Rename 'call_genotype_non_allele' to 'call_genotype_fill'

Author: tomwhite

docs/api.rst

@@ -133,7 +133,7 @@ By convention, variable names are singular in sgkit. For example, ``genotype_cou
     variables.call_genotype_complete_mask_spec
     variables.call_genotype_spec
     variables.call_genotype_mask_spec
-    variables.call_genotype_non_allele_spec
+    variables.call_genotype_fill_spec
     variables.call_genotype_phased_spec
     variables.call_genotype_probability_spec
     variables.call_genotype_probability_mask_spec

sgkit/io/vcf/vcf_reader.py

@@ -340,10 +340,10 @@ def update_dataset(self, ds: xr.Dataset) -> None:
             {"comment": variables.call_genotype_mask_spec.__doc__.strip()},
         )
         if self.mixed_ploidy is True:
-            ds["call_genotype_non_allele"] = (
+            ds["call_genotype_fill"] = (
                 [DIM_VARIANT, DIM_SAMPLE, DIM_PLOIDY],
                 self.call_genotype < -1,
-                {"comment": variables.call_genotype_non_allele_spec.__doc__.strip()},
+                {"comment": variables.call_genotype_fill_spec.__doc__.strip()},
             )
         ds["call_genotype_phased"] = (
             [DIM_VARIANT, DIM_SAMPLE],
@@ -642,7 +642,7 @@ def vcf_to_zarrs(
         The (maximum) ploidy of genotypes in the VCF file.
     mixed_ploidy
         If True, genotype calls with fewer alleles than the specified ploidy will be padded
-        with the non-allele sentinel value of -2. If false, calls with fewer alleles than
+        with the fill (non-allele) sentinel value of -2. If false, calls with fewer alleles than
         the specified ploidy will be treated as incomplete and will be padded with the
         missing-allele sentinel value of -1.
     truncate_calls
@@ -845,7 +845,7 @@ def vcf_to_zarr(
         The (maximum) ploidy of genotypes in the VCF file.
     mixed_ploidy
         If True, genotype calls with fewer alleles than the specified ploidy will be padded
-        with the non-allele sentinel value of -2. If false, calls with fewer alleles than
+        with the fill (non-allele) sentinel value of -2. If false, calls with fewer alleles than
         the specified ploidy will be treated as incomplete and will be padded with the
         missing-allele sentinel value of -1.
     truncate_calls

sgkit/stats/aggregation.py

@@ -617,7 +617,7 @@ def sample_stats(
     return conditional_merge_datasets(ds, variables.validate(new_ds), merge)
 
 
-def infer_non_alleles(
+def infer_call_genotype_fill(
     ds: Dataset,
     *,
     call_genotype: Hashable = variables.call_genotype,
@@ -626,24 +626,22 @@ def infer_non_alleles(
     variables.validate(ds, {call_genotype: variables.call_genotype_spec})
     mixed_ploidy = ds[variables.call_genotype].attrs.get("mixed_ploidy", False)
     if mixed_ploidy:
-        call_genotype_non_allele = ds[call_genotype] < -1
+        call_genotype_fill = ds[call_genotype] < -1
     else:
-        call_genotype_non_allele = xr.full_like(ds[call_genotype], False, "b1")
-    new_ds = create_dataset(
-        {variables.call_genotype_non_allele: call_genotype_non_allele}
-    )
+        call_genotype_fill = xr.full_like(ds[call_genotype], False, "b1")
+    new_ds = create_dataset({variables.call_genotype_fill: call_genotype_fill})
     return conditional_merge_datasets(ds, variables.validate(new_ds), merge)
 
 
 def infer_call_ploidy(
     ds: Dataset,
     *,
     call_genotype: Hashable = variables.call_genotype,
-    call_genotype_non_allele: Hashable = variables.call_genotype_non_allele,
+    call_genotype_fill: Hashable = variables.call_genotype_fill,
     merge: bool = True,
 ) -> Dataset:
     """Infer the ploidy of each call genotype based on the number of
-    non-allele values in each call genotype.
+    fill (non-allele) values in each call genotype.
 
