Exclude Test Scripts and Data from PyPI Release (#148)

* move tests to dir and rewrite paths

* add python 3.7 test run support

* add importlib_resources to appveyor

* format files with 79 line length

* run tests from root dir in workflow

* docs: update changelog

---------

Co-authored-by: Arian Jamasb <[email protected]>

Author: Irlirion

.appveyor.yml

@@ -14,7 +14,7 @@ install:
   - conda config --set always_yes yes --set changeps1 no
   - conda update -q conda
   - conda info -a
-  - conda create -q -n test-environment --channel=conda-forge mmtf-python numpy scipy pandas pytest looseversion python=%PYTHON_VERSION%
+  - conda create -q -n test-environment --channel=conda-forge mmtf-python numpy scipy pandas pytest looseversion importlib_resources python=%PYTHON_VERSION%
   - activate test-environment
 
 test_script:

.github/workflows/publish.yaml

@@ -5,50 +5,50 @@ name: Publish BioPandas to PyPI / GitHub
 
 on:
   pull_request:
-    branches: [ main ]
+    branches: [main]
 
 jobs:
   test-style:
     name: Run style tests
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
 
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.x'
-        cache: 'pip'
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.x"
+          cache: "pip"
 
-    - name: Install package dependencies for testing
-      run: pip install .[test]
+      - name: Install package dependencies for testing
+        run: pip install .[test]
 
-    - name: Run all the pytest tests
-      run: flake8 ./biopandas
+      - name: Run all the pytest tests
+        run: flake8 ./biopandas
 
   test-pytest:
     name: Run pytest tests
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
 
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.x'
-        cache: 'pip'
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.x"
+          cache: "pip"
 
-    - name: Install package dependencies for testing
-      run: pip install .[test]
+      - name: Install package dependencies for testing
+        run: pip install .[test]
 
-    - name: Run all the pytest tests
-      run: pytest ./biopandas -sv
+      - name: Run all the pytest tests
+        run: pytest -sv
 
   build-n-publish:
     needs: [test-pytest] # only runs if tests are passing
-    if: startsWith(github.ref, 'refs/tags/v')  # Check if the tag starts with 'v'
+    if: startsWith(github.ref, 'refs/tags/v') # Check if the tag starts with 'v'
     name: Build and publish to PyPI
     runs-on: ubuntu-latest
 

docs/CHANGELOG.md

@@ -8,6 +8,7 @@ The CHANGELOG for the current development version is available at
 
 - Feature: added method to `PandasMmcif` that allow to select by model ids. PR #[145](https://github.com/BioPandas/biopandas/pull/145))
 - Dev: switched testing framework entirely to pytest. Drops nose dependency due to version conflicts with Python 3.12 (`nose`) and 3.8 (`nose`) PR #[146](https://github.com/BioPandas/biopandas/pull/146))
+-  Avoid inclusion of test scripts and test data in the PyPI release of the Biopandas library. PR #[148](https://github.com/BioPandas/biopandas/pull/148). Addresses issue [#147](https://github.com/BioPandas/biopandas/issues/147)
 
 
 ### 0.5.0dev1 (31/7/2023)

biopandas/mmcif/tests/__init__.py tests/__init__.py

@@ -4,14 +4,23 @@
 # Project Website: http://rasbt.github.io/biopandas/
 # Code Repository: https://github.com/rasbt/biopandas
 
-import os
+import sys
+
+if sys.version_info >= (3, 9):
+    import importlib.resources as pkg_resources
+else:
+    import importlib_resources as pkg_resources
 
 import numpy as np
+
+import tests.mmcif.data
 from biopandas.mmcif import PandasMmcif
 
