WIP: VCF loading

pandas_genomics/io/__init__.py

@@ -7,8 +7,10 @@
      :toctree: io
 
      from_plink
+     from_vcf
 """
 
 from .plink import from_plink
+from .vcf import from_vcf
 
-__all__ = ['from_plink', ]
+__all__ = ['from_plink', 'from_vcf']

tests/io/conftest.py

@@ -1,36 +1,45 @@
 from pathlib import Path
+
+import cyvcf2
 import pytest
 
 from pandas_genomics import io
 
-data_dir = Path(__file__).parent.parent / "data"
+DATA_DIR = Path(__file__).parent.parent / "data"
+VCF_DIR = Path(cyvcf2.__file__) / "tests"
 
 
 @pytest.mark.slow
 @pytest.fixture
 def plink_small():
-    bed_file = data_dir / "plink" / "plink_test_small.bed"
+    bed_file = DATA_DIR / "plink" / "plink_test_small.bed"
     result = io.from_plink(bed_file)
     return result
 
 
 @pytest.mark.slow
 @pytest.fixture
 def plink_medium():
-    bed_file = data_dir / "plink" / "plink_test_medium.bed"
+    bed_file = DATA_DIR / "plink" / "plink_test_medium.bed"
     result = io.from_plink(bed_file)
     return result
 
 
 @pytest.fixture
 def plink_small_20():
-    bed_file = data_dir / "plink" / "plink_test_small.bed"
+    bed_file = DATA_DIR / "plink" / "plink_test_small.bed"
     result = io.from_plink(bed_file, max_variants=20)
     return result
 
 
 @pytest.fixture
 def plink_small_20_swap():
-    bed_file = data_dir / "plink" / "plink_test_small.bed"
+    bed_file = DATA_DIR / "plink" / "plink_test_small.bed"
     result = io.from_plink(bed_file, max_variants=20, swap_alleles=True)
     return result
+
+@pytest.fixture
+def vcf_test():
+    vcf_filename = VCF_DIR / "test.vcf.gz"
+    result = io.from_vcf(vcf_filename)
+    return result

tests/io/test_vcf.py

@@ -0,0 +1,4 @@
+def test_loaded(vcf_test):
+    """Validate the dataset"""
+    # TODO: Add more assertions
+    assert vcf_test.shape == (150, 3020)