataDF[ , 1 : gmHumanRowCount ]
#str( gmHumanNetworkDF )


    

In [23]:

    

# convert to a matrix
gmHumanNetworkMatrix <- as.matrix( gmHumanNetworkDF )
# str( gmHumanNetworkMatrix )


    

In [24]:

    

# make sure you've loaded the statnet library
# install.packages( "statnet" )
library( statnet )


    

In [25]:

    

# If you have a data frame of attributes (each attribute is a column, with
#     attribute name the column name), you can associate those attributes
#     when you create the network.
# attribute help: http://www.inside-r.org/packages/cran/network/docs/loading.attributes

# load attributes from a file:
#tab_attribute_test1 <- read.delim( "tab-test1-attribute_data.txt", header = TRUE, row.names = 1, check.names = FALSE )

# or create DataFrame by just grabbing the attribute columns
#gmHumanNetworkAttributeDF <- gmHumanDataDF[ , 1169:1170 ]
gmHumanNetworkAttributeDF <- gmHumanDataDF[ , 1168:1169 ]

# convert matrix to statnet network object instance.
gmHumanNetworkStatnet <- network( gmHumanNetworkMatrix, matrix.type = "adjacency", directed = FALSE, vertex.attr = gmHumanNetworkAttributeDF )

# look at information now.
gmHumanNetworkStatnet

# Network attributes:
#  vertices = 314
#  directed = FALSE
#  hyper = FALSE
#  loops = FALSE
#  multiple = FALSE
#  bipartite = FALSE
#  total edges= 309
#    missing edges= 0
#    non-missing edges= 309
#
# Vertex attribute names:
#    person_type vertex.names
#
# No edge attributes


    

    






 Network attributes:
  vertices = 1167 
  directed = FALSE 
  hyper = FALSE 
  loops = FALSE 
  multiple = FALSE 
  bipartite = FALSE 
  total edges= 1201 
    missing edges= 0 
    non-missing edges= 1201 

 Vertex attribute names: 
    person_id person_type vertex.names 

 Edge attribute names not shown 

In [26]:

    

# human - include ties Greater than or equal to 0 (GE0)
gmHumanMeanTieWeightGE0Vector <- apply( gmHumanNetworkMatrix, 1, calculateListMean )
gmHumanDataDF$meanTieWeightGE0 <- gmHumanMeanTieWeightGE0Vector

# human - include ties Greater than or equal to 1 (GE1)
gmHumanMeanTieWeightGE1Vector <- apply( gmHumanNetworkMatrix, 1, calculateListMean, minValueToIncludeIN = 1 )
gmHumanDataDF$meanTieWeightGE1 <- gmHumanMeanTieWeightGE1Vector

# human - Max tie weight?
gmHumanMaxTieWeightVector <- apply( gmHumanNetworkMatrix, 1, calculateListMax )
gmHumanDataDF$maxTieWeight <- gmHumanMaxTieWeightVector


    

In [27]:

    

# assuming that our statnet network object is in reference test1_statnet.

# Use the degree function in the sna package to create vector of degree values
#    for each node.  Make sure to pass the gmode parameter to tell it that the
#    graph is not directed (gmode = "graph", instead of "digraph").
# Doc: http://www.inside-r.org/packages/cran/sna/docs/degree
#degree_vector <- degree( test1_statnet, gmode = "graph" )

# If you have other libraries loaded that also implement a degree function, you
#    can also call this with package name:
gmHumanDegreeVector <- sna::degree( gmHumanNetworkStatnet, gmode = "graph" )

# output the vector
gmHumanDegreeVector

# want more info on the degree function?  You can get to it eventually through
#    the following:
#help( package = "sna" )
#??sna::degree

# what is the average (mean) degree?
gmHumanAvgDegree <- mean( gmHumanDegreeVector )
paste( "average degree = ", gmHumanAvgDegree, sep = "" )

# subset vector to get only those that are above mean
gmHumanAboveMeanVector <- gmHumanDegreeVector[ gmHumanDegreeVector > gmHumanAvgDegree ]

# Take the degree and associate it with each node as a node attribute.
#    (%v% is a shortcut for the get.vertex.attribute command)
gmHumanNetworkStatnet %v% "degree" <- gmHumanDegreeVector

