def test_constructor(self):
# missing data arg
with pytest.raises(TypeError):
# noinspection PyArgumentList
SortedIndex()
# data has wrong dtype
data = 'foo bar'
with pytest.raises(TypeError):
SortedIndex(data)
# data has wrong dimensions
data = [[1, 2], [3, 4]]
with pytest.raises(TypeError):
SortedIndex(data)
# values are not sorted
data = [2, 1, 3, 5]
with pytest.raises(ValueError):
SortedIndex(data)
# values are not sorted
data = [4., 5., 3.7]
with pytest.raises(ValueError):
SortedIndex(data)
# valid data (unique)
data = [1, 4, 5, 7, 12]
idx = SortedIndex(data)
aeq(data, idx)
assert np.int == idx.dtype
assert 1 == idx.ndim
assert 5 == len(idx)
assert idx.is_unique
# valid data (non-unique)
data = [1, 4, 5, 5, 7, 12]
idx = SortedIndex(data)
aeq(data, idx)
assert np.int == idx.dtype
assert 1 == idx.ndim
assert 6 == len(idx)
assert not idx.is_unique
# valid data (typed)
data = [1, 4, 5, 5, 7, 12]
idx = SortedIndex(data, dtype='u4')
aeq(data, idx)
assert np.uint32 == idx.dtype
# valid data (non-numeric)
data = np.array(['1', '12', '4', '5', '5', '7'], dtype=object)
idx = SortedIndex(data)
aeq(data, idx)
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 test_masked_windowed_diversity(self):
# four haplotypes, 6 pairwise comparison
h = allel.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])
mask = np.tile(np.repeat(np.array([True, False]), 5), 3)
# expected is every other window with size 5
expect, _, _, _ = allel.windowed_diversity(pos,
ac,
size=5,
start=1,
stop=31)
# only getting every other element
expect = expect[::2]
# actual is window of size 10 with the last half masked out
actual, _, _, _ = allel.windowed_diversity(pos,
ac,
size=10,
start=1,
stop=31,
is_accessible=mask)
assert_array_almost_equal(expect, actual)
def test_slice(self):
data = [1, 4, 5, 5, 7, 12]
idx = SortedIndex(data, dtype='u4')
# row slice
s = idx[1:]
assert isinstance(s, SortedIndex)
# index
s = idx[0]
assert isinstance(s, np.uint32)
assert not isinstance(s, SortedIndex)
assert data[0] == s
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_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 setup_instance(self, data):
return SortedIndex(data)
