Merge branch 'main' into impl-validate-command

CAST-genomics · Oct 1, 2023 · 9234bef · 9234bef
2 parents d16f7bd + 7856638
commit 9234bef
Show file tree

Hide file tree

Showing 12 changed files with 6 additions and 70 deletions.
diff --git a/docs/api/data.rst b/docs/api/data.rst
@@ -193,13 +193,6 @@ The :class:`GenotypesPLINK` class offers experimental support for reading and wr
 
 	The time required to load various genotype file formats.
 
-.. warning::
-	This class depends on the ``Pgenlib`` python library. This can be installed automatically with ``haptools`` if you specify the "files" extra requirements during installation.
-
-	.. code-block:: bash
-
-		pip install haptools[files]
-
 The :class:`GenotypesPLINK` class inherits from the :class:`GenotypesVCF` class, so it has all the same methods and properties. Loading genotypes is the exact same, for example.
 
 .. code-block:: python

diff --git a/docs/formats/genotypes.rst b/docs/formats/genotypes.rst
@@ -22,13 +22,6 @@ There is also experimental support for `PLINK2 PGEN <https://github.com/chrchang
 
 If you run out memory when using PGEN files, consider reading/writing variants from the file in chunks via the ``--chunk-size`` parameter.
 
-.. note::
-	PLINK2 support depends on the ``Pgenlib`` python library. This can be installed automatically with ``haptools`` if you specify the "files" extra requirements during installation.
-
-	.. code-block:: bash
-
-		pip install haptools[files]
-
 Converting from VCF to PGEN
 ---------------------------
 To convert a VCF containing only biallelic SNPs to PGEN, use the following command.

diff --git a/docs/project_info/contributing.rst b/docs/project_info/contributing.rst
@@ -13,7 +13,7 @@ Types of Contributions
 ~~~~~~~~~~~~
 Report a bug
 ~~~~~~~~~~~~
-If you have found a bug, please report it on `our issues page <https://github.com/aryarm/haptools/issues>`_ rather than emailing us directly. Others may have the same issue and this helps us get that information to them.
+If you have found a bug, please report it on `our issues page <https://github.com/CAST-genomics/haptools/issues>`_ rather than emailing us directly. Others may have the same issue and this helps us get that information to them.
 
 Before you submit a bug, please search through our issues to ensure it hasn't already been reported. If you encounter an issue that has already been reported, please upvote it by reacting with a thumbs-up emoji. This helps us prioritize the issue.
 
@@ -80,7 +80,7 @@ Follow these steps to set up a development environment.
 
     .. code-block:: bash
 
-        poetry install -E docs -E tests -E files
+        poetry install -E docs -E tests
 
 Now, try importing ``haptools`` or running it on the command line.
 

diff --git a/docs/project_info/installation.rst b/docs/project_info/installation.rst
@@ -9,8 +9,8 @@ Using pip
 
 You can install ``haptools`` from PyPI using ``pip``.
 
-.. warning::
-   We recommend using ``pip >= 20.3`` because of `an issue in pysam <https://github.com/pysam-developers/pysam/issues/1132>`_.
+.. note::
+   We recommend using ``pip >= 20.3``.
 
    .. code-block:: bash
 
@@ -20,27 +20,6 @@ You can install ``haptools`` from PyPI using ``pip``.
 
    pip install haptools
 
-Installing ``haptools`` with the "files" extra requirements enables automatic support for a variety of additional file formats, like PLINK2 PGEN files.
-
-.. note::
-   The "files" extra requirement requires ``gcc`` and a few other compiler tools. Please make sure that they are installed first. To install with conda, for example, please execute the following:
-
-   .. code-block:: bash
-
-      conda install -c conda-forge gxx_linux-64
-
-   Alternatively, you can use the following on Ubuntu:
-
-   .. code-block:: bash
-
-      sudo apt install build-essential
-
-   See `issue 217 <https://github.com/chrchang/plink-ng/issues/217>`_ for current progress on this problem.
-
-.. code-block:: bash
-
-   pip install 'haptools[files]'
-
 Using conda
 -----------
 
@@ -50,9 +29,6 @@ We also support installing ``haptools`` from bioconda using ``conda``.
 
    conda install -c conda-forge -c bioconda haptools
 
-.. note::
-   Installing ``haptools`` from bioconda with PGEN support is not yet possible. See `issue 228 <https://github.com/chrchang/plink-ng/issues/228>`_ for current progress on this challenge.
-
 Installing the latest, unreleased version
 -----------------------------------------
 Can't wait for us to tag and release our most recent updates? You can install ``haptools`` directly from the ``main`` branch of our Github repository using ``pip``.

diff --git a/haptools/data/genotypes.py b/haptools/data/genotypes.py
@@ -7,6 +7,7 @@
 from logging import getLogger, Logger
 from collections import namedtuple, Counter
 
