bio2zarr 0.1.6__tar.gz → 0.1.7__tar.gz

{bio2zarr-0.1.6 → bio2zarr-0.1.7}/.github/workflows/ci.yml

@@ -6,6 +6,9 @@ on:
   push:
     branches:
       - main
+  schedule:
+    # At 04:44 on Monday, see https://crontab.guru/
+    - cron: "44 4 * * 1"
 
 jobs:
   pre-commit:
@@ -22,22 +25,16 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        # Use macos-13 because pip binary packages for ARM aren't
-        # available for many dependencies
-        os: [macos-13, macos-14, ubuntu-latest]
-        python-version: ["3.10", "3.11", "3.12"]
+        os: [macos-14, ubuntu-latest]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
         exclude:
           # Just run macos tests on one Python version
-          - os: macos-13
-            python-version: "3.10"
-          - os: macos-13
-            python-version: "3.11"
-          - os: macos-13
-            python-version: "3.12"
           - os: macos-14
             python-version: "3.10"
           - os: macos-14
             python-version: "3.12"
+          - os: macos-14
+            python-version: "3.13"
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }}
@@ -152,36 +149,16 @@ jobs:
           plink2zarr --help
           python -m bio2zarr plink2zarr --help
 
-  test-numpy-version:
-    name: Test numpy versions
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        numpy: ["==1.26", ">=2"]
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install '.[dev]'
-      - name: Install numpy${{ matrix.numpy }}
-        run: |
-          python -m pip install 'numpy${{ matrix.numpy }}'
-      - name: Run tests
-        run: |
-          # We just run the CLI tests here because it doesn't require other upstream
-          # packages like sgkit (which are tangled up with the numpy 2 dependency)
-          python -m pytest tests/test_cli.py
-
   test-zarr-version:
     name: Test Zarr versions
     runs-on: ubuntu-latest
     strategy:
       matrix:
         zarr: ["==2.18.3", ">=3.0.3"]
+        zarr-format: [2, 3]
+        exclude:
+          - zarr: "==2.18.3"
+            zarr-format: 3
     steps:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
@@ -197,3 +174,5 @@ jobs:
       - name: Run tests
         run: |
           python -m pytest
+        env:
+          BIO2ZARR_ZARR_FORMAT: ${{ matrix.zarr-format }}

{bio2zarr-0.1.6 → bio2zarr-0.1.7}/CHANGELOG.md

@@ -1,3 +1,31 @@
+# 0.1.7 2026-02-03
+
+*Bug fixes*
+
+- Fix issue with 0-dimensional arrays (#437)
+
+- Fix issue with pandas 3.x (required in plink code; #439)
+
+*Breaking changes*
+
+- Require NumPy 2 (#426)
+
+- Require tskit >= 1.0.
+
+- The default `isolated_as_missing` behaviour for tskit conversion now follows
+  tskit's default (currently `True`). To get the previous behaviour, create a
+  model mapping using `ts.map_to_vcf_model(isolated_as_missing=False)` and pass
+  it via the `model_mapping` parameter (or use `tskit2zarr convert --isolated-as-ancestral`).
+
+- The `contig_id` and `isolated_as_missing` parameters to
+  `bio2zarr.tskit.convert` have been removed; set these via
+  `tskit.TreeSequence.map_to_vcf_model` and pass the returned mapping via the
+  `model_mapping` parameter.
+
+*Maintenance*
+
+- Add support for Python 3.13
+
 # 0.1.6 2025-05-23
 
