ploidyDict = dict(zip(samples, ploidy))
elif args.ploidyFile is not None:
with open(args.ploidyFile, "rt") as pf:
ploidyDict = dict([[s[0], int(s[1])] for s in [l.split() for l in pf]])
elif args.inferPloidy:
ploidyDict = dict(zip(samples, [None] * len(samples)))
else:
if args.genoFormat == "haplo":
ploidyDict = dict(zip(samples, [1] * len(samples)))
else:
ploidyDict = dict(zip(samples, [2] * len(samples)))
if args.haploid:
for sample in args.haploid:
ploidyDict[sample] = 1
sampleData = genomics.SampleData(indNames=samples, ploidyDict=ploidyDict)
############################################################################################################################################
#open files
if args.genoFile != None:
genoFile = gzip.open(args.genoFile,
"rt") if args.genoFile.endswith(".gz") else open(
args.genoFile, "rt")
else:
genoFile = sys.stdin
outs = {}
if args.outFile:
#if populations and samples not specified, just get all sample names from file
if len(allInds) == 0:
with gzip.open(args.genoFile,
"r") if args.genoFile.endswith(".gz") else open(
args.genoFile, "r") as gf:
allInds = gf.readline().split()[2:]
if args.inferPloidy: ploidyDict = dict(zip(allInds, [None] * len(allInds)))
else: ploidyDict = dict(zip(allInds, [2] * len(allInds)))
if args.haploid:
for sample in args.haploid.split(","):
ploidyDict[sample] = 1
sampleData = genomics.SampleData(indNames=allInds,
popNames=popNames,
popInds=popInds,
ploidyDict=ploidyDict)
############################################################################################################################################
#open files
if args.genoFile:
genoFile = gzip.open(args.genoFile,
"r") if args.genoFile.endswith(".gz") else open(
args.genoFile, "r")
else:
genoFile = sys.stdin
if args.outFile:
outFile = gzip.open(args.outFile,
#Define the input file and create a file handle:
genoFileName = filename
genoFile = gzip.open(genoFileName, "r")
#Provide names for the populations in our dataset, and list the individuals in each.
# We have 9 silvereye populations
popNames = ["P1", "P2"]
samples = [["P1_" + str(i) for i in xrange(1, int(pop1))],
["P2_" + str(i) for i in xrange(1, int(pop2))]]
#Create a sampleData object, which stores this population information.
sampleData = genomics.SampleData(popInds=samples, popNames=popNames)
#Set the run parameters
windSize = 500000
stepSize = 500000
minSites = 1
#Now we create a windowGenerator object
windowGenerator = genomics.slidingWindows(genoFile,
windSize,
stepSize,
skipDeepcopy=True)
#Define and open the output file.
outFileName = "FST_" + str(genoFileName) + ".csv"
