def test_grouper():
groups = list(grouper([1, 2] * 100, 2))
assert all(len(x) == 2 for x in groups)
assert all(x == (1, 2) for x in groups)
groups = list(grouper([1, 2] * 100 + [1], 2))
assert groups[-1] == (1, None)
def test_grouper():
groups = list(grouper([1,2]*100, 2))
assert all(len(x) == 2 for x in groups)
assert all(x == (1,2) for x in groups)
groups = list(grouper([1,2]*100 + [1], 2))
assert groups[-1] == (1, None)
def test_ld():
# Data from Hartl & Clark, Table 2.2 (pg 85)
haplotypes = chain([Alleles(['A','B'])] * 25,
[Alleles(['A','b'])] * 475, [Alleles(['a','B'])] * 475,
[Alleles(['a','b'])] * 9025)
pop = Population()
for chroms in grouper(haplotypes,2):
ind = pop.founder_individual()
ind.genotypes = [chroms]
known_D = 0
assert pop.ld( (0,0), (0,1), method='D') == known_D
def read_beagle_genotypefile(filename, pop, missingcode='0'):
'''
Reads BEAGLE formatted genotype files
Arguments
:param filename: Filename of BEAGLE genotype file
:param pop: the population to add these individuals to
:param missingcode: The value that indicates a missing genotype
:type missingcode: string
:rtype: void
'''
with smartopen(filename) as f:
for line in f:
rec = BeagleGenotypeRecord(line)
if rec.identifier == 'I':
inds = [Individual(pop, label) for label in rec.data[::2]]
elif rec.is_phenotype_record:
for ind, pheno_status in zip(inds, rec.data[::2]):
if rec.identifier == 'A':
pheno_status = pheno_status == '2'
else:
try:
pheno_status = float(pheno_status)
except ValueError:
pass
ind.phenotypes[rec.label] = pheno_status
else:
# We've reached the genotypes, and we're skipping out
break
f.seek(0)
gtrows = [
list(grouper(BeagleGenotypeRecord(x).data, 2)) for x in f
if x.startswith('M')
]
genotypes = zip(*gtrows)
for ind, sequentialalleles in zip(inds, genotypes):
ind.genotypes = gt_from_seq(ind.chromosomes,
sequentialalleles,
missing_code=missingcode)
def read_beagle_genotypefile(filename, pop, missingcode='0'):
'''
Reads BEAGLE formatted genotype files
Arguments
:param filename: Filename of BEAGLE genotype file
:param pop: the population to add these individuals to
:param missingcode: The value that indicates a missing genotype
:type missingcode: string
:rtype: void
'''
with smartopen(filename) as f:
for line in f:
rec = BeagleGenotypeRecord(line)
if rec.identifier == 'I':
inds = [Individual(pop, label) for label in rec.data[::2]]
elif rec.is_phenotype_record:
for ind, pheno_status in zip(inds, rec.data[::2]):
if rec.identifier == 'A':
pheno_status = pheno_status == '2'
else:
try:
pheno_status = float(pheno_status)
except ValueError:
pass
ind.phenotypes[rec.label] = pheno_status
else:
# We've reached the genotypes, and we're skipping out
break
f.seek(0)
gtrows = [list(grouper(BeagleGenotypeRecord(x).data, 2))
for x in f if x.startswith('M')]
genotypes = zip(*gtrows)
for ind, sequentialalleles in zip(inds, genotypes):
ind.genotypes = gt_from_seq(ind.chromosomes,
sequentialalleles,
missing_code=missingcode)
