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_close(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.stats.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.stats.mean_pairwise_difference(ac, fill=-1)
assert_array_close(expect, actual)
def test_rogers_huff_r(self):
gn = [[0, 1, 2],
[0, 1, 2]]
expect = 1.
actual = allel.stats.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 1, 2],
[2, 1, 0]]
expect = -1.
actual = allel.stats.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 0, 0],
[1, 1, 1]]
actual = allel.stats.rogers_huff_r(gn)
assert np.isnan(actual)
gn = [[0, 1, 0, 1],
[0, 1, 1, 0]]
expect = 0
actual = allel.stats.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 1, 2, -1],
[0, 1, 2, 2]]
expect = 1.
actual = allel.stats.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 1, 2, 2],
[0, 1, 2, -1]]
expect = 1.
actual = allel.stats.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 1, 2],
[0, 1, -1]]
expect = 1.
actual = allel.stats.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 2],
[2, 0],
[0, 1]]
expect = [-1, 1, -1]
actual = allel.stats.rogers_huff_r(gn)
assert_array_close(expect, actual)
gn = [[0, 2, 0],
[0, 2, 0],
[2, 0, 2],
[0, 2, -1]]
expect = [1, -1, 1, -1, 1, -1]
actual = allel.stats.rogers_huff_r(gn)
assert_array_close(expect, actual)
def test_rogers_huff_r(self):
gn = [[0, 1, 2],
[0, 1, 2]]
expect = 1.
actual = allel.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 1, 2],
[2, 1, 0]]
expect = -1.
actual = allel.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 0, 0],
[1, 1, 1]]
actual = allel.rogers_huff_r(gn)
assert np.isnan(actual)
gn = [[0, 1, 0, 1],
[0, 1, 1, 0]]
expect = 0
actual = allel.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 1, 2, -1],
[0, 1, 2, 2]]
expect = 1.
actual = allel.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 1, 2, 2],
[0, 1, 2, -1]]
expect = 1.
actual = allel.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 1, 2],
[0, 1, -1]]
expect = 1.
actual = allel.rogers_huff_r(gn)
eq(expect, actual)
gn = [[0, 2],
[2, 0],
[0, 1]]
expect = [-1, 1, -1]
actual = allel.rogers_huff_r(gn)
assert_array_close(expect, actual)
gn = [[0, 2, 0],
[0, 2, 0],
[2, 0, 2],
[0, 2, -1]]
expect = [1, -1, 1, -1, 1, -1]
actual = allel.rogers_huff_r(gn)
assert_array_close(expect, actual)
def test_heterozygosity_expected(self):
def refimpl(af, ploidy, fill=0):
"""Limited reference implementation for testing purposes."""
# check allele frequencies sum to 1
af_sum = np.sum(af, axis=1)
# assume three alleles
p = af[:, 0]
q = af[:, 1]
r = af[:, 2]
out = 1 - p**ploidy - q**ploidy - r**ploidy
with ignore_invalid():
out[(af_sum < 1) | np.isnan(af_sum)] = fill
return out
# diploid
g = GenotypeArray([[[0, 0], [0, 0]],
[[1, 1], [1, 1]],
[[1, 1], [2, 2]],
[[0, 0], [0, 1]],
[[0, 0], [0, 2]],
[[1, 1], [1, 2]],
[[0, 1], [0, 1]],
[[0, 1], [1, 2]],
[[0, 0], [-1, -1]],
[[0, 1], [-1, -1]],
[[-1, -1], [-1, -1]]], dtype='i1')
expect1 = [0, 0, 0.5, .375, .375, .375, .5, .625, 0, .5, -1]
af = g.count_alleles().to_frequencies()
expect2 = refimpl(af, ploidy=g.ploidy, fill=-1)
actual = allel.stats.heterozygosity_expected(af, ploidy=g.ploidy,
fill=-1)
assert_array_close(expect1, actual)
assert_array_close(expect2, actual)
expect3 = [0, 0, 0.5, .375, .375, .375, .5, .625, 0, .5, 0]
actual = allel.stats.heterozygosity_expected(af, ploidy=g.ploidy,
fill=0)
assert_array_close(expect3, actual)
# polyploid
g = GenotypeArray([[[0, 0, 0], [0, 0, 0]],
[[1, 1, 1], [1, 1, 1]],
[[1, 1, 1], [2, 2, 2]],
[[0, 0, 0], [0, 0, 1]],
[[0, 0, 0], [0, 0, 2]],
[[1, 1, 1], [0, 1, 2]],
[[0, 0, 1], [0, 1, 1]],
[[0, 1, 1], [0, 1, 2]],
[[0, 0, 0], [-1, -1, -1]],
[[0, 0, 1], [-1, -1, -1]],
[[-1, -1, -1], [-1, -1, -1]]], dtype='i1')
af = g.count_alleles().to_frequencies()
expect = refimpl(af, ploidy=g.ploidy, fill=-1)
actual = allel.stats.heterozygosity_expected(af, ploidy=g.ploidy,
fill=-1)
assert_array_close(expect, actual)
def test_heterozygosity_expected(self):
def refimpl(f, ploidy, fill=0):
"""Limited reference implementation for testing purposes."""