+import pgenlib
 import numpy as np
 import numpy.typing as npt
 from cyvcf2 import VCF, Variant
@@ -958,15 +959,6 @@ class GenotypesPLINK(GenotypesVCF):
     def __init__(self, fname: Path | str, log: Logger = None, chunk_size: int = None):
         super().__init__(fname, log)
         self.chunk_size = chunk_size
-        try:
-            global pgenlib
-            import pgenlib
-        except ImportError:
-            raise ImportError(
-                f"We cannot read PGEN files without the pgenlib library. Please "
-                f"reinstall haptools with the 'files' extra requirement via\n"
-                f"pip install haptools[files]"
-            )
 
     def read_samples(self, samples: list[str] = None):
         """
@@ -1238,7 +1230,6 @@ def read(
             See documentation for :py:attr:`~.GenotypesVCF.read`
         """
         super(Genotypes, self).read()
-        import pgenlib
 
         sample_idxs = self.read_samples(samples)
         pv = pgenlib.PvarReader(bytes(str(self.fname.with_suffix(".pvar")), "utf8"))
@@ -1395,7 +1386,6 @@ def __iter__(
             See documentation for :py:meth:`~.GenotypesPLINK._iterate`
         """
         super(Genotypes, self).read()
-        import pgenlib
 
         pv = pgenlib.PvarReader(bytes(str(self.fname.with_suffix(".pvar")), "utf8"))
 
@@ -1484,8 +1474,6 @@ def write(self):
         Write the variants in this class to PLINK2 files at
         :py:attr:`~.GenotypesPLINK.fname`
         """
-        import pgenlib
-
         # write the psam and pvar files
         self.write_samples()
         self.write_variants()

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -16,7 +16,7 @@ click = ">=8.0.3"
 pysam = ">=0.19.0"
 cyvcf2 = ">=0.30.14"
 matplotlib = ">=3.5.1"
-Pgenlib = {version = ">=0.90.1", optional = true, extras = ["files"]}
+Pgenlib = ">=0.90.1"
 
 # docs
 # these belong in dev-dependencies, but RTD doesn't support that yet -- see
@@ -61,10 +61,6 @@ tests = [
     "nox-poetry"
 ]
 
-files = [
-    "Pgenlib"
-]
-
 [tool.poetry.scripts]
 haptools = 'haptools.__main__:main'
 

diff --git a/tests/test_data.py b/tests/test_data.py
@@ -313,7 +313,6 @@ def test_merge_variants(self):
 
 class TestGenotypesPLINK:
     def _get_fake_genotypes_plink(self):
-        pgenlib = pytest.importorskip("pgenlib")
         gts_ref_alt = TestGenotypesVCF()._get_fake_genotypes_refalt()
         gts = GenotypesPLINK(gts_ref_alt.fname)
         gts.data = gts_ref_alt.data
@@ -322,7 +321,6 @@ def _get_fake_genotypes_plink(self):
         return gts
 
     def _get_fake_genotypes_multiallelic(self):
-        pgenlib = pytest.importorskip("pgenlib")
         gts_ref_alt = TestGenotypesVCF()._get_fake_genotypes_multiallelic()
         gts = GenotypesPLINK(gts_ref_alt.fname)
         gts.data = gts_ref_alt.data
@@ -331,8 +329,6 @@ def _get_fake_genotypes_multiallelic(self):
         return gts
 
     def _get_fake_genotypes_multiallelic_tr(self):
-        pgenlib = pytest.importorskip("pgenlib")
-
         gts_tr = GenotypesTR(DATADIR / "simple-tr.vcf")
         gts_tr.read()
 

diff --git a/tests/test_outputvcf.py b/tests/test_outputvcf.py
@@ -21,8 +21,6 @@
 
 def _get_files(plink_input=False, plink_output=False):
     log = getLogger(name="test")
-    if plink_input or plink_output:
-        pytest.importorskip("pgenlib")
     bkp_file = DATADIR / "outvcf_test.bp"
     model_file = DATADIR / "outvcf_gen.dat"
     vcf_file = DATADIR / ("outvcf_test" + (".pgen" if plink_input else ".vcf.gz"))

diff --git a/tests/test_simgenotype.py b/tests/test_simgenotype.py
@@ -43,7 +43,6 @@ def test_basic(capfd):
 
 
 def test_pgen_output(capfd):
-    pytest.importorskip("pgenlib")
     prefix = DATADIR / "example_simgenotype.pgen"
     dat_file = DATADIR / "outvcf_gen.dat"
     map_dir = DATADIR / "map"

diff --git a/tests/test_simphenotype.py b/tests/test_simphenotype.py
@@ -526,7 +526,6 @@ def test_ancestry(self, capfd):
         tmp_transform.unlink()
 
     def test_pgen(self, capfd):
-        pytest.importorskip("pgenlib")
         # first, create a temporary file containing the output of transform
         tmp_tsfm = Path("simple-haps.pgen")
         gt_file = DATADIR / "simple.pgen"

diff --git a/tests/test_transform.py b/tests/test_transform.py
@@ -261,7 +261,6 @@ def test_basic_subset(capfd):
 
 
 def test_basic_pgen_input(capfd):
-    pytest.importorskip("pgenlib")
     expected = """##fileformat=VCFv4.2
 ##FILTER=<ID=PASS,Description="All filters passed">
 ##contig=<ID=1>