+TEST_DATA = pkg_resources.files(tests.mmcif.data)
+
 
 def test_defaults():
-    TESTDATA_1t48 = os.path.join(os.path.dirname(__file__), "data", "1t48.cif")
+    TESTDATA_1t48 = str(TEST_DATA.joinpath("1t48.cif"))
     p1t48 = PandasMmcif()
     p1t48.read_mmcif(TESTDATA_1t48)
     expect_res = [
@@ -309,7 +318,7 @@ def test_defaults():
 
 
 def test_sameindex():
-    TESTDATA_1t48 = os.path.join(os.path.dirname(__file__), "data", "1t48.cif")
+    TESTDATA_1t48 = str(TEST_DATA.joinpath("1t48.cif"))
     p1t48 = PandasMmcif()
     p1t48.read_mmcif(TESTDATA_1t48)
     p1t48.df["ATOM"].index = np.zeros(p1t48.df["ATOM"].shape[0], dtype=int)
@@ -608,9 +617,7 @@ def test_sameindex():
 
 
 def test_multichain():
-    TESTDATA_5mtn = os.path.join(
-        os.path.dirname(__file__), "data", "5mtn_multichain.cif"
-    )
+    TESTDATA_5mtn = str(TEST_DATA.joinpath("5mtn_multichain.cif"))
     mtn = PandasMmcif()
     mtn.read_mmcif(TESTDATA_5mtn)
     expect_res_a = [
@@ -818,7 +825,7 @@ def test_multichain():
 
 
 def test_pdb_with_insertion_codes():
-    PDB_2D7T_PATH = os.path.join(os.path.dirname(__file__), "data", "2d7t.cif")
+    PDB_2D7T_PATH = str(TEST_DATA.joinpath("2d7t.cif"))
 
     ppdb = PandasMmcif().read_mmcif(PDB_2D7T_PATH)
     sequence = ppdb.amino3to1()

biopandas/mmtf/tests/__init__.py tests/mmcif/__init__.py

@@ -4,16 +4,22 @@
 # Project Website: http://rasbt.github.io/biopandas/
 # Code Repository: https://github.com/rasbt/biopandas
 
-import os
+import sys
 
+if sys.version_info >= (3, 9):
+    import importlib.resources as pkg_resources
+else:
+    import importlib_resources as pkg_resources
+
+import tests.mmcif.data
 from biopandas.mmcif import PandasMmcif
-from biopandas.testutils import assert_raises
+from tests.testutils import assert_raises
 
-TESTDATA_FILENAME = os.path.join(os.path.dirname(__file__), "data", "3eiy.cif")
+TEST_DATA = pkg_resources.files(tests.mmcif.data)
 
 
 def test_overwrite_df():
-    data_path = os.path.join(os.path.dirname(__file__), "data", "3eiy.cif")
+    data_path = str(TEST_DATA.joinpath("3eiy.cif"))
     pdb = PandasMmcif().read_mmcif(data_path)
 
     def overwrite():

biopandas/mmcif/tests/data/1ehz.cif tests/mmcif/data/1ehz.cif

@@ -4,14 +4,23 @@
 # Project Website: http://rasbt.github.io/biopandas/
 # Code Repository: https://github.com/rasbt/biopandas
 
-import os
+import sys
+
+if sys.version_info >= (3, 9):
+    import importlib.resources as pkg_resources
+else:
+    import importlib_resources as pkg_resources
 
 import pandas as pd
+
+import tests.mmcif.data
 from biopandas.mmcif import PandasMmcif
 
+TEST_DATA = pkg_resources.files(tests.mmcif.data)
+
 
 def test_equal():
-    TESTDATA_1t48 = os.path.join(os.path.dirname(__file__), "data", "1t48.cif")
+    TESTDATA_1t48 = str(TEST_DATA.joinpath("1t48.cif"))
 
     p1t48 = PandasMmcif()
     p1t48.read_mmcif(TESTDATA_1t48)
@@ -25,7 +34,7 @@ def test_equal():
 
 
 def test_deprecated_str_arg():
-    TESTDATA_1t48 = os.path.join(os.path.dirname(__file__), "data", "1t48.cif")
+    TESTDATA_1t48 = str(TEST_DATA.joinpath("1t48.cif"))
 
