Merge pull request #41 from samuell/add-github-actions-workflow

Add GitHub Actions workflow

.github/workflows/python-tests.yml

@@ -0,0 +1,41 @@
+name: Python Package using Conda
+
+on: [push, pull_request]
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-20.04
+    strategy:
+      max-parallel: 5
+    defaults:
+      run:
+        shell: bash -l {0}
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.6.15
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.6.15'
+    - name: Create conda/mamba environment using micromamba
+      uses: mamba-org/setup-micromamba@v1
+      with:
+        environment-file: environment.yml
+        cache-downloads: true
+    - name: Add micromamba to system path                                                                                                                                                                                                                         
+      run: |                                                                                                                                                                                                                                                 
+        # $CONDA is an environment variable pointing to the root of the miniconda directory                                                                                                                                                                  
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Set EMU_DATABASE env variable
+      run: echo "EMU_DATABASE_DIR=./emu_database" >> $GITHUB_ENV
+    - name: Lint with flake8
+      run: |
+        micromamba install flake8
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        micromamba install pytest
+        pytest

README.md

@@ -1,5 +1,6 @@
 ## Emu: species-level taxonomic abundance for full-length 16S reads
 
+[![Tests](https://github.com/treangenlab/emu/actions/workflows/python-tests.yml/badge.svg)](https://github.com/treangenlab/emu/actions/workflows/python-tests.yml)
 
 ### Description
 

environment.yml

@@ -1,8 +1,9 @@
 name: custom-emu
 
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 
 dependencies:
   - biopython

tests/test_emu.py

@@ -0,0 +1,6 @@
+def test_placeholder():
+    """
+    Add an empty test so as not to fail the pytest process until some real
+    tests have been added.
+    """
+    assert True

tests/test_emu_cli.py

@@ -0,0 +1,54 @@
+import pytest
+import subprocess
+import os
+import pandas as pd
+import tempfile
+
+
+@pytest.mark.parametrize(
+    "emu_command_tpl, abundance_filepath_tpl, expected_abundancies",
+    [
+        (
+            "./emu abundance --db emu_database --output-dir {tempdir_path} --keep-files example/full_length.fa",
+            "{tempdir_path}/full_length_rel-abundance.tsv",
+            {
+                "Sphingobacterium puteale": 0.5,
+                "Mycobacterium saskatchewanense": 0.25,
+                "Streptococcus sobrinus": 0.25,
+            },
+        ),
+        (
+            "./emu abundance --db emu_database --output-dir {tempdir_path} --type sr --keep-files example/short_read_f.fq",
+            "{tempdir_path}/short_read_f_rel-abundance.tsv",
+            {
+                "Staphylococcus hominis": 1.0,
+            },
+        ),
+        (
+            "./emu abundance --db emu_database --output-dir {tempdir_path} --type sr --keep-files example/short_read_f.fq example/short_read_r.fq",
+            "{tempdir_path}/short_read_f-short_read_r_rel-abundance.tsv",
+            {
+                "Staphylococcus aureus": 1.0 / 3,
+                "Salmonella enterica": 1.0 / 3,
+                "Enterococcus columbae": 1.0 / 3,
+            },
+        ),
+    ],
+)
+def test_cli_on_example_datasets(emu_command_tpl, abundance_filepath_tpl, expected_abundancies):
+    tempdir = tempfile.TemporaryDirectory()
+
+    emu_command = emu_command_tpl.format(tempdir_path=tempdir.name)
+    abundance_filepath = abundance_filepath_tpl.format(tempdir_path=tempdir.name)
+
+    if os.path.exists(abundance_filepath):
+        os.remove(abundance_filepath)
+
+    subprocess.check_output(emu_command, shell=True)
+
+    assert os.path.exists(abundance_filepath)
+
+    df = abundance_df = pd.read_csv(abundance_filepath, sep="\t")
+
+    for species, expected_abundance in expected_abundancies.items():
+        assert df[df["species"] == species].iloc[0]["abundance"] == expected_abundance