Skip to content

Make chunks have the same number of dimensions as shape #269

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

Merged
merged 1 commit into from
Jul 8, 2024
Merged

Make chunks have the same number of dimensions as shape #269

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
13 changes: 11 additions & 2 deletions bio2zarr/vcf2zarr/vcz.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,7 @@ def from_field(
# TODO make an option to add in the empty extra dimension
if vcf_field.summary.max_number > 1:
shape.append(vcf_field.summary.max_number)
chunks.append(vcf_field.summary.max_number)
# TODO we should really be checking this to see if the named dimensions
# are actually correct.
if vcf_field.vcf_number == "R":
Expand Down Expand Up @@ -251,7 +252,12 @@ def spec_from_field(field, array_name=None):
)

def fixed_field_spec(
name, dtype, vcf_field=None, shape=(m,), dimensions=("variants",)
name,
dtype,
vcf_field=None,
shape=(m,),
dimensions=("variants",),
chunks=None,
):
return ZarrArraySpec.new(
vcf_field=vcf_field,
Expand All @@ -260,7 +266,7 @@ def fixed_field_spec(
shape=shape,
description="",
dimensions=dimensions,
chunks=[variants_chunk_size],
chunks=chunks or [variants_chunk_size],
)

alt_field = icf.fields["ALT"]
Expand All @@ -276,12 +282,14 @@ def fixed_field_spec(
dtype="bool",
shape=(m, icf.metadata.num_filters),
dimensions=["variants", "filters"],
chunks=(variants_chunk_size, icf.metadata.num_filters),
),
fixed_field_spec(
name="variant_allele",
dtype="O",
shape=(m, max_alleles),
dimensions=["variants", "alleles"],
chunks=(variants_chunk_size, max_alleles),
),
fixed_field_spec(
name="variant_id",
Expand Down Expand Up @@ -329,6 +337,7 @@ def fixed_field_spec(
)
)
shape += [ploidy]
chunks += [ploidy]
dimensions += ["ploidy"]
array_specs.append(
ZarrArraySpec.new(
Expand Down
6 changes: 3 additions & 3 deletions tests/test_vcz.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -313,7 +313,7 @@ def test_call_genotype(self, schema):
"name": "call_genotype",
"dtype": "i1",
"shape": (9, 3, 2),
"chunks": (10000, 1000),
"chunks": (10000, 1000, 2),
"dimensions": ("variants", "samples", "ploidy"),
"description": "",
"vcf_field": None,
Expand All @@ -332,7 +332,7 @@ def test_call_genotype_mask(self, schema):
"name": "call_genotype_mask",
"dtype": "bool",
"shape": (9, 3, 2),
"chunks": (10000, 1000),
"chunks": (10000, 1000, 2),
"dimensions": ("variants", "samples", "ploidy"),
"description": "",
"vcf_field": None,
Expand All @@ -351,7 +351,7 @@ def test_call_genotype_phased(self, schema):
"name": "call_genotype_mask",
"dtype": "bool",
"shape": (9, 3, 2),
"chunks": (10000, 1000),
"chunks": (10000, 1000, 2),
"dimensions": ("variants", "samples", "ploidy"),
"description": "",
"vcf_field": None,
Expand Down
Loading