tskit 1.0.1__cp314-cp314-macosx_10_15_universal2.whl

tskit/vcf.py

@@ -0,0 +1,219 @@
+#
+# MIT License
+#
+# Copyright (c) 2019-2024 Tskit Developers
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+"""
+Convert tree sequences to VCF.
+"""
+import numpy as np
+
+from . import provenance
+
+
+class VcfWriter:
+    """
+    Writes a VCF representation of the genotypes tree sequence to a
+    file-like object.
+    """
+
+    def __init__(
+        self,
+        tree_sequence,
+        *,
+        ploidy,
+        contig_id,
+        individuals,
+        individual_names,
+        position_transform,
+        site_mask,
+        sample_mask,
+        isolated_as_missing,
+        allow_position_zero,
+        include_non_sample_nodes,
+    ):
+        self.tree_sequence = tree_sequence
+
+        vcf_model = tree_sequence.map_to_vcf_model(
+            individuals=individuals,
+            ploidy=ploidy,
+            individual_names=individual_names,
+            include_non_sample_nodes=include_non_sample_nodes,
+            position_transform=position_transform,
+            contig_id=contig_id,
+            isolated_as_missing=isolated_as_missing,
+        )
+
+        # We now make some tweaks to the VCF model required for
+        # writing the VCF in text format
+
+        # Remove individuals with zero ploidy as these cannot be
+        # represented in VCF.
+        to_keep = (vcf_model.individuals_nodes != -1).any(axis=1)
+        vcf_model.individuals_nodes = vcf_model.individuals_nodes[to_keep]
+        vcf_model.individual_names = vcf_model.individuals_name[to_keep]
+        self.individual_ploidies = [
+            len(nodes[nodes >= 0]) for nodes in vcf_model.individuals_nodes
+        ]
+        self.num_individuals = len(vcf_model.individual_names)
+
+        if len(vcf_model.individuals_nodes) == 0:
+            raise ValueError("No samples in resulting VCF model")
+
+        if len(vcf_model.transformed_positions) > 0:
+            # Arguably this should be last_pos + 1, but if we hit this
+            # condition the coordinate systems are all muddled up anyway
+            # so it's simpler to stay with this rule that was inherited
+            # from the legacy VCF output code.
+            vcf_model.contig_length = max(
+                vcf_model.transformed_positions[-1], vcf_model.contig_length
+            )
+
+        # Flatten the array of node IDs, filtering out the -1 padding values
+        self.samples = []
+        for row in vcf_model.individuals_nodes:
+            for node_id in row:
+                if node_id != -1:
+                    self.samples.append(node_id)
+
+        if site_mask is None:
+            site_mask = np.zeros(tree_sequence.num_sites, dtype=bool)
+        self.site_mask = np.array(site_mask, dtype=bool)
+        if self.site_mask.shape != (tree_sequence.num_sites,):
+            raise ValueError("Site mask must be 1D a boolean array of length num_sites")
+
+        # The VCF spec does not allow for positions to be 0, so we error if one of the
+        # transformed positions is 0 and allow_position_zero is False.
+        if not allow_position_zero and np.any(
+            vcf_model.transformed_positions[~site_mask] == 0
+        ):
+            raise ValueError(
+                "A variant position of 0 was found in the VCF output, this is not "
+                "fully compliant with the VCF spec. If you still wish to write the VCF "
+                'please use the "allow_position_zero" argument to write_vcf. '
+                "Alternatively, you can increment all the positions by one using "
+                '"position_transform = lambda x: 1 + x" or coerce the zero to one with '
+                '"position_transform = lambda x: np.fmax(1, x)"'
+            )
+
+        self.sample_mask = sample_mask
+        if sample_mask is not None:
+            if not callable(sample_mask):
