igraph-help
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[igraph] Stanford SNA lab-3 : Error in exercise


From: pranav nerurkar
Subject: [igraph] Stanford SNA lab-3 : Error in exercise
Date: Wed, 24 May 2017 12:24:53 +0530

0 down vote favorite

I am following this lab exercise on community detection https://sna.stanford.edu/lab.php?l=3

since in their program community.to.membership was deprecated i modified their code. Original code is at https://sna.stanford.edu/lab.php?l=3 Line 251 onwards.

My code:
library(sna)
gadj: //adjacency matrix of a graph with 106 rows.

ideal_observed_cors = vector()

num_vertices = nrow(gadj)-1


for (i in 0:(num_vertices-1)) {
    num_comms = (num_vertices - i)
    cat('number of communities: ', num_comms, '\n')
    community <- list(cutat(wc, steps=i)) //replaced community.to.membership with cutat
    names(community)=c("membership")
    print(community)
    idealized_comm_mat <- matrix(nrow=num_vertices, ncol=num_vertices)

    for (m in 1:num_vertices) {
        for (n in 1:num_vertices) {
            if (m==n) {
                idealized_comm_mat[m,n] = 0
            } else if (community$membership[m] == community$membership[n]) {
                idealized_comm_mat[m,n] = 1
            } else {
                idealized_comm_mat[m,n] = 0
            }
        }
    }
    print(idealized_comm_mat) 

    if (num_comms > 1 & num_comms < num_vertices) {
        ideal_observed_cors <- append(ideal_observed_cors, (gcor(idealized_comm_mat, gadj)))
        print(ideal_observed_cors[length(ideal_observed_cors)])
    } else {
        ideal_observed_cors <- append(ideal_observed_cors, 0)
        print('unable to calcuate correlation; setting value to 0')
    }
    cat('\n')
}
ideal_observed_cors <- rev(ideal_observed_cors)
ideal_observed_cors 
plot(ideal_observed_cors)

But i am getting error

number of communities: 105 [1] "unable to calcuate correlation; setting value to 0"

number of communities: 104 Error in as.sociomatrix.sna(dat2) : as.sociomatrix.sna input must be an adjacency matrix/array, network, or list.

--

Warm and Kind regards,

Pranav .A.Nerurkar
Student
Dept of Computer Engineering
Veermata Jijabai Technological Institute
Matunga, Mumbai, Maharashtra.
Ph: 9619997797

reply via email to

[Prev in Thread] Current Thread [Next in Thread]