# also add degree vector to original data frame
gmHumanDataDF$degree <- gmHumanDegreeVector


    

    






	
28
	
1
	
36
	
1
	
34
	
0
	
1
	
50
	
28
	
1
	
32
	
1
	
61
	
1
	
1
	
99
	
44
	
31
	
47
	
66
	
2
	
6
	
1
	
1
	
2
	
1
	
38
	
2
	
2
	
2
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
41
	
1
	
1
	
1
	
2
	
1
	
1
	
7
	
1
	
0
	
1
	
46
	
4
	
1
	
19
	
3
	
1
	
2
	
2
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
0
	
1
	
2
	
3
	
1
	
1
	
32
	
1
	
1
	
3
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
7
	
1
	
1
	
1
	
9
	
2
	
1
	
1
	
1
	
1
	
1
	
2
	
7
	
1
	
0
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
37
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
19
	
1
	
1
	
1
	
1
	
1
	
1
	
33
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
4
	
1
	
1
	
31
	
45
	
1
	
2
	
1
	
1
	
1
	
44
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
2
	
1
	
1
	
3
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
4
	
4
	
4
	
4
	
4
	
1
	
1
	
1
	
1
	
1
	
4
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
19
	
1
	
1
	
1
	
1
	
2
	
2
	
2
	
3
	
2
	
2
	
4
	
1
	
0
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
3
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
2
	
2
	
3
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
4
	
1
	
1
	
2
	
1
	
1
	
2
	
4
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
76
	
22
	
50
	
3
	
1
	
1
	
1
	
13
	
9
	
3
	
1
	
2
	
3
	
1
	
1
	
2
	
1
	
2
	
2
	
1
	
0
	
1
	
0
	
0
	
0
	
0
	
1
	
1
	
0
	
1
	
0
	
0
	
1
	
0
	
2
	
0
	
1
	
1
	
1
	
0
	
0
	
1
	
1
	
0
	
0
	
1
	
0
	
1
	
1
	
0
	
10
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
3
	
2
	
14
	
2
	
1
	
0
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
2
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
7
	
1
	
1
	
0
	
1
	
1
	
1
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
3
	
2
	
4
	
2
	
1
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
4
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
4
	
0
	
1
	
1
	
1
	
1
	
0
	
1
	
5
	
1
	
1
	
1
	
1
	
1
	
1
	
3
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
2
	
2
	
2
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
4
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
2
	
2
	
2
	
2
	
2
	
1
	
1
	
1
	
2
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
3
	
2
	
1
	
1
	
1
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
0
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
0
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
5
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
0
	
2
	
2
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
2
	
2
	
2
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
2
	
2
	
2
	
2
	
2
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
1
	
0
	
0
	
0
	
0
	
0
	
1
	
0
	
1
	
0
	
0
	
0
	
1
	
0
	
0
	
0
	
0
	
0
	
0
	
0
	
0
	
0
	
1
	
0
	
0
	
0
	
0
	
0
	
0
	
0
	
0
	
2
	
0
	
1
	
0
	
0
	
1
	
1
	
1
	
1








    





'average degree = 2.05826906598115'

In [28]:

    

# average author degree (person types 2 and 4)
gmHumanAverageAuthorDegree2And4 <- calcAuthorMeanDegree( dataFrameIN = gmHumanDataDF, includeBothIN = TRUE )
paste( "average author degree (2 and 4) = ", gmHumanAverageAuthorDegree2And4, sep = "" )

# average author degree (person type 2 only)
gmHumanAverageAuthorDegreeOnly2 <- calcAuthorMeanDegree( dataFrameIN = gmHumanDataDF, includeBothIN = FALSE )
paste( "average author degree (only 2) = ", gmHumanAverageAuthorDegreeOnly2, sep = "" )

# average source degree (person types 3 and 4)
gmHumanAverageSourceDegree3And4 <- calcSourceMeanDegree( dataFrameIN = gmHumanDataDF, includeBothIN = TRUE )
paste( "average source degree (3 and 4) = ", gmHumanAverageSourceDegree3And4, sep = "" )

# average source degree (person type 3 only)
gmHumanAverageSourceDegreeOnly3 <- calcSourceMeanDegree( dataFrameIN = gmHumanDataDF, includeBothIN = FALSE )
paste( "average source degree (only 3) = ", gmHumanAverageSourceDegreeOnly3, sep = "" )