 - Initial Python API support for VCF and tskit one-shot conversion. Format

{bio2zarr-0.1.6 → bio2zarr-0.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bio2zarr
-Version: 0.1.6
+Version: 0.1.7
 Summary: Convert bioinformatics data to Zarr
 Author-email: sgkit Developers <project@sgkit.dev>
 License:                                  Apache License
@@ -219,11 +219,12 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy>=1.26
+Requires-Dist: numpy>=2
 Requires-Dist: zarr<3,>=2.17
 Requires-Dist: numcodecs[msgpack]!=0.14.0,!=0.14.1,<0.16
 Requires-Dist: tabulate
@@ -240,22 +241,25 @@ Requires-Dist: pysam; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-coverage; extra == "dev"
 Requires-Dist: pytest-xdist; extra == "dev"
-Requires-Dist: sgkit>=0.8.0; extra == "dev"
 Requires-Dist: tqdm; extra == "dev"
-Requires-Dist: tskit>=0.6.4; extra == "dev"
+Requires-Dist: tskit>=1; extra == "dev"
 Requires-Dist: bed_reader; extra == "dev"
 Requires-Dist: cyvcf2; extra == "dev"
+Requires-Dist: xarray<2025.03.1; extra == "dev"
+Requires-Dist: dask[array]<=2024.8.0,>=2022.01.0; extra == "dev"
 Provides-Extra: tskit
-Requires-Dist: tskit>=0.6.4; extra == "tskit"
+Requires-Dist: tskit>=1; extra == "tskit"
 Provides-Extra: vcf
 Requires-Dist: cyvcf2; extra == "vcf"
 Provides-Extra: all
-Requires-Dist: tskit>=0.6.4; extra == "all"
+Requires-Dist: tskit>=1; extra == "all"
 Requires-Dist: cyvcf2; extra == "all"
 Dynamic: license-file
 
 [![CI](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml)
 [![Coverage Status](https://coveralls.io/repos/github/sgkit-dev/bio2zarr/badge.svg)](https://coveralls.io/github/sgkit-dev/bio2zarr)
+[![PyPI Downloads](https://static.pepy.tech/badge/bio2zarr)](https://pepy.tech/projects/bio2zarr)
+[![Anaconda-Server Badge](https://anaconda.org/bioconda/bio2zarr/badges/downloads.svg)](https://anaconda.org/bioconda/bio2zarr)
 
 
 # bio2zarr

{bio2zarr-0.1.6 → bio2zarr-0.1.7}/README.md

@@ -1,5 +1,7 @@
 [![CI](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml)
 [![Coverage Status](https://coveralls.io/repos/github/sgkit-dev/bio2zarr/badge.svg)](https://coveralls.io/github/sgkit-dev/bio2zarr)
+[![PyPI Downloads](https://static.pepy.tech/badge/bio2zarr)](https://pepy.tech/projects/bio2zarr)
+[![Anaconda-Server Badge](https://anaconda.org/bioconda/bio2zarr/badges/downloads.svg)](https://anaconda.org/bioconda/bio2zarr)
 
 
 # bio2zarr

{bio2zarr-0.1.6 → bio2zarr-0.1.7}/bio2zarr/_version.py

@@ -1,7 +1,14 @@
 # file generated by setuptools-scm
 # don't change, don't track in version control
 
-__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
 
 TYPE_CHECKING = False
 if TYPE_CHECKING:
@@ -9,13 +16,19 @@ if TYPE_CHECKING:
     from typing import Union
 
     VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
 else:
     VERSION_TUPLE = object
+    COMMIT_ID = object
 
 version: str
 __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.6'
-__version_tuple__ = version_tuple = (0, 1, 6)
+__version__ = version = '0.1.7'
+__version_tuple__ = version_tuple = (0, 1, 7)
+
+__commit_id__ = commit_id = 'g4359d72e2'

{bio2zarr-0.1.6 → bio2zarr-0.1.7}/bio2zarr/cli.py

@@ -652,7 +652,12 @@ def vcfpartition(vcfs, verbose, num_partitions, partition_size):
 @click.argument("zarr_path", type=click.Path())
 @click.option("--contig-id", type=str, help="Contig/chromosome ID (default: '1')")
 @click.option(
-    "--isolated-as-missing", is_flag=True, help="Treat isolated nodes as missing"
+    "--isolated-as-missing/--isolated-as-ancestral",
+    default=None,
+    help=(
+        "Treat isolated samples without mutations as missing or ancestral "
+        "(default: tskit default)"
+    ),
 )
 @variants_chunk_size
 @samples_chunk_size
@@ -660,6 +665,7 @@ def vcfpartition(vcfs, verbose, num_partitions, partition_size):
 @progress
 @worker_processes
 @force
+@core.requires_optional_dependency("tskit", "tskit")
 def convert_tskit(
     ts_path,
     zarr_path,
@@ -675,11 +681,18 @@ def convert_tskit(
     setup_logging(verbose)
     check_overwrite_dir(zarr_path, force)
 
