library(adegenet)
library(hierfstat)

rm(list = ls())

## get number of individuals (n_ind) and number of loci (n_loc)
##
## skip the first line, since STRUCTURE wants only allele labels and other
## lines include inidividual number and pop
##
wang <- read.table("wang-et-al.stru",
                   header = FALSE,
                   skip = 1)
## the STRUCTURE file has 2 lines per individuals, so the number of
## individuals is the number of rows divided by 2
##
n_ind = nrow(wang)/2
## the STRUCTURE file has 1 column with the individual index and a 2nd
## column with the group number, so the number of loci is the number of
## columns minus 2
##
n_loc = ncol(wang) - 2

## get group, area, and continent labels
##
wang_lbl <- read.table("wang-et-al.pop",
                       header = TRUE)

## read data and labels into genind object
##
wang_fst <- read.structure(file = "wang-et-al.stru",
                           n.ind = n_ind,
                           n.loc = n_loc,
                           onerowperind = FALSE,
                           col.lab = 1,
                           col.pop = 2,
                           col.others = NULL,
                           row.marknames = 1,
                           NA.char = "-9",
                           pop = NULL,
                           sep = NULL,
                           ask = FALSE,
                           quiet = TRUE)
other(wang_fst)$continent <- wang_lbl$continent
other(wang_fst)$area <- wang_lbl$area
other(wang_fst)$group <- wang_lbl$group

## wang_levels contains information for each individual indicating
## which continent, area, and group they belong to
##
wang_levels <- data.frame(other(wang_fst))
## wang_loci contains information about the genotype of each individual
## the strange 2nd line is necessary to make sure the alleles are
## treated as number rather than as characters
##
wang_loci <- genind2df(wang_fst)[, -1]
wang_loci <- data.frame(lapply(wang_loci, as.numeric))