Merge pull request #3 from xin-huang/dev

Add CI

.coveragerc

@@ -0,0 +1,2 @@
+[report]
+omit = tests/*,setup.py,*__init__.py,*conftest.py

.github/workflows/build.yaml

@@ -0,0 +1,35 @@
+name: build
+
+on: [push, pull_request]
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10"]
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Add micromamba to system path
+      uses: mamba-org/setup-micromamba@v1
+      with:
+        environment-name: sai
+        environment-file: build-env.yaml
+    - name: Test with pytest
+      run: |
+        micromamba run -n sai pip install -e .
+        micromamba run -n sai pytest --cov=. --cov-report term-missing -vv
+        micromamba run -n sai coverage xml
+    - name: upload coverage report to codecov
+      uses: codecov/codecov-action@v4
+      with:
+          name: codecov-umbrella
+          fail_ci_if_error: true
+          env_vars: OS,PYTHON
+          token: ${{ secrets.CODECOV_TOKEN }}

README.md

@@ -1 +1,10 @@
-# sai
+# SAI
+
+[![license](https://img.shields.io/badge/license-GPL%20v3-black.svg?style=flat-square)](LICENSE) 
+[![language](http://img.shields.io/badge/language-Python-blue.svg?style=flat-square)](https://www.python.org/) 
+[![build status](https://img.shields.io/github/actions/workflow/status/xin-huang/sai/build.yaml?branch=main&style=flat-square)](https://github.com/xin-huang/sai/actions)
+[![codecov](https://img.shields.io/codecov/c/github/xin-huang/sai)](https://app.codecov.io/gh/xin-huang/sai)
+
+A Python Package for **S**tatistics for **A**daptive **I**ntrogression
+
+The manual can be found [here](https://xin-huang.github.io/sai).

build-env.yaml

@@ -8,5 +8,6 @@ dependencies:
   - pip=24.0
   - python=3.9.19
   - pytest=8.1.1
+  - pytest-cov=6.0.0
   - scikit-allel=1.3.7
   - scipy=1.12.0

dev-env.yaml

@@ -10,5 +10,6 @@ dependencies:
   - pip=24.0
   - python=3.9.19
   - pytest=8.1.1
+  - pytest-cov=6.0.0
   - scikit-allel=1.3.7
   - scipy=1.12.0

tests/data/example.ref.ind.list

@@ -0,0 +1,5 @@
+AFR	ind1
+AFR	ind2
+AFR	ind3
+AFR	ind4
+AFR	ind5

tests/data/example.scores

@@ -0,0 +1,2 @@
+Chrom	Start	End	Ref	Tgt	Src	U	Q95
+21	0	3333	AFR	CHB	Nean	3	0.9

tests/data/example.src.ind.list

@@ -0,0 +1 @@
+Nean	ind11

tests/data/example.tgt.ind.list

@@ -0,0 +1,5 @@
+CHB	ind6
+CHB	ind7
+CHB	ind8
+CHB	ind9
+CHB	ind10

tests/data/example.vcf

@@ -0,0 +1,19 @@
+##fileformat=VCFv4.1
+##FILTER=<ID=PASS,Description="All filters passed">
+##contig=<ID=21,assembly=b37,length=48129895>
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele. Format: AA|REF|ALT|IndelType. AA: Ancestral allele, REF:Reference Allele, ALT:Alternate Allele, IndelType:Type of Indel (REF, ALT and IndelType are only defined for indels)">
+##INFO=<ID=VT,Number=.,Type=String,Description="indicates what type of variant the line represents">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	ind1	ind2	ind3	ind4	ind5	ind6	ind7	ind8	ind9	ind10	ind11
+21	111	.	A	T	100	PASS	AA=A	GT	0|0	0|0	0|0	0|0	0|0	1|0	0|0	0|0	0|0	0|0	0|0
+21	222	.	A	T	100	PASS	AA=A	GT	0|0	0|0	1|1	0|0	0|0	0|1	1|1	1|1	1|1	1|1	1|1
+21	333	.	A	T	100	PASS	AA=A	GT	0|1	0|0	0|0	0|0	0|0	0|0	0|1	1|1	1|1	1|1	1|1
+21	444	.	A	T	100	PASS	AA=A	GT	0|0	0|0	0|0	0|0	0|0	0|1	1|1	1|1	1|1	1|1	0|0
+21	555	.	A	T	100	PASS	AA=A	GT	0|0	0|0	1|1	1|0	0|1	0|0	0|0	0|0	0|0	0|0	0|0
+21	666	.	A	T	100	PASS	AA=A	GT	0|0	0|0	0|0	0|0	0|0	1|0	0|0	0|0	0|0	0|0	0|0
+21	777	.	A	T	100	PASS	AA=A	GT	0|0	0|0	0|0	0|0	0|0	0|1	1|1	1|1	1|1	1|1	1|1
+21	888	.	A	T	100	PASS	AA=A	GT	0|0	0|0	0|0	0|0	0|0	0|0	0|0	0|0	0|0	0|1	1|1
+21	999	.	A	T	100	PASS	AA=A	GT	0|0	1|1	0|0	0|0	0|0	0|0	0|0	0|0	0|0	0|0	0|0
+21	1111	.	A	T	100	PASS	AA=A	GT	0|1	1|1	1|1	1|1	1|1	0|0	0|0	0|0	0|0	0|0	1|1
+21	2222	.	A	T	100	PASS	AA=A	GT	0|0	0|0	0|0	0|0	0|0	0|0	0|0	0|0	0|1	1|1	1|1
+21	3333	.	A	T	100	PASS	AA=A	GT	1|1	1|1	0|0	0|0	0|1	0|0	0|0	0|0	0|0	0|0	1|0

