words = line.split()
chr = str(words[0].split('_')[1])
pos = words[1]
# split chromosomes into separate files
if chr != chrPrev:
fileoutput.close()
fileoutput = open(chr+'_'+args.output, 'w')
chrPrev = chr
siteNumber = 1
# select samples
genotypes = calls.selectSamples(sampCol, words)
# count Ns
valueN = calls.countPerPosition(genotypes, 'N')
if valueN <= args.missing:
genotypesMerged = ''.join(str(e) for e in genotypes)
genotypesMergedP = genotypesMerged.replace('N', '?')
else:
continue
# count the number of called sites
if not calls.is_polymorphic(genotypes):
siteNumber += 1
else:
fileoutput.write("%s\t%s\t%s\t%s\n" % (chr, pos, siteNumber, genotypesMergedP))
siteNumber = 1
# track progress
HeterWindow = round(meanWindow(Hwindow, Twindow), 4)
except Exception:
HeterWindow = "NA"
calls.processWindow(Chr, posS, posE, HeterWindow, outputFile)
windPosEnd = windPosEnd + windSize
Hwindow = []
Twindow = []
posS = pos
while pos > windPosEnd: # if the gap in positions is larger than window size
windPosEnd = windPosEnd + windSize
ChrPrevious = Chr
posE = pos
# count hetero
Nmising = calls.countPerPosition(sample_charaters, 'N')
if Nmising < allowedN: # skip if too many Ns
nHerer = calls.countHeteroPerPosition(sample_charaters)
nTotal = float(nSample - Nmising)
Hwindow.append(float(nHerer))
Twindow.append(float(nTotal))
# track progress
counter += 1
if counter % 1000000 == 0:
print str(counter), "lines processed"
# process the last window
try:
HeterWindow = round(meanWindow(Hwindow, Twindow), 4)
except Exception:
words = line.split()
chr = str(words[0].split('_')[1])
pos = words[1]
# split chromosomes into separate files
if chr != chrPrev:
fileoutput.close()
fileoutput = open(chr + '_' + args.output, 'w')
chrPrev = chr
siteNumber = 1
# select samples
genotypes = calls.selectSamples(sampCol, words)
# count Ns
valueN = calls.countPerPosition(genotypes, 'N')
if valueN <= args.missing:
genotypesMerged = ''.join(str(e) for e in genotypes)
genotypesMergedP = genotypesMerged.replace('N', '?')
else:
continue
# count the number of called sites
if not calls.is_polymorphic(genotypes):
siteNumber += 1
else:
fileoutput.write("%s\t%s\t%s\t%s\n" %
(chr, pos, siteNumber, genotypesMergedP))
siteNumber = 1
for line in datafile:
# track progress
counter += 1
if counter % 1000000 == 0:
print str(counter), "lines processed"
words = line.split()
chr_pos = words[0:2]
ch = int(words[0].split('_')[1])
pos = int(words[1])
# select samples
alleles = calls.selectSamples(sampCol, words)
# count Ns
valueN = calls.countPerPosition(alleles, 'N')
if valueN <= args.missing:
Allalleles = [i for i in alleles if i != 'N']
else:
continue
# find overlap with the ancestor
while ch > ref_ch or (ch == ref_ch and pos > ref_pos):
words2 = ref.readline().split()
if words2 == []:
ancest = 'N'
break
else:
ref_chr_pos = words2[0:2]
ref_ch = int(ref_chr_pos[0].split('_')[1])
sampColnames = calls.selectSamples(sampCol, header_words)
sampNs = [0 for i in sampColnames]
print('Counting Ns ...')
Ns = []
for line in datafile:
words = line.split()
chr_pos = words[0:2]
# select samples
sample_charaters = calls.selectSamples(sampCol, words)
# count Ns per position
contNsOnly = calls.countPerPosition(sample_charaters, 'N')
Ns.append(contNsOnly)
# count Ns per sample
calls.countPerSample(sample_charaters, sampNs, 'N')
# track progress
counter += 1
if counter % 1000000 == 0:
print str(counter), "lines processed"
datafile.close()
# write the counts to a fine
outputTXTsite = open(args.output + "_Ns_per_site.csv", 'w')
outputTXTsample = open(args.output + "_Ns_per_sample.csv", 'w')
for line in datafile:
words = line.split()
ch = int(words[0].split('_')[1])
pos = int(words[1])
# track progress
counter += 1
if counter % 1000000 == 0:
print str(counter), "lines processed"
# select samples
genotypesN = calls.selectSamples(sampCol, words)
# skip sites with missing data
numN = calls.countPerPosition(genotypesN, 'N')
if numN <= AlowedN:
genotypes = [i for i in genotypesN if i != 'N']
nGenotypes = len(genotypes)
else:
continue # skip lines with too many Ns
# count alleles
numAl = collections.Counter(genotypes)
numAlM = numAl.most_common()
while ch > ref_ch or (ch == ref_ch and pos > ref_pos):
words2 = ref.readline().split()
if words2 == []:
ancest = 'N'
break