+                sample_mask = np.array(sample_mask, dtype=bool)
+                self.sample_mask = lambda _: sample_mask
+
+        self.vcf_model = vcf_model
+
+    def __write_header(self, output):
+        print("##fileformat=VCFv4.2", file=output)
+        print(f"##source=tskit {provenance.__version__}", file=output)
+        print('##FILTER=<ID=PASS,Description="All filters passed">', file=output)
+        print(
+            f"##contig=<ID={self.vcf_model.contig_id},length={self.vcf_model.contig_length}>",
+            file=output,
+        )
+        print(
+            '##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">', file=output
+        )
+        vcf_samples = "\t".join(self.vcf_model.individual_names)
+        print(
+            "#CHROM",
+            "POS",
+            "ID",
+            "REF",
+            "ALT",
+            "QUAL",
+            "FILTER",
+            "INFO",
+            "FORMAT",
+            vcf_samples,
+            sep="\t",
+            file=output,
+        )
+
+    def write(self, output):
+        self.__write_header(output)
+
+        # Build the array for hold the text genotype VCF data and the indexes into
+        # this array for when we're updating it.
+        gt_array = []
+        indexes = []
+        for ploidy in self.individual_ploidies:
+            for _ in range(ploidy):
+                indexes.append(len(gt_array))
+                # First element here is a placeholder that we'll write the actual
+                # genotypes into when for each variant.
+                gt_array.extend([0, ord("|")])
+            gt_array[-1] = ord("\t")
+        gt_array[-1] = ord("\n")
+        gt_array = np.array(gt_array, dtype=np.int8)
+        # TODO Unclear here whether using int64 or int32 will be faster for this index
+        # array. Test it out.
+        indexes = np.array(indexes, dtype=int)
+
+        for variant in self.tree_sequence.variants(
+            samples=self.samples, isolated_as_missing=self.vcf_model.isolated_as_missing
+        ):
+            site_id = variant.site.id
+            # We check the mask before we do any checks so we can use this as a
+            # way of skipping problematic sites.
+            if self.site_mask[site_id]:
+                continue
+
+            if variant.num_alleles > 9:
+                raise ValueError(
+                    "More than 9 alleles not currently supported. Please open an issue "
+                    "on GitHub if this limitation affects you."
+                )
+            pos = self.vcf_model.transformed_positions[variant.index]
+            ref = variant.alleles[0]
+            alt = "."
+            if variant.num_alleles > 1:
+                alt = ",".join(variant.alleles[1 : variant.num_alleles])
+            print(
+                self.vcf_model.contig_id,
+                pos,
+                site_id,
+                ref,
+                alt,
+                ".",
+                "PASS",
+                ".",
+                "GT",
+                sep="\t",
+                end="\t",
+                file=output,
+            )
+            genotypes = variant.genotypes
+            gt_array[indexes] = genotypes + ord("0")
+            if self.sample_mask is not None:
+                genotypes = genotypes.copy()
+                sample_mask = np.array(self.sample_mask(variant), dtype=bool)
+                if sample_mask.shape != genotypes.shape:
+                    raise ValueError(
+                        "Sample mask must be a numpy array of size num_samples"
+                    )
+                genotypes[sample_mask] = -1
+            if self.sample_mask is not None or variant.has_missing_data:
+                missing = genotypes == -1
+                gt_array[indexes[missing]] = ord(".")
+            g_bytes = memoryview(gt_array).tobytes()
+            g_str = g_bytes.decode()
+            print(g_str, end="", file=output)

