fitComunities.R

library(dplyr)     

#options(stringsAsFactors = F)                                                                                                                                                 
#z1=read.delim(file='/Users/jalbrzikowskime/gordon_ci.txt',header=F)                                                                                                          
#z2=read.delim(file='/Users/jalbrzikowskime/infomap_luna_denoise_t9.txt',header=F) 

# fake data
d<-data.frame(                                                                                                                                                                
 id=c(1,2,3,4,5,6,7,8,9,10),                                                                                                                                                  
 z1=c(1,1,1,3,3,3,3,2,2,1),                                                                                                                                                   
 z2=c(5,5,5,5,4,4,4,8,8,4)                                                                                                                                                    
)                                                                                                                                                                             

# function to find the index of a max value (and pick the first if there is mroe than one)
firstbestmatch <- function(x) which.max(x) %>% first()
# count overlap between z2 and z1
matchtable=table(d$z2,d$z1)
# get best fit based on highest overlap (count)
bestfit<-apply(FUN=firstbestmatch,MARGIN=1,matchtable)