    

    





'average author degree (2 and 4) = 25.3958333333333'






    





'average author degree (only 2) = 25.3958333333333'






    





'average source degree (3 and 4) = 1.1564027370479'






    





'average source degree (only 3) = 1.1564027370479'

In [29]:

    

# Links:
# - manual (PDF): http://cran.r-project.org/web/packages/sna/sna.pdf
# - good notes: http://www.shizukalab.com/toolkits/sna/node-level-calculations

# Also, be advised that statnet and igraph don't really play nice together.
#    If you'll be using both, best idea is to have a workspace for each.

#==============================================================================#
# statnet
#==============================================================================#

# make sure you've loaded the statnet library (includes sna)
# install.packages( "statnet" )
#library( statnet )

#==============================================================================#
# NODE level
#==============================================================================#

# what is the standard deviation of the degrees?
gmHumanDegreeSd <- sd( gmHumanDegreeVector )
paste( "degree SD = ", gmHumanDegreeSd, sep = "" )

# what is the variance of the degrees?
gmHumanDegreeVar <- var( gmHumanDegreeVector )
paste( "degree variance = ", gmHumanDegreeVar, sep = "" )

# what is the max value among the degrees?
gmHumanDegreeMax <- max( gmHumanDegreeVector )
paste( "degree max = ", gmHumanDegreeMax, sep = "" )

# calculate and plot degree distributions
gmHumanDegreeFrequenciesTable <- table( gmHumanDegreeVector )
paste( "degree frequencies = ", gmHumanDegreeFrequenciesTable, sep = "" )
gmHumanDegreeFrequenciesTable

# node-level undirected betweenness
gmHumanBetweenness <- sna::betweenness( gmHumanNetworkStatnet, gmode = "graph", cmode = "undirected" )

#paste( "betweenness = ", gmHumanBetweenness, sep = "" )
# associate with each node as a node attribute.
#    (%v% is a shortcut for the get.vertex.attribute command)
gmHumanNetworkStatnet %v% "betweenness" <- gmHumanBetweenness

# also add degree vector to original data frame
gmHumanDataDF$betweenness <- gmHumanBetweenness

#==============================================================================#
# NETWORK level
#==============================================================================#

# graph-level degree centrality
gmHumanDegreeCentrality <- sna::centralization( gmHumanNetworkStatnet, sna::degree, mode = "graph" )
paste( "degree centrality = ", gmHumanDegreeCentrality, sep = "" )

# graph-level betweenness centrality
gmHumanBetweennessCentrality <- sna::centralization( gmHumanNetworkStatnet, sna::betweenness, mode = "graph", cmode = "undirected" )
paste( "betweenness centrality = ", gmHumanBetweennessCentrality, sep = "" )

# graph-level connectedness
gmHumanConnectedness <- sna::connectedness( gmHumanNetworkStatnet )
paste( "connectedness = ", gmHumanConnectedness, sep = "" )

# graph-level transitivity
gmHumanTransitivity <- sna::gtrans( gmHumanNetworkStatnet, mode = "graph" )
paste( "transitivity = ", gmHumanTransitivity, sep = "" )

# graph-level density
gmHumanDensity <- sna::gden( gmHumanNetworkStatnet, mode = "graph" )
paste( "density = ", gmHumanDensity, sep = "" )


    

    





'degree SD = 6.65377784484138'






    





'degree variance = 44.272759608502'






    





'degree max = 99'






    






	
'degree frequencies = 97'
	
'degree frequencies = 911'
	
'degree frequencies = 91'
	
'degree frequencies = 14'
	
'degree frequencies = 15'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 4'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 3'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 2'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 2'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'
	
'degree frequencies = 1'








    






gmHumanDegreeVector
  0   1   2   3   4   5   6   7   9  10  13  14  19  22  28  31  32  33  34  36 
 97 911  91  14  15   2   1   4   2   1   1   1   3   1   2   2   2   1   1   1 
 37  38  41  44  45  46  47  50  61  66  76  99 
  1   1   1   2   1   1   1   2   1   1   1   1 






    





'degree centrality = 0.0832831513777339'






    





'betweenness centrality = 0.220493193695819'






    





'connectedness = 0.673448360502733'






    




Warning message in sna::gtrans(gmHumanNetworkStatnet, mode = "graph"):
“gtrans called with use.adjacency=TRUE, but your data looks too large for that to work well.  Overriding to edgelist method.”