tests/parsers/test_argument_validation.py

@@ -0,0 +1,100 @@
+# Copyright 2024 Xin Huang
+#
+# GNU General Public License v3.0
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, please see
+#
+#    https://www.gnu.org/licenses/gpl-3.0.en.html
+
+
+import argparse
+import pytest
+import os
+from sai.parsers.argument_validation import positive_int
+from sai.parsers.argument_validation import positive_number
+from sai.parsers.argument_validation import between_zero_and_one
+from sai.parsers.argument_validation import existed_file
+
+
+def test_positive_int():
+    # Valid positive integer
+    assert positive_int("5") == 5
+
+    # Not a positive integer (zero)
+    with pytest.raises(argparse.ArgumentTypeError, match="0 is not a positive integer"):
+        positive_int("0")
+
+    # Negative integer
+    with pytest.raises(
+        argparse.ArgumentTypeError, match="-1 is not a positive integer"
+    ):
+        positive_int("-1")
+
+    # Non-integer string
+    with pytest.raises(argparse.ArgumentTypeError, match="abc is not a valid integer"):
+        positive_int("abc")
+
+
+def test_positive_number():
+    # Valid positive number
+    assert positive_number("3.14") == 3.14
+
+    # Not a positive number (zero)
+    with pytest.raises(argparse.ArgumentTypeError, match="0 is not a positive number"):
+        positive_number("0")
+
+    # Negative number
+    with pytest.raises(
+        argparse.ArgumentTypeError, match="-2.5 is not a positive number"
+    ):
+        positive_number("-2.5")
+
+    # Non-numeric string
+    with pytest.raises(argparse.ArgumentTypeError, match="xyz is not a valid number"):
+        positive_number("xyz")
+
+
+def test_between_zero_and_one():
+    # Values within range
+    assert between_zero_and_one("0.5") == 0.5
+    assert between_zero_and_one("0") == 0
+    assert between_zero_and_one("1") == 1
+
+    # Values out of range
+    with pytest.raises(argparse.ArgumentTypeError, match="1.5 is not between 0 and 1"):
+        between_zero_and_one("1.5")
+
+    with pytest.raises(argparse.ArgumentTypeError, match="-0.1 is not between 0 and 1"):
+        between_zero_and_one("-0.1")
+
+    # Non-numeric string
+    with pytest.raises(
+        argparse.ArgumentTypeError, match="not_a_number is not a valid number"
+    ):
+        between_zero_and_one("not_a_number")
+
+
+def test_existed_file(tmp_path):
+    # Create a temporary file for testing
+    temp_file = tmp_path / "temp.txt"
+    temp_file.write_text("This is a test file.")
+
+    # Validate an existing file path
+    assert existed_file(str(temp_file)) == str(temp_file)
+
+    # Validate a non-existent file path
+    with pytest.raises(
+        argparse.ArgumentTypeError, match="non_existent_file is not found"
+    ):
+        existed_file("non_existent_file")

