def test_calculate_hwe(self):
variations = VariationsArrays()
gts = numpy.array([])
variations['/calls/GT'] = gts
variations['/variations/alt'] = gts
result = calc_hwe_chi2_test(variations, min_num_genotypes=0,
chunk_size=None)
assert result.shape[0] == 0
variations = VariationsArrays()
gts = numpy.array([[[0, 0], [0, 1], [0, 1], [0, 0], [0, 1], [0, 0],
[0, 0], [0, 1], [1, 1], [0, 0]],
[[0, 0], [1, 0], [0, 1], [0, 0], [0, 1], [0, 0],
[0, 0], [1, 0], [1, 1], [0, 0]]])
variations['/calls/GT'] = gts
variations._create_matrix('/variations/alt', shape=(1, 1),
dtype=numpy.int16, fillvalue=0)
expected = numpy.array([[1.25825397e+01, 1.85240619e-03],
[1.25825397e+01, 1.85240619e-03]])
result = calc_hwe_chi2_test(variations, min_num_genotypes=0,
chunk_size=None)
assert numpy.allclose(result, expected)
hdf5 = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
hwe_test1 = calc_hwe_chi2_test(hdf5, chunk_size=None)
hdf5 = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
hwe_test2 = calc_hwe_chi2_test(hdf5)
assert numpy.allclose(hwe_test1, hwe_test2, equal_nan=True)
def test_calculate_hwe(self):
variations = VariationsArrays()
gts = numpy.array([])
variations['/calls/GT'] = gts
variations['/variations/alt'] = gts
result = calc_hwe_chi2_test(variations, min_num_genotypes=0,
chunk_size=None)
assert result.shape[0] == 0
variations = VariationsArrays()
gts = numpy.array([[[0, 0], [0, 1], [0, 1], [0, 0], [0, 1], [0, 0],
[0, 0], [0, 1], [1, 1], [0, 0]],
[[0, 0], [1, 0], [0, 1], [0, 0], [0, 1], [0, 0],
[0, 0], [1, 0], [1, 1], [0, 0]]])
variations['/calls/GT'] = gts
variations._create_matrix('/variations/alt', shape=(1, 1),
dtype=numpy.int16, fillvalue=0)
expected = numpy.array([[1.25825397e+01, 1.85240619e-03],
[1.25825397e+01, 1.85240619e-03]])
result = calc_hwe_chi2_test(variations, min_num_genotypes=0,
chunk_size=None)
assert numpy.allclose(result, expected)
hdf5 = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
hwe_test1 = calc_hwe_chi2_test(hdf5, chunk_size=None)
hdf5 = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
hwe_test2 = calc_hwe_chi2_test(hdf5)
assert numpy.allclose(hwe_test1, hwe_test2, equal_nan=True)
def plot_hwe(variations, max_num_alleles, data_dir, ploidy=2,
min_num_genotypes=MIN_NUM_GENOTYPES_FOR_POP_STAT,
chunk_size=SNPS_PER_CHUNK):
fpath = join(data_dir, 'hwe_chi2_distrib.png')
fhand = open(fpath, 'w')
fig = Figure(figsize=(10, 20))
canvas = FigureCanvas(fig)
num_alleles = range(2, max_num_alleles + 1)
gs = gridspec.GridSpec(len(num_alleles), 1)
for i, num_allele in enumerate(num_alleles):
df = len(list(combinations_with_replacement(range(num_allele),
ploidy))) - num_allele
hwe_test = calc_hwe_chi2_test(variations, num_allele=num_allele,
min_num_genotypes=min_num_genotypes,
chunk_size=chunk_size)
hwe_chi2 = hwe_test[:, 0]
hwe_chi2_distrib, bins = histogram(hwe_chi2, n_bins=50)
# Plot observed distribution
axes = fig.add_subplot(gs[i, 0])
title = 'Chi2 df={} statistic values distribution'.format(df)
mpl_params = {'set_xlabel': {'args': ['Chi2 statistic'], 'kwargs': {}},
'set_ylabel': {'args': ['SNP number'], 'kwargs': {}},
'set_title': {'args': [title], 'kwargs': {}}}
plot_distrib(hwe_chi2_distrib, bins, axes=axes, mpl_params=mpl_params)
# Plot expected chi2 distribution
axes = axes.twinx()
rv = chi2(df)
x = numpy.linspace(0, max(hwe_chi2), 1000)
axes.plot(x, rv.pdf(x), color='b', lw=2, label='Expected Chi2')
axes.set_ylabel('Expected Chi2 density')
canvas.print_figure(fhand)
def plot_hwe(variations,
max_num_alleles,
data_dir,
ploidy=2,
min_num_genotypes=MIN_NUM_GENOTYPES_FOR_POP_STAT,
chunk_size=SNPS_PER_CHUNK):
fpath = join(data_dir, 'hwe_chi2_distrib.png')
fhand = open(fpath, 'w')
fig = Figure(figsize=(10, 20))
canvas = FigureCanvas(fig)
num_alleles = range(2, max_num_alleles + 1)
gs = gridspec.GridSpec(len(num_alleles), 1)
for i, num_allele in enumerate(num_alleles):
df = len(list(combinations_with_replacement(range(num_allele),
ploidy))) - num_allele
hwe_test = calc_hwe_chi2_test(variations,
num_allele=num_allele,
min_num_genotypes=min_num_genotypes,
chunk_size=chunk_size)
hwe_chi2 = hwe_test[:, 0]
hwe_chi2_distrib, bins = histogram(hwe_chi2, n_bins=50)
# Plot observed distribution
axes = fig.add_subplot(gs[i, 0])
title = 'Chi2 df={} statistic values distribution'.format(df)
mpl_params = {
'set_xlabel': {
'args': ['Chi2 statistic'],
'kwargs': {}
},
'set_ylabel': {
'args': ['SNP number'],
'kwargs': {}
},
'set_title': {
'args': [title],
'kwargs': {}
}
}
plot_distrib(hwe_chi2_distrib, bins, axes=axes, mpl_params=mpl_params)
# Plot expected chi2 distribution
axes = axes.twinx()
rv = chi2(df)
x = numpy.linspace(0, max(hwe_chi2), 1000)
axes.plot(x, rv.pdf(x), color='b', lw=2, label='Expected Chi2')
axes.set_ylabel('Expected Chi2 density')
canvas.print_figure(fhand)