    





'transitivity = 0.0131821874307658'






    





'density = 0.00176523933617594'

In [30]:

    

#==============================================================================#
# output attributes to data frame
#==============================================================================#

# if you want to just work with the traits of the nodes/vertexes, you can
#    combine the attribute vectors into a data frame.

# first, output network object to see what attributes you have
gmHumanNetworkStatnet

# then, combine them into a data frame.
gmHumanNodeAttrDF <- data.frame( id = gmHumanNetworkStatnet %v% "vertex.names",
                                 person_id = gmHumanNetworkStatnet %v% "person_id",
                                 person_type = gmHumanNetworkStatnet %v% "person_type",
                                 degree = gmHumanNetworkStatnet %v% "degree",
                                 betweenness = gmHumanNetworkStatnet %v% "betweenness" )


    

    






 Network attributes:
  vertices = 1167 
  directed = FALSE 
  hyper = FALSE 
  loops = FALSE 
  multiple = FALSE 
  bipartite = FALSE 
  total edges= 1201 
    missing edges= 0 
    non-missing edges= 1201 

 Vertex attribute names: 
    betweenness degree person_id person_type vertex.names 

 Edge attribute names not shown 

In [8]:

    

outputPrefix <- "grp_month a2b"


    

In [9]:

    

grpMontha2bOutput <- compareMatricesQAP( gmHumanNetworkMatrix, gmAutomatedNetworkMatrix, outputPrefix )


    

    




==> Start of  compareMatricesQAP  at  2019-07-25 22:22:48
----> grp_month a2b graph correlation = 0.914011398376571 ( @ 2019-07-25 22:22:49 )
----> grp_month a2b QAP correlation analysis complete at 2019-07-25 22:26:16.  Summary:






    




QAP Test Results

Estimated p-values:
	p(f(perm) >= f(d)): 0 
	p(f(perm) <= f(d)): 1 

Test Diagnostics:
	Test Value (f(d)): 0.9140114 
	Replications: 1000 
	Distribution Summary:
		Min:	 -0.00153729 
		1stQ:	 -0.0009019339 
		Med:	 -0.0002665774 
		Mean:	 -5.881582e-05 
		3rdQ:	 0.0003687791 
		Max:	 0.00926377 







    




----> grp_month a2b graph covariance = 0.0021144384905141 ( @ 2019-07-25 22:26:16 )
----> grp_month a2b QAP covariance analysis complete at 2019-07-25 22:29:38.  Summary:






    




QAP Test Results

Estimated p-values:
	p(f(perm) >= f(d)): 0 
	p(f(perm) <= f(d)): 1 

Test Diagnostics:
	Test Value (f(d)): 0.002114438 
	Replications: 1000 
	Distribution Summary:
		Min:	 -3.556308e-06 
		1stQ:	 -2.086499e-06 
		Med:	 -6.166898e-07 
		Mean:	 1.182147e-07 
		3rdQ:	 2.322928e-06 
		Max:	 2.290025e-05 







    




----> grp_month a2b graph hamming distance = 514 ( @ 2019-07-25 22:29:38 )
----> grp_month a2b QAP hamming distance analysis complete at 2019-07-25 22:32:35.  Summary:






    




QAP Test Results

Estimated p-values:
	p(f(perm) >= f(d)): 1 
	p(f(perm) <= f(d)): 0 

Test Diagnostics:
	Test Value (f(d)): 514 
	Replications: 1000 
	Distribution Summary:
		Min:	 5086 
		1stQ:	 5122 
		Med:	 5126 
		Mean:	 5125.728 
		3rdQ:	 5130 
		Max:	 5134 







    




==> End of  compareMatricesQAP  at  2019-07-25 22:32:35

In [ ]:

    

# also output plots of distributions of QAP values?
displayCompareMatricesQAPOutput( grpMontha2bOutput, outputPrefix, TRUE )


    

In [10]:

    

# help( save.image )
message( paste( "Output workspace to: ", workspace_file_name, sep = "" ) )
save.image( file = workspace_file_name )


    

    




Output workspace to: statnet-grp_month.RData