# check allele frequencies sum to 1
af_sum = np.sum(f, axis=1)
# assume three alleles
p = f[:, 0]
q = f[:, 1]
r = f[:, 2]
out = 1 - p**ploidy - q**ploidy - r**ploidy
with ignore_invalid():
out[(af_sum < 1) | np.isnan(af_sum)] = fill
return out
# diploid
g = GenotypeArray([[[0, 0], [0, 0]],
[[1, 1], [1, 1]],
[[1, 1], [2, 2]],
[[0, 0], [0, 1]],
[[0, 0], [0, 2]],
[[1, 1], [1, 2]],
[[0, 1], [0, 1]],
[[0, 1], [1, 2]],
[[0, 0], [-1, -1]],
[[0, 1], [-1, -1]],
[[-1, -1], [-1, -1]]], dtype='i1')
expect1 = [0, 0, 0.5, .375, .375, .375, .5, .625, 0, .5, -1]
af = g.count_alleles().to_frequencies()
expect2 = refimpl(af, ploidy=g.ploidy, fill=-1)
actual = allel.heterozygosity_expected(af, ploidy=g.ploidy, fill=-1)
assert_array_close(expect1, actual)
assert_array_close(expect2, actual)
expect3 = [0, 0, 0.5, .375, .375, .375, .5, .625, 0, .5, 0]
actual = allel.heterozygosity_expected(af, ploidy=g.ploidy, fill=0)
assert_array_close(expect3, actual)
# polyploid
g = GenotypeArray([[[0, 0, 0], [0, 0, 0]],
[[1, 1, 1], [1, 1, 1]],
[[1, 1, 1], [2, 2, 2]],
[[0, 0, 0], [0, 0, 1]],
[[0, 0, 0], [0, 0, 2]],
[[1, 1, 1], [0, 1, 2]],
[[0, 0, 1], [0, 1, 1]],
[[0, 1, 1], [0, 1, 2]],
[[0, 0, 0], [-1, -1, -1]],
[[0, 0, 1], [-1, -1, -1]],
[[-1, -1, -1], [-1, -1, -1]]], dtype='i1')
af = g.count_alleles().to_frequencies()
expect = refimpl(af, ploidy=g.ploidy, fill=-1)
actual = allel.heterozygosity_expected(af, ploidy=g.ploidy, fill=-1)
assert_array_close(expect, actual)
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_close(expect, actual)
def test_inbreeding_coefficient(self):
# diploid
g = GenotypeArray([[[0, 0], [0, 0]],
[[1, 1], [1, 1]],
[[1, 1], [2, 2]],
[[0, 0], [0, 1]],
[[0, 0], [0, 2]],
[[1, 1], [1, 2]],
[[0, 1], [0, 1]],
[[0, 1], [1, 2]],
[[0, 0], [-1, -1]],
[[0, 1], [-1, -1]],
[[-1, -1], [-1, -1]]], dtype='i1')
# ho = np.array([0, 0, 0, .5, .5, .5, 1, 1, 0, 1, -1])
# he = np.array([0, 0, 0.5, .375, .375, .375, .5, .625, 0, .5, -1])
# expect = 1 - (ho/he)
expect = [-1, -1, 1-0, 1-(.5/.375), 1-(.5/.375), 1-(.5/.375),
1-(1/.5), 1-(1/.625), -1, 1-(1/.5), -1]
actual = allel.stats.inbreeding_coefficient(g, fill=-1)
assert_array_close(expect, actual)
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.stats.windowed_diversity(pos, ac, size=10,
start=1,
stop=31)
assert_array_close(expect, actual)
def test_inbreeding_coefficient(self):
# diploid
g = GenotypeArray([[[0, 0], [0, 0]],
[[1, 1], [1, 1]],
[[1, 1], [2, 2]],
[[0, 0], [0, 1]],
[[0, 0], [0, 2]],
[[1, 1], [1, 2]],
[[0, 1], [0, 1]],
[[0, 1], [1, 2]],
[[0, 0], [-1, -1]],
[[0, 1], [-1, -1]],
[[-1, -1], [-1, -1]]], dtype='i1')
# ho = np.array([0, 0, 0, .5, .5, .5, 1, 1, 0, 1, -1])
# he = np.array([0, 0, 0.5, .375, .375, .375, .5, .625, 0, .5, -1])
# expect = 1 - (ho/he)
expect = [-1, -1, 1-0, 1-(.5/.375), 1-(.5/.375), 1-(.5/.375),
1-(1/.5), 1-(1/.625), -1, 1-(1/.5), -1]
actual = allel.inbreeding_coefficient(g, fill=-1)
assert_array_close(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.stats.windowed_divergence(
pos, ac1, ac2, size=10, start=1, stop=31
)
assert_array_close(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_close(expect, actual)