     p1t48 = PandasMmcif()
     p1t48.read_mmcif(TESTDATA_1t48)
@@ -39,7 +48,7 @@ def test_deprecated_str_arg():
 
 
 def test_use_external_df():
-    TESTDATA_1t48 = os.path.join(os.path.dirname(__file__), "data", "1t48.cif")
+    TESTDATA_1t48 = str(TEST_DATA.joinpath("1t48.cif"))
 
     p1t48 = PandasMmcif()
     p1t48.read_mmcif(TESTDATA_1t48)

biopandas/mmcif/tests/data/1t48.cif tests/mmcif/data/1t48.cif

@@ -4,27 +4,43 @@
 # License: BSD 3 clause
 # Project Website: http://rasbt.github.io/biopandas/
 # Code Repository: https://github.com/rasbt/biopandas
-import os
+import sys
 
+if sys.version_info >= (3, 9):
+    import importlib.resources as pkg_resources
+else:
+    import importlib_resources as pkg_resources
+
+import tests.mmcif.data
 from biopandas.mmcif import PandasMmcif
 
-TESTDATA_FILENAME = os.path.join(os.path.dirname(__file__), "data", "2jyf.cif.gz")
+TEST_DATA = pkg_resources.files(tests.mmcif.data)
+
+TESTDATA_FILENAME = str(TEST_DATA.joinpath("2jyf.cif.gz"))
+
 
 def test_label_models():
     biopandas_structure = PandasMmcif().read_mmcif(TESTDATA_FILENAME)
     biopandas_structure.label_models()
     assert "model_id" in biopandas_structure.df["ATOM"].columns
 
+
 def test_get_model():
     biopandas_structure = PandasMmcif().read_mmcif(TESTDATA_FILENAME)
     MODEL_INDEX = 1
     new_biopandas_structure = biopandas_structure.get_model(MODEL_INDEX)
-    assert new_biopandas_structure.df["ATOM"]["pdbx_PDB_model_num"].all() == MODEL_INDEX
+    assert (
+        new_biopandas_structure.df["ATOM"]["pdbx_PDB_model_num"].all()
+        == MODEL_INDEX
+    )
 
 
 def test_get_models():
     biopandas_structure = PandasMmcif().read_mmcif(TESTDATA_FILENAME)
     MODEL_INDICES = [1, 3, 5]
 
     new_biopandas_structure = biopandas_structure.get_models(MODEL_INDICES)
-    assert new_biopandas_structure.df["ATOM"]["pdbx_PDB_model_num"].all() in MODEL_INDICES
+    assert (
+        new_biopandas_structure.df["ATOM"]["pdbx_PDB_model_num"].all()
+        in MODEL_INDICES
+    )

biopandas/mmcif/tests/data/1t49.cif tests/mmcif/data/1t49.cif

@@ -5,36 +5,35 @@
 # Code Repository: https://github.com/rasbt/biopandas
 
 
-import os
+import sys
+
+if sys.version_info >= (3, 9):
+    import importlib.resources as pkg_resources
+else:
+    import importlib_resources as pkg_resources
 from pathlib import Path
 from urllib.error import HTTPError
 
 import pandas as pd
 import pytest
+from pandas.testing import assert_frame_equal
+
+import tests.mmcif.data
 from biopandas.mmcif import PandasMmcif
 from biopandas.pdb import PandasPdb
-from biopandas.testutils import assert_raises
-from pandas.testing import assert_frame_equal
+from tests.testutils import assert_raises
+
+TEST_DATA = pkg_resources.files(tests.mmcif.data)
 
-TESTDATA_FILENAME = os.path.join(os.path.dirname(__file__), "data", "3eiy.cif")
+TESTDATA_FILENAME = str(TEST_DATA.joinpath("3eiy.cif"))
 
 # Not clear on how ANISOU records are handled in mmCIF files so skipping
-# TESTDATA_FILENