def test_Garud_h(n_variants, n_samples, n_contigs, n_cohorts, cohorts,
cohort_indexes, chunks):
ds = simulate_genotype_call_dataset(n_variant=n_variants,
n_sample=n_samples,
n_contig=n_contigs)
ds = ds.chunk(dict(zip(["variants", "samples"], chunks)))
subsets = np.array_split(ds.samples.values, n_cohorts)
sample_cohorts = np.concatenate(
[np.full_like(subset, i) for i, subset in enumerate(subsets)])
ds["sample_cohort"] = xr.DataArray(sample_cohorts, dims="samples")
cohort_names = [f"co_{i}" for i in range(n_cohorts)]
coords = {k: cohort_names for k in ["cohorts"]}
ds = ds.assign_coords(coords) # type: ignore[no-untyped-call]
ds = window(ds, size=3)
gh = Garud_H(ds, cohorts=cohorts)
h1 = gh.stat_Garud_h1.values
h12 = gh.stat_Garud_h12.values
h123 = gh.stat_Garud_h123.values
h2_h1 = gh.stat_Garud_h2_h1.values
# scikit-allel
for c in range(n_cohorts):
if cohort_indexes is not None and c not in cohort_indexes:
# cohorts that were not computed should be nan
np.testing.assert_array_equal(h1[:, c],
np.full_like(h1[:, c], np.nan))
np.testing.assert_array_equal(h12[:, c],
np.full_like(h12[:, c], np.nan))
np.testing.assert_array_equal(h123[:, c],
np.full_like(h123[:, c], np.nan))
np.testing.assert_array_equal(h2_h1[:, c],
np.full_like(h2_h1[:, c], np.nan))
else:
gt = ds.call_genotype.values[:, sample_cohorts == c, :]
ska_gt = allel.GenotypeArray(gt)
ska_ha = ska_gt.to_haplotypes()
ska_h = allel.moving_garud_h(ska_ha, size=3)
np.testing.assert_allclose(h1[:, c], ska_h[0])
np.testing.assert_allclose(h12[:, c], ska_h[1])
np.testing.assert_allclose(h123[:, c], ska_h[2])
np.testing.assert_allclose(h2_h1[:, c], ska_h[3])
def test_Garud_h__raise_on_no_windows():
ds = simulate_genotype_call_dataset(n_variant=10, n_sample=10)
with pytest.raises(ValueError,
match="Dataset must be windowed for Garud_H"):
Garud_H(ds)
def test_Garud_h__raise_on_non_diploid():
ds = simulate_genotype_call_dataset(n_variant=10, n_sample=10, n_ploidy=3)
with pytest.raises(NotImplementedError,
match="Garud H only implemented for diploid genotypes"):
Garud_H(ds)