tests/parsers/test_outlier_parser.py

@@ -0,0 +1,56 @@
+# Copyright 2024 Xin Huang
+#
+# GNU General Public License v3.0
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, please see
+#
+#    https://www.gnu.org/licenses/gpl-3.0.en.html
+
+
+import pytest
+import argparse
+from sai.parsers.outlier_parser import add_outlier_parser
+
+
+@pytest.fixture
+def parser():
+    # Initialize the argument parser with a subparser for the 'outlier' command
+    main_parser = argparse.ArgumentParser()
+    subparsers = main_parser.add_subparsers(dest="command")
+    add_outlier_parser(subparsers)
+    return main_parser
+
+
+def test_add_outlier_parser(parser):
+    # Simulate command-line arguments to parse
+    args = parser.parse_args(
+        [
+            "outlier",
+            "--score",
+            "tests/data/example.scores",
+            "--output-dir",
+            "output/",
+            "--output-prefix",
+            "test_outliers",
+            "--quantile",
+            "0.95",
+        ]
+    )
+
+    # Validate parsed arguments
+    assert args.command == "outlier"
+    assert args.score == "tests/data/example.scores"
+    assert args.output_dir == "output/"
+    assert args.output_prefix == "test_outliers"
+    assert args.quantile == 0.95

tests/parsers/test_score_parser.py

@@ -0,0 +1,95 @@
+# Copyright 2024 Xin Huang
+#
+# GNU General Public License v3.0
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, please see
+#
+#    https://www.gnu.org/licenses/gpl-3.0.en.html
+
+
+import pytest
+import argparse
+from sai.parsers.score_parser import add_score_parser
+
+
+@pytest.fixture
+def parser():
+    # Initialize the argument parser with a subparser for the 'score' command
+    main_parser = argparse.ArgumentParser()
+    subparsers = main_parser.add_subparsers(dest="command")
+    add_score_parser(subparsers)
+    return main_parser
+
+
+def test_add_score_parser(parser):
+    # Simulate command-line arguments to parse
+    args = parser.parse_args(
+        [
+            "score",
+            "--vcf",
+            "tests/data/example.vcf",
+            "--chr-name",
+            "chr1",
+            "--ref",
+            "tests/data/example.ref.ind.list",
+            "--tgt",
+            "tests/data/example.tgt.ind.list",
+            "--src",
+            "tests/data/example.src.ind.list",
+            "--win-len",
+            "50000",
+            "--win-step",
+            "10000",
+            "--num-src",
+            "2",
+            "--anc-allele-file",
+            "tests/data/test.anc.allele.bed",
+            "--ploidy",
+            "2",
+            "--phased",
+            "--w",
+            "0.3",
+            "--x",
+            "0.5",
+            "--y",
+            "0.1",
+            "0.2",
+            "--output",
+            "output/results.tsv",
+            "--q",
+            "0.95",
+            "--workers",
+            "4",
+        ]
+    )
+
+    # Validate parsed arguments
+    assert args.command == "score"
+    assert args.vcf == "tests/data/example.vcf"
+    assert args.chr_name == "chr1"
+    assert args.ref == "tests/data/example.ref.ind.list"
+    assert args.tgt == "tests/data/example.tgt.ind.list"
+    assert args.src == "tests/data/example.src.ind.list"
+    assert args.win_len == 50000
+    assert args.win_step == 10000
+    assert args.num_src == 2
+    assert args.anc_allele_file == "tests/data/test.anc.allele.bed"
+    assert args.ploidy == 2
+    assert args.is_phased is True
+    assert args.w == 0.3
+    assert args.x == 0.5
+    assert args.y == [0.1, 0.2]
+    assert args.output == "output/results.tsv"
+    assert args.q == 0.95
+    assert args.workers == 4

tests/test___main__.py

@@ -16,3 +16,37 @@
 # along with this program. If not, please see
 #
 #    https://www.gnu.org/licenses/gpl-3.0.en.html
+
+
+import pytest
+from unittest.mock import patch, MagicMock
+from sai.__main__ import main
+
+
+@patch("sai.__main__._sai_cli_parser")  # Mock _sai_cli_parser to control its output
+@patch(
+    "sai.__main__._set_sigpipe_handler"
+)  # Mock _set_sigpipe_handler as it doesn’t need testing
+def test_main(mock_set_sigpipe_handler, mock_sai_cli_parser):
+    # Mock parser and its return values
+    mock_parser = MagicMock()
+    mock_args = MagicMock()
+    mock_args.runner = MagicMock()
+
+    # Configure _sai_cli_parser to return the mock parser
+    mock_sai_cli_parser.return_value = mock_parser
+    # Configure the mock parser to return mock_args when parse_args is called
+    mock_parser.parse_args.return_value = mock_args
+
+    # Call the main function with a test argument list
+    test_args = ["score", "--vcf", "tests/data/example.vcf", "--chr-name", "chr1"]
+    main(test_args)
+
+    # Check if _set_sigpipe_handler was called
+    mock_set_sigpipe_handler.assert_called_once()
+
+    # Verify parse_args was called with test_args
+    mock_parser.parse_args.assert_called_once_with(test_args)
+
+    # Ensure runner was called with the parsed arguments
+    mock_args.runner.assert_called_once_with(mock_args)