+    import tskit
+
+    ts = tskit.load(ts_path)
+    model_mapping = ts.map_to_vcf_model(
+        contig_id=contig_id,
+        isolated_as_missing=isolated_as_missing,
+    )
+
     tskit_mod.convert(
         ts_path,
         zarr_path,
-        contig_id=contig_id,
-        isolated_as_missing=isolated_as_missing,
+        model_mapping=model_mapping,
         variants_chunk_size=variants_chunk_size,
         samples_chunk_size=samples_chunk_size,
         worker_processes=worker_processes,

{bio2zarr-0.1.6 → bio2zarr-0.1.7}/bio2zarr/plink.py

@@ -6,6 +6,7 @@ import numpy as np
 import pandas as pd
 
 from bio2zarr import constants, core, vcz
+from bio2zarr.zarr_utils import STRING_DTYPE_NAME
 
 logger = logging.getLogger(__name__)
 
@@ -198,7 +199,7 @@ class PlinkFormat(vcz.Source):
         ref_iter = self.bim.allele_2.values[start:stop]
         gt_iter = self.bed_reader.iter_decode(start, stop)
         for alt, ref, gt in zip(alt_iter, ref_iter, gt_iter):
-            alleles = np.full(num_alleles, constants.STR_FILL, dtype="O")
+            alleles = np.full(num_alleles, constants.STR_FILL, dtype=STRING_DTYPE_NAME)
             alleles[0] = ref
             alleles[1 : 1 + len(alt)] = alt
             phased = np.zeros(gt.shape[0], dtype=bool)
@@ -234,8 +235,9 @@ class PlinkFormat(vcz.Source):
         )
         # If we don't have SVLEN or END annotations, the rlen field is defined
         # as the length of the REF
-        max_len = self.bim.allele_2.values.itemsize
-
+        # Explicitly cast to fixed size array to support pandas 2.x and 3.x
+        allele_2_array = self.bim.allele_2.values.astype("S")
+        max_len = allele_2_array.itemsize
         array_specs = [
             vcz.ZarrArraySpec(
                 source="position",
@@ -246,13 +248,13 @@ class PlinkFormat(vcz.Source):
             ),
             vcz.ZarrArraySpec(
                 name="variant_allele",
-                dtype="O",
+                dtype=STRING_DTYPE_NAME,
                 dimensions=["variants", "alleles"],
                 description=None,
             ),
             vcz.ZarrArraySpec(
                 name="variant_id",
-                dtype="O",
+                dtype=STRING_DTYPE_NAME,
                 dimensions=["variants"],
                 description=None,
             ),

{bio2zarr-0.1.6 → bio2zarr-0.1.7}/bio2zarr/tskit.py

@@ -4,6 +4,7 @@ import pathlib
 import numpy as np
 
 from bio2zarr import constants, core, vcz
+from bio2zarr.zarr_utils import STRING_DTYPE_NAME
 
 logger = logging.getLogger(__name__)
 
@@ -15,8 +16,6 @@ class TskitFormat(vcz.Source):
         ts,
         *,
         model_mapping=None,
-        contig_id=None,
-        isolated_as_missing=False,
     ):
         import tskit
 
@@ -35,14 +34,14 @@ class TskitFormat(vcz.Source):
             f"{self.ts.num_sites} sites"
         )
 
-        self.contig_id = contig_id if contig_id is not None else "1"
-        self.isolated_as_missing = isolated_as_missing
-
-        self.positions = self.ts.sites_position
-
         if model_mapping is None:
             model_mapping = self.ts.map_to_vcf_model()
 
+        self.contig_id = model_mapping.contig_id
+        self.contig_length = model_mapping.contig_length
+        self.isolated_as_missing = model_mapping.isolated_as_missing
+        self.raw_positions = self.ts.sites_position
+        self.vcf_positions = model_mapping.transformed_positions
         individuals_nodes = model_mapping.individuals_nodes
         sample_ids = model_mapping.individuals_name
 
@@ -91,14 +90,14 @@ class TskitFormat(vcz.Source):
 
     @property
     def contigs(self):
-        return [vcz.Contig(id=self.contig_id)]
+        return [vcz.Contig(id=self.contig_id, length=self.contig_length)]
 
     def iter_contig(self, start, stop):
         yield from (0 for _ in range(start, stop))
 
     def iter_field(self, field_name, shape, start, stop):
         if field_name == "position":
-            for pos in self.ts.sites_position[start:stop]:
+            for pos in self.vcf_positions[start:stop]:
                 yield int(pos)
         else:
             raise ValueError(f"Unknown field {field_name}")
@@ -110,13 +109,13 @@ class TskitFormat(vcz.Source):
 
         for variant in self.ts.variants(
             isolated_as_missing=self.isolated_as_missing,
-            left=self.positions[start],
-            right=self.positions[stop] if stop < self.num_records else None,
+            left=self.raw_positions[start],
+            right=self.raw_positions[stop] if stop < self.num_records else None,
             samples=self.tskit_samples,
             copy=False,
         ):
             gt = np.full(shape, constants.INT_FILL, dtype=np.int8)
-            alleles = np.full(num_alleles, constants.STR_FILL, dtype="O")
+            alleles = np.full(num_alleles, constants.STR_FILL, dtype=STRING_DTYPE_NAME)
             # length is the length of the REF allele unless other fields
             # are included.
             variant_length = len(variant.alleles[0])
@@ -176,8 +175,8 @@ class TskitFormat(vcz.Source):
         min_position = 0
         max_position = 0
         if self.ts.num_sites > 0:
-            min_position = np.min(self.ts.sites_position)
-            max_position = np.max(self.ts.sites_position)
+            min_position = np.min(self.vcf_positions)
+            max_position = np.max(self.vcf_positions)
 
         tables = self.ts.tables
         ancestral_state_offsets = tables.sites.ancestral_state_offset
@@ -200,7 +199,7 @@ class TskitFormat(vcz.Source):
             vcz.ZarrArraySpec(
                 source=None,
                 name="variant_allele",
-                dtype="O",
+                dtype=STRING_DTYPE_NAME,
                 dimensions=["variants", "alleles"],
                 description="Alleles for each variant",
             ),
@@ -252,8 +251,6 @@ def convert(
     vcz_path,
     *,
     model_mapping=None,
-    contig_id=None,
-    isolated_as_missing=False,
     variants_chunk_size=None,
     samples_chunk_size=None,
     worker_processes=core.DEFAULT_WORKER_PROCESSES,
@@ -277,8 +274,6 @@ def convert(
     tskit_format = TskitFormat(
         ts_or_path,
         model_mapping=model_mapping,
-        contig_id=contig_id,
-        isolated_as_missing=isolated_as_missing,
     )
     schema_instance = tskit_format.generate_schema(
         variants_chunk_size=variants_chunk_size,

{bio2zarr-0.1.6 → bio2zarr-0.1.7}/bio2zarr/vcf.py

@@ -16,6 +16,8 @@ from typing import Any
 import numcodecs
 import numpy as np
 
+from bio2zarr.zarr_utils import STRING_DTYPE_NAME, zarr_exists
+
 from . import constants, core, provenance, vcf_utils, vcz
 
 logger = logging.getLogger(__name__)
@@ -110,7 +112,7 @@ class VcfField:
             ret = "U1"
         else:
             assert self.vcf_type == "String"
-            ret = "O"
+            ret = STRING_DTYPE_NAME
         return ret
 
 
@@ -397,7 +399,7 @@ def sanitise_value_string_scalar(shape, value):
 
 def sanitise_value_string_1d(shape, value):
     if value is None:
-        return np.full(shape, ".", dtype="O")
+        return np.full(shape, ".", dtype=STRING_DTYPE_NAME)
     else:
         value = drop_empty_second_dim(value)
         result = np.full(shape, "", dtype=value.dtype)
@@ -407,9 +409,9 @@ def sanitise_value_string_1d(shape, value):
 
 def sanitise_value_string_2d(shape, value):
     if value is None:
-        return np.full(shape, ".", dtype="O")
+        return np.full(shape, ".", dtype=STRING_DTYPE_NAME)
     else:
-        result = np.full(shape, "", dtype="O")
+        result = np.full(shape, "", dtype=STRING_DTYPE_NAME)
         if value.ndim == 2:
             result[: value.shape[0], : value.shape[1]] = value
         else:
@@ -569,7 +571,12 @@ class StringValueTransformer(VcfValueTransformer):
             value = np.array(list(vcf_value.split(",")))
         else:
             # TODO can we make this faster??
-            value = np.array([v.split(",") for v in vcf_value], dtype="O")
+            var_len_values = [v.split(",") for v in vcf_value]
+            number = max(len(v) for v in var_len_values)
+            value = np.array(
+                [v + [""] * (number - len(v)) for v in var_len_values],
+                dtype=STRING_DTYPE_NAME,
+            )
             # print("HERE", vcf_value, value)
             # for v in vcf_value:
             #     print("\t", type(v), len(v), v.split(","))
@@ -1044,7 +1051,7 @@ class IntermediateColumnarFormat(vcz.Source):
             ref_field.iter_values(start, stop),
             alt_field.iter_values(start, stop),
         ):
-            alleles = np.full(num_alleles, constants.STR_FILL, dtype="O")
+            alleles = np.full(num_alleles, constants.STR_FILL, dtype=STRING_DTYPE_NAME)
             alleles[0] = ref[0]
             alleles[1 : 1 + len(alt)] = alt
             yield alleles
@@ -1068,14 +1075,16 @@ class IntermediateColumnarFormat(vcz.Source):
             for variant_length, alleles in zip(
                 variant_lengths, self.iter_alleles(start, stop, num_alleles)
             ):
-                yield vcz.VariantData(variant_length, alleles, None, None)
+                # Stored ICF values are always at least 1D arrays; "rlen" is Number=1
+                # so we must extract the scalar to avoid NumPy scalar-conversion issues.
+                yield vcz.VariantData(variant_length[0], alleles, None, None)
         else:
             for variant_length, alleles, (gt, phased) in zip(
                 variant_lengths,
                 self.iter_alleles(start, stop, num_alleles),
                 self.iter_genotypes(shape, start, stop),
             ):
-                yield vcz.VariantData(variant_length, alleles, gt, phased)
+                yield vcz.VariantData(variant_length[0], alleles, gt, phased)
 
     def generate_schema(
         self, variants_chunk_size=None, samples_chunk_size=None, local_alleles=None
@@ -1087,8 +1096,10 @@ class IntermediateColumnarFormat(vcz.Source):
 
         # Add ploidy and genotypes dimensions only when needed
         max_genotypes = 0
+        has_g_field = False
         for field in self.metadata.format_fields:
             if field.vcf_number == "G":
+                has_g_field = True
                 max_genotypes = max(max_genotypes, field.summary.max_number)
 
         ploidy = None
@@ -1100,7 +1111,7 @@ class IntermediateColumnarFormat(vcz.Source):
             genotypes_size = math.comb(max_alleles + ploidy - 1, ploidy)
             # assert max_genotypes == genotypes_size
         else:
-            if max_genotypes > 0:
+            if max_genotypes > 0 or has_g_field:
                 # there is no GT field, but there is at least one Number=G field,
                 # so need to define genotypes dimension
                 genotypes_size = max_genotypes
@@ -1163,7 +1174,7 @@ class IntermediateColumnarFormat(vcz.Source):
             ),
             fixed_field_spec(
                 name="variant_allele",
-                dtype="O",
+                dtype=STRING_DTYPE_NAME,
                 dimensions=["variants", "alleles"],
             ),
             fixed_field_spec(
@@ -1173,7 +1184,7 @@ class IntermediateColumnarFormat(vcz.Source):
             ),
             fixed_field_spec(
                 name="variant_id",
-                dtype="O",
+                dtype=STRING_DTYPE_NAME,
             ),
             fixed_field_spec(
                 name="variant_id_mask",
@@ -1581,8 +1592,7 @@ def inspect(path):
         raise ValueError(f"Path not found: {path}")
     if (path / "metadata.json").exists():
         obj = IntermediateColumnarFormat(path)
-    # NOTE: this is too strict, we should support more general Zarrs, see #276
-    elif (path / ".zmetadata").exists():
+    elif zarr_exists(path):
         obj = vcz.VcfZarr(path)
     else:
         raise ValueError(f"{path} not in ICF or VCF Zarr format")