     Parameters
     ----------
@@ -653,12 +651,12 @@ def infer_call_ploidy(
         Input variable name holding call_genotype as defined by
         :data:`sgkit.variables.call_genotype_spec`.
         Must be present in ``ds``.
-    call_genotype_non_allele
-        Input variable name holding call_genotype_non_allele as defined by
-        :data:`sgkit.variables.call_genotype_non_allele_spec`.
+    call_genotype_fill
+        Input variable name holding call_genotype_fill as defined by
+        :data:`sgkit.variables.call_genotype_fill_spec`.
         If the variable is not present in ``ds``, it will be computed
-        assuming that allele values less than -1 are non-alleles in mixed ploidy
-        datasets, or that no non-alleles are present in fixed ploidy datasets.
+        assuming that allele values less than -1 are fill (non-allele) values in mixed ploidy
+        datasets, or that no fill values are present in fixed ploidy datasets.
     merge
         If True (the default), merge the input dataset and the computed
         output variables into a single dataset, otherwise return only
@@ -671,13 +669,13 @@ def infer_call_ploidy(
     """
     ds = define_variable_if_absent(
         ds,
-        variables.call_genotype_non_allele,
-        call_genotype_non_allele,
-        infer_non_alleles,
+        variables.call_genotype_fill,
+        call_genotype_fill,
+        infer_call_genotype_fill,
     )
     mixed_ploidy = ds[variables.call_genotype].attrs.get("mixed_ploidy", False)
     if mixed_ploidy:
-        call_ploidy = (~ds[call_genotype_non_allele]).sum(axis=-1)
+        call_ploidy = (~ds[call_genotype_fill]).sum(axis=-1)
     else:
         ploidy = ds[variables.call_genotype].shape[-1]
         call_ploidy = xr.full_like(ds[variables.call_genotype][..., 0], ploidy)
@@ -694,7 +692,7 @@ def infer_variant_ploidy(
     merge: bool = True,
 ) -> Dataset:
     """Infer the ploidy at each variant across all samples based on
-    the number of non-allele values in call genotypes.
+    the number of fill (non-allele) values in call genotypes.
 
     Parameters
     ----------
@@ -743,7 +741,7 @@ def infer_sample_ploidy(
     merge: bool = True,
 ) -> Dataset:
     """Infer the ploidy of each sample across all variants based on
-    the number of non-allele values in call genotypes.
+    the number of fill (non-allele) values in call genotypes.
 
     Parameters
     ----------

sgkit/tests/io/vcf/test_vcf_reader.py

@@ -634,7 +634,7 @@ def test_vcf_to_zarr__mixed_ploidy_vcf(
     assert_array_equal(ds["sample_id"], ["SAMPLE1", "SAMPLE2", "SAMPLE3"])
 
     assert ds["call_genotype"].attrs["mixed_ploidy"] == mixed_ploidy
-    pad = -2 if mixed_ploidy else -1  # -2 indicates a non-allele
+    pad = -2 if mixed_ploidy else -1  # -2 indicates a fill (non-allele) value
     call_genotype = np.array(
         [
             [[0, 0, 1, 1, pad], [0, 0, pad, pad, pad], [0, 0, 0, 1, pad]],
@@ -648,7 +648,7 @@ def test_vcf_to_zarr__mixed_ploidy_vcf(
     assert_array_equal(ds["call_genotype"], call_genotype)
     assert_array_equal(ds["call_genotype_mask"], call_genotype < 0)
     if mixed_ploidy:
-        assert_array_equal(ds["call_genotype_non_allele"], call_genotype < -1)
+        assert_array_equal(ds["call_genotype_fill"], call_genotype < -1)
 
 
 @pytest.mark.parametrize(
@@ -1141,7 +1141,7 @@ def test_spec(shared_datadir, tmp_path):
             "call_GQ",
             "call_genotype",
             "call_genotype_mask",
-            "call_genotype_non_allele",
+            "call_genotype_fill",
             "call_genotype_phased",
             "call_HQ",
             "sample_id",

sgkit/variables.py

@@ -245,17 +245,14 @@ def _check_field(
     )
 )
 
-(
-    call_genotype_non_allele,
-    call_genotype_non_allele_spec,
-) = SgkitVariables.register_variable(
+(call_genotype_fill, call_genotype_fill_spec,) = SgkitVariables.register_variable(
     ArrayLikeSpec(
-        "call_genotype_non_allele",
+        "call_genotype_fill",
         kind="b",
         ndim=3,
         __doc__="""
 A flag for each allele position within mixed ploidy call genotypes
-indicating non-allele values of lower ploidy calls.
+indicating fill (non-allele) values of lower ploidy calls.
 """,
     )
 )