def test_condition():
V = variants('fixture/sample.vcf')
eq_(9, len(V))
C = calldata('fixture/sample.vcf', condition=V['FILTER']['PASS'])
eq_(5, len(C))
Vf = variants('fixture/sample.vcf', condition=V['FILTER']['PASS'])
eq_(5, len(Vf))
def test_condition():
V = variants("fixture/sample.vcf")
eq_(9, len(V))
C = calldata("fixture/sample.vcf", condition=V["FILTER"]["PASS"])
eq_(5, len(C))
Vf = variants("fixture/sample.vcf", condition=V["FILTER"]["PASS"])
eq_(5, len(Vf))
def test_variable_calldata():
C = calldata("fixture/test1.vcf")
eq_((1, 0), tuple(C["test2"]["AD"][0]))
eq_((1, 0), tuple(C["test2"]["AD"][1]))
eq_((1, 0), tuple(C["test2"]["AD"][2]))
eq_(".", C["test2"]["GT"][0])
eq_("0", C["test2"]["GT"][1])
eq_("1", C["test2"]["GT"][2])
def test_variable_calldata():
C = calldata('fixture/test1.vcf')
eq_((1, 0), tuple(C['test2']['AD'][0]))
eq_((1, 0), tuple(C['test2']['AD'][1]))
eq_((1, 0), tuple(C['test2']['AD'][2]))
eq_('.', C['test2']['GT'][0])
eq_('0', C['test2']['GT'][1])
eq_('1', C['test2']['GT'][2])
def test_condition():
v = variants('fixture/sample.vcf')
eq_(9, len(v))
c = calldata('fixture/sample.vcf', condition=v['FILTER']['PASS'])
eq_(5, len(c))
i = info('fixture/sample.vcf', condition=v['FILTER']['PASS'])
eq_(5, len(i))
vf = variants('fixture/sample.vcf', condition=v['FILTER']['PASS'])
eq_(5, len(vf))
def test_calldata():
a = calldata('fixture/sample.vcf')
print repr(a)
eq_('0|0', a[0]['NA00001']['GT'])
eq_(True, a[0]['NA00001']['is_called'])
eq_(True, a[0]['NA00001']['is_phased'])
eq_((0, 0), tuple(a[0]['NA00001']['genotype']))
eq_((-1, -1), tuple(a[6]['NA00003']['genotype']))
eq_((-1, -1), tuple(a[7]['NA00003']['genotype']))
eq_((10, 10), tuple(a[0]['NA00001']['HQ']))
def test_calldata():
a = calldata("fixture/sample.vcf")
print repr(a)
eq_("0|0", a[0]["NA00001"]["GT"])
eq_(True, a[0]["NA00001"]["is_called"])
eq_(True, a[0]["NA00001"]["is_phased"])
eq_((0, 0), tuple(a[0]["NA00001"]["genotype"]))
eq_((-1, -1), tuple(a[6]["NA00003"]["genotype"]))
eq_((-1, -1), tuple(a[7]["NA00003"]["genotype"]))
eq_((10, 10), tuple(a[0]["NA00001"]["HQ"]))
def test_error_handling():
# try to open a directory
vcf_fn = '.'
with assert_raises(ValueError):
vcfnp.variants(vcf_fn)
# try to open a file that doesn't exist
vcf_fn = 'doesnotexist'
with assert_raises(ValueError):
vcfnp.variants(vcf_fn)
# file is nothing like a VCF (has no header etc.)
vcf_fn = 'fixture/test48a.vcf'
with assert_raises(RuntimeError):
vcfnp.variants(vcf_fn)
# file has mode sample columns than in header row
vcf_fn = 'fixture/test48b.vcf'
with assert_raises(RuntimeError):
vcfnp.calldata(vcf_fn)
def test_caching():
vcf_fn = "fixture/sample.vcf.gz"
cache_fn = vcfnp._mk_cache_fn(vcf_fn, array_type="variants")
if os.path.exists(cache_fn):
os.remove(cache_fn)
A = variants(vcf_fn, cache=True, verbose=True)
A2 = np.load(cache_fn)
assert np.all(A == A2)
cache_fn = vcfnp._mk_cache_fn(vcf_fn, array_type="calldata")
if os.path.exists(cache_fn):
os.remove(cache_fn)
A = calldata(vcf_fn, cache=True, verbose=True)
A2 = np.load(cache_fn)
assert np.all(A == A2)
cache_fn = vcfnp._mk_cache_fn(vcf_fn, array_type="calldata_2d")
if os.path.exists(cache_fn):
os.remove(cache_fn)
A = calldata_2d(vcf_fn, cache=True, verbose=True)
A2 = np.load(cache_fn)
assert np.all(A == A2)
def test_calldata_region_empty():
a = calldata("fixture/sample.vcf.gz", region="18")
eq_(0, len(a))
a = calldata("fixture/sample.vcf.gz", region="19:113-200")
eq_(0, len(a))
def profile():
v = vcfnp.variants(sys.argv[1], count=int(sys.argv[2]))
c = vcfnp.calldata(sys.argv[1], condition=v['FILTER']['PASS'])
def test_missing_calldata():
C = calldata('fixture/test1.vcf')
eq_('.', C['test3']['GT'][2])
eq_((-1, -1), tuple(C['test3']['genotype'][2]))
eq_('./.', C['test4']['GT'][2])
eq_((-1, -1), tuple(C['test4']['genotype'][2]))
def test_duplicate_field_definitions():
V = variants("fixture/test10.vcf")
# should not raise, but print useful message to stderr
C = calldata("fixture/test10.vcf")
def test_missing_format_definition():
# FORMAT field DP not declared in VCF header
C = calldata("fixture/test14.vcf", fields=["DP"], vcf_types={"DP": "Integer"})
eq_(1, C[2]["NA00001"]["DP"])
def test_missing_calldata():
C = calldata("fixture/test1.vcf")
eq_(".", C["test3"]["GT"][2])
eq_((-1, -1), tuple(C["test3"]["genotype"][2]))
eq_("./.", C["test4"]["GT"][2])
eq_((-1, -1), tuple(C["test4"]["genotype"][2]))
def test_missing_format_definition():
# FORMAT field DP not declared in VCF header
C = calldata('fixture/test14.vcf', fields=['DP'], vcf_types={'DP':'Integer'})
eq_(1, C[2]['NA00001']['DP'])
def test_calldata_region():
a = calldata('fixture/sample.vcf.gz', region='20')
eq_(6, len(a))
def test_calldata_region_empty():
a = calldata('fixture/sample.vcf.gz', region='18')
eq_(0, len(a))
a = calldata('fixture/sample.vcf.gz', region='19:113-200')
eq_(0, len(a))
def test_calldata_region():
a = calldata("fixture/sample.vcf.gz", region="20")
eq_(6, len(a))