def test_slice_types(self):
h = HaplotypeArray(haplotype_data, dtype='i1')
# row slice
s = h[1:]
assert isinstance(s, HaplotypeArray)
# col slice
s = h[:, 1:]
assert isinstance(s, HaplotypeArray)
# row index
s = h[0]
assert isinstance(s, np.ndarray)
assert not isinstance(s, HaplotypeArray)
# col index
s = h[:, 0]
assert isinstance(s, np.ndarray)
assert not isinstance(s, HaplotypeArray)
# item
s = h[0, 0]
assert isinstance(s, np.int8)
assert not isinstance(s, HaplotypeArray)
def test_windowed_diversity(self):
# four haplotypes, 6 pairwise comparison
h = HaplotypeArray([[0, 0, 0, 0], [0, 0, 0, 1], [0, 0, 1, 1],
[0, 1, 1, 1], [1, 1, 1, 1], [0, 0, 1, 2],
[0, 1, 1, 2], [0, 1, -1, -1], [-1, -1, -1, -1]])
ac = h.count_alleles()
# mean pairwise diversity
# expect = [0, 3/6, 4/6, 3/6, 0, 5/6, 5/6, 1, -1]
pos = SortedIndex([2, 4, 7, 14, 15, 18, 19, 25, 27])
expect = [(7 / 6) / 10, (13 / 6) / 10, 1 / 11]
actual, _, _, _ = allel.windowed_diversity(pos,
ac,
size=10,
start=1,
stop=31)
assert_array_almost_equal(expect, actual)
def test_pdist(self):
from allel.stats.distance import pdist
h = HaplotypeArray([[0, 0, 0, 0], [0, 0, 0, 1], [0, 0, 1, 1],
[0, 1, 1, 1], [1, 1, 1, 1], [0, 0, 1, 2],
[0, 1, 1, 2], [0, 1, -1, -1], [-1, -1, -1, -1]])
import scipy.spatial
d1 = scipy.spatial.distance.pdist(h.T, 'hamming')
d2 = pdist(h, 'hamming')
aeq(d1, d2)
def test_mean_pairwise_divergence(self):
# simplest case, two haplotypes in each population
h = HaplotypeArray([[0, 0, 0, 0],
[0, 0, 0, 1],
[0, 0, 1, 1],
[0, 1, 1, 1],
[1, 1, 1, 1],
[0, 0, 1, 2],
[0, 1, 1, 2],
[0, 1, -1, -1],
[-1, -1, -1, -1]])
h1 = h.take([0, 1], axis=1)
h2 = h.take([2, 3], axis=1)
ac1 = h1.count_alleles()
ac2 = h2.count_alleles()
expect = [0/4, 2/4, 4/4, 2/4, 0/4, 4/4, 3/4, -1, -1]
actual = allel.mean_pairwise_difference_between(ac1, ac2, fill=-1)
aeq(expect, actual)
def test_windowed_divergence(self):
# simplest case, two haplotypes in each population
h = HaplotypeArray([[0, 0, 0, 0], [0, 0, 0, 1], [0, 0, 1, 1],
[0, 1, 1, 1], [1, 1, 1, 1], [0, 0, 1, 2],
[0, 1, 1, 2], [0, 1, -1, -1], [-1, -1, -1, -1]])
h1 = h.take([0, 1], axis=1)
h2 = h.take([2, 3], axis=1)
ac1 = h1.count_alleles()
ac2 = h2.count_alleles()
# mean pairwise divergence
# expect = [0/4, 2/4, 4/4, 2/4, 0/4, 4/4, 3/4, -1, -1]
pos = SortedIndex([2, 4, 7, 14, 15, 18, 19, 25, 27])
expect = [(6 / 4) / 10, (9 / 4) / 10, 0 / 11]
actual, _, _, _ = allel.windowed_divergence(pos,
ac1,
ac2,
size=10,
start=1,
stop=31)
assert_array_almost_equal(expect, actual)
def test_mean_pairwise_diversity(self):
# start with simplest case, two haplotypes, one pairwise comparison
h = HaplotypeArray([[0, 0],
[1, 1],
[0, 1],
[1, 2],
[0, -1],
[-1, -1]])
ac = h.count_alleles()
expect = [0, 0, 1, 1, -1, -1]
actual = allel.mean_pairwise_difference(ac, fill=-1)
aeq(expect, actual)
# four haplotypes, 6 pairwise comparison
h = HaplotypeArray([[0, 0, 0, 0],
[0, 0, 0, 1],
[0, 0, 1, 1],
[0, 1, 1, 1],
[1, 1, 1, 1],
[0, 0, 1, 2],
[0, 1, 1, 2],
[0, 1, -1, -1],
[-1, -1, -1, -1]])
ac = h.count_alleles()
expect = [0, 3/6, 4/6, 3/6, 0, 5/6, 5/6, 1, -1]
actual = allel.mean_pairwise_difference(ac, fill=-1)
assert_array_almost_equal(expect, actual)
def test_constructor(self):
# missing data arg
with self.assertRaises(TypeError):
# noinspection PyArgumentList
HaplotypeArray()
# data has wrong dtype
data = 'foo bar'
with self.assertRaises(TypeError):
HaplotypeArray(data)
# data has wrong dtype
data = [4., 5., 3.7]
with self.assertRaises(TypeError):
HaplotypeArray(data)
# data has wrong dimensions
data = [1, 2, 3]
with self.assertRaises(TypeError):
HaplotypeArray(data)
# data has wrong dimensions
data = diploid_genotype_data # use GenotypeArray instead
with self.assertRaises(TypeError):
HaplotypeArray(data)
# haploid data (typed)
h = HaplotypeArray(haplotype_data, dtype='i1')
aeq(haplotype_data, h)
assert np.int8 == h.dtype
def test_masked_windowed_divergence(self):
h = HaplotypeArray([[0, 0, 0, 0],
[0, 0, 0, 1],
[0, 0, 1, 1],
[0, 1, 1, 1],
[1, 1, 1, 1],
[0, 0, 1, 2],
[0, 1, 1, 2],
[0, 1, -1, -1],
[-1, -1, -1, -1]])
h1 = h.take([0, 1], axis=1)
h2 = h.take([2, 3], axis=1)
ac1 = h1.count_alleles()
ac2 = h2.count_alleles()
pos = SortedIndex([2, 4, 7, 14, 15, 18, 19, 25, 27])
mask = np.tile(np.repeat(np.array([True, False]), 5), 3)
expect, _, _, _ = allel.windowed_divergence(pos, ac1, ac2, size=5,
start=1, stop=31)
expect = expect[::2]
actual, _, _, _ = allel.windowed_divergence(pos, ac1, ac2, size=10,
start=1, stop=31,
is_accessible=mask)
assert_array_almost_equal(expect, actual)
def setup_instance(self, data, dtype=None):
return HaplotypeArray(data, dtype=dtype)