tskit-1.0.1.dist-info/METADATA

@@ -0,0 +1,105 @@
+Metadata-Version: 2.4
+Name: tskit
+Version: 1.0.1
+Summary: The tree sequence toolkit.
+Author-email: Tskit Developers <admin@tskit.dev>
+License-Expression: MIT
+Project-URL: Homepage, https://tskit.dev/tskit
+Project-URL: Documentation, https://tskit.dev/tskit/docs/stable
+Project-URL: Changelog, https://tskit.dev/tskit/docs/stable/changelogs.html
+Project-URL: Bug Tracker, https://github.com/tskit-dev/tskit/issues
+Project-URL: GitHub, https://github.com/tskit-dev/tskit/
+Keywords: population genetics,tree sequence,ancestral recombination graph,evolutionary tree,statistical genetics,phylogenetics,tskit
+Classifier: Programming Language :: C
+Classifier: Programming Language :: Python
+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: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Other Environment
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: POSIX
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.10
+Description-Content-Type: text/x-rst
+License-File: LICENSE
+Requires-Dist: jsonschema>=3.0.0
+Requires-Dist: numpy>=2
+Provides-Extra: test
+Requires-Dist: biopython==1.85; extra == "test"
+Requires-Dist: coverage==7.7.0; extra == "test"
+Requires-Dist: dendropy==5.0.1; extra == "test"
+Requires-Dist: kastore==0.3.3; extra == "test"
+Requires-Dist: lshmm==0.0.8; extra == "test"
+Requires-Dist: msgpack==1.1.0; extra == "test"
+Requires-Dist: msprime==1.4.0b2; extra == "test"
+Requires-Dist: networkx==3.2.1; extra == "test"
+Requires-Dist: numba==0.63.1; extra == "test"
+Requires-Dist: portion==2.6.0; extra == "test"
+Requires-Dist: pytest==8.3.5; extra == "test"
+Requires-Dist: pytest-cov==6.0.0; extra == "test"
+Requires-Dist: pytest-xdist==3.6.1; extra == "test"
+Requires-Dist: tszip==0.2.5; extra == "test"
+Requires-Dist: xmlunittest==1.0.1; extra == "test"
+Requires-Dist: svgwrite==1.4.3; extra == "test"
+Requires-Dist: newick==1.10.0; extra == "test"
+Requires-Dist: zarr<3; extra == "test"
+Provides-Extra: docs
+Requires-Dist: jupyter-book==1.0.4.post1; extra == "docs"
+Requires-Dist: breathe==4.35.0; extra == "docs"
+Requires-Dist: sphinx-autodoc-typehints==2.3.0; extra == "docs"
+Requires-Dist: sphinx-issues==5.0.0; extra == "docs"
+Requires-Dist: sphinx-argparse==0.5.2; extra == "docs"
+Requires-Dist: msprime==1.4.0b2; extra == "docs"
+Requires-Dist: numba==0.63.1; extra == "docs"
+Requires-Dist: sphinx-book-theme; extra == "docs"
+Requires-Dist: pandas==2.2.3; extra == "docs"
+Provides-Extra: dev
+Requires-Dist: biopython>=1.70; extra == "dev"
+Requires-Dist: coverage; extra == "dev"
+Requires-Dist: dendropy; extra == "dev"
+Requires-Dist: flake8; extra == "dev"
+Requires-Dist: kastore; extra == "dev"
+Requires-Dist: lshmm; extra == "dev"
+Requires-Dist: msgpack; extra == "dev"
+Requires-Dist: msprime; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: networkx; extra == "dev"
+Requires-Dist: numba; extra == "dev"
+Requires-Dist: portion; extra == "dev"
+Requires-Dist: pre-commit; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: pytest-xdist; extra == "dev"
+Requires-Dist: setuptools_scm; extra == "dev"
+Requires-Dist: svgwrite; extra == "dev"
+Requires-Dist: tszip; extra == "dev"
+Requires-Dist: xmlunittest; extra == "dev"
+Requires-Dist: newick; extra == "dev"
+Requires-Dist: zarr<3; extra == "dev"
+Requires-Dist: jupyter-book<2; extra == "dev"
+Requires-Dist: breathe; extra == "dev"
+Requires-Dist: sphinx-autodoc-typehints; extra == "dev"
+Requires-Dist: sphinx-issues; extra == "dev"
+Requires-Dist: sphinx-argparse; extra == "dev"
+Requires-Dist: sphinx-book-theme; extra == "dev"
+Requires-Dist: pandas; extra == "dev"
+Dynamic: license-file
+
+
+The tree sequence toolkit.
+
+Tskit is a cross-platform library for the storage and analysis of large-scale
+genetic genealogy and variation data.
+Please see the `documentation <https://tskit.dev/tskit/docs/stable/>`_
+for further details.
+
+Tskit is highly portable, and provides a number of
+`installation options <https://tskit.dev/tskit/docs/stable/installation.html>`_.

