feat: use chunking when reading from PGENs in simgenotype (#270)

CAST-genomics · Feb 7, 2025 · 5ae546d · 5ae546d
1 parent 4c22846
commit 5ae546d
Show file tree

Hide file tree

Showing 3 changed files with 2 additions and 3 deletions.
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -17,7 +17,7 @@ jobs:
           - { python: "3.10", os: "ubuntu-latest", session: "tests" }
           - { python: "3.11", os: "ubuntu-latest", session: "tests" }
           - { python: "3.12", os: "ubuntu-latest", session: "tests" }
-          - { python: "3.13", os: "ubuntu-latest", session: "tests" }
+          # - { python: "3.13", os: "ubuntu-latest", session: "tests" }
           # - { python: "3.11", os: "windows-latest", session: "tests" }
           - { python: "3.9", os: "macos-13", session: "tests" }
           - { python: "3.12", os: "macos-latest", session: "tests" }

diff --git a/haptools/sim_genotype.py b/haptools/sim_genotype.py
@@ -104,7 +104,7 @@ def output_vcf(
     #      IE sample HG00097 is index 1 in a list of samples [HG00096 HG00097 HG00098]
     # create sample dictionary that holds sample name to the index in the vcf file for quick access 
     if variant_file.endswith(".pgen"):
-        vcf = GenotypesPLINK(variant_file, log=log)
+        vcf = GenotypesPLINK(variant_file, chunk_size=chunk_size, log=log)
     else:
         vcf = GenotypesVCF(variant_file, log=log)
 

diff --git a/noxfile.py b/noxfile.py
@@ -64,7 +64,6 @@ def tests(session: Session) -> None:
         session.conda_install(
             "coverage[toml]",
             "pytest",
-            "numpy>=1.20.0",
             channel="conda-forge",
         )
         install_handle_python_numpy(session)