Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Check duplicate positions #889

Merged
merged 1 commit into from
May 15, 2024
Merged

Check duplicate positions #889

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions tests/test_sgkit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -600,6 +600,22 @@ def test_ploidy1_unphased(self, tmp_path):
sgkit.save_dataset(ds, path)
tsinfer.SgkitSampleData(path)

def test_duplicate_positions(self, tmp_path):
path = tmp_path / "data.zarr"
ds = sgkit.simulate_genotype_call_dataset(n_variant=3, n_sample=3, phased=True)
ds["variant_position"][2] = ds["variant_position"][1]
sgkit.save_dataset(ds, path)
with pytest.raises(ValueError, match="duplicate or out-of-order values"):
tsinfer.SgkitSampleData(path)

def test_bad_order_positions(self, tmp_path):
path = tmp_path / "data.zarr"
ds = sgkit.simulate_genotype_call_dataset(n_variant=3, n_sample=3, phased=True)
ds["variant_position"][0] = ds["variant_position"][2] - 0.5
sgkit.save_dataset(ds, path)
with pytest.raises(ValueError, match="duplicate or out-of-order values"):
tsinfer.SgkitSampleData(path)

def test_empty_alleles_not_at_end(self, tmp_path):
path = tmp_path / "data.zarr"
ds = sgkit.simulate_genotype_call_dataset(n_variant=3, n_sample=3, n_ploidy=1)
Expand Down
6 changes: 6 additions & 0 deletions tsinfer/formats.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2309,6 +2309,12 @@ def __init__(self, path):
" sgkit dataset, indicating that all the genotypes are"
" unphased"
)
if np.any(np.diff(self.sites_position) <= 0):
raise ValueError(
"Values taken from the variant_position array are not strictly "
"increasing (i.e. have duplicate or out-of-order values). "
"These must be masked out to run tsinfer."
)

@functools.cached_property
def format_name(self):
Expand Down
Loading