tskit-1.0.1.dist-info/RECORD

@@ -0,0 +1,27 @@
+_tskit.cpython-314-darwin.so,sha256=mlmsekrnU9N0F-gfudwc_zpYnWCmoi-Aj0jtybBsthU,1466160
+tskit/__init__.py,sha256=bGaMlZ4MkZYgtZVkgbICh8D7Xi0Z2bk8NttnqS8bOKY,3220
+tskit/__main__.py,sha256=T98e67vxj_8C_O83DgZpq9Ln5Dp12xCKwWgatn43FR4,67
+tskit/_version.py,sha256=n8oAMlxCefvQC8EK_h0SQbULPyinNZeCexLSvo1GGVI,142
+tskit/cli.py,sha256=J2jr6Q-Qe8CT4km4fcErwsnK9I3MCDLb_6H8xeahXFU,8756
+tskit/combinatorics.py,sha256=HDIz34Myk-kA4HwNWD-WNwIS2kf5iHsTV2zIXl19FS0,55875
+tskit/drawing.py,sha256=pWeL7bxfsTi08yHb-X1NNIHfVeDVJsVAF4hr-5NwOp4,111256
+tskit/exceptions.py,sha256=ZC9Hvvi1Nv8EBK03erKowqPrXaxIkp14C2Su6V12K9s,2392
+tskit/genotypes.py,sha256=36BUGbAN7Da5gtOlAwxTshT9ZHIWoTkX6MOmKfOhRWw,17859
+tskit/intervals.py,sha256=YcgBP8tPhMYd1eQVjzZ_5fhIpF7SuPEGFLhS9NHJIho,23931
+tskit/metadata.py,sha256=wR4UgmsXPRPcWQ1gwZgQBzzmb2WVgY_d1dkACLNSuuU,41974
+tskit/provenance.py,sha256=jccUxhCozBPaCXX7zMcKIQON-zugGSbghuyH1vgChTM,4963
+tskit/provenance.schema.json,sha256=JJE6_KkaEWYmxYZ0ylgJYtdwMv8E5F5C644_veRcMZk,2117
+tskit/stats.py,sha256=Wy6k4XlthyDsZY9KBe9esmXGXkXmT1MvaTq6-EAao2w,7078
+tskit/tables.py,sha256=FJc-kbFCFGNdL0ApTcz-CfoMwg7ldZc-TW-f3yf87GQ,195817
+tskit/text_formats.py,sha256=DdnxGO-UBKKE0w_gtoxjWsmboqiwEySoyUxgBCpWh5E,14972
+tskit/trees.py,sha256=S6eXCHJ0jUAadWvdf0WWhy6MARUjOrP07Bemavl-qZ8,501364
+tskit/util.py,sha256=8K6l1EgDgLB-fHdsS6oztAGvkitynidA9kifcI9rCiE,35497
+tskit/vcf.py,sha256=HvUmSeHlF9DCTicD87tmaUmImNy4GLAAvwAz7ORpsj8,8595
+tskit/jit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tskit/jit/numba.py,sha256=ElOZyipEgQW8GJ9On8xTBMwB9i6uKzevqvs0aJK5e_U,24779
+tskit-1.0.1.dist-info/licenses/LICENSE,sha256=v9lcVGkQC5dVVV4SBBLsa9shqr22IXDbRedRoo9v1IA,1078
+tskit-1.0.1.dist-info/METADATA,sha256=Y3WaZfZKkC_eNH_eXEZZwsPe3oWiqittekuJOEoF3PA,4555
+tskit-1.0.1.dist-info/WHEEL,sha256=pBq69egh5x97PWc2-uzeinGu5GE3fGCM9h7i8BZE5wo,116
+tskit-1.0.1.dist-info/entry_points.txt,sha256=3Zik1X8C9Io1WvmTRBao5yEG5Kwy_xhFdM-ABC9TkWQ,47
+tskit-1.0.1.dist-info/top_level.txt,sha256=6GsXJYqSCR5Uhb4Js0BBzC0EFXE0FA5ywslsixSbwGM,13
+tskit-1.0.1.dist-info/RECORD,,

tskit-1.0.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.10.2)
+Root-Is-Purelib: false
+Tag: cp314-cp314-macosx_10_15_universal2
+

tskit-1.0.1.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+tskit = tskit.cli:tskit_main

tskit-1.0.1.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2018-2019 Tskit Developers
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

tskit-1.0.1.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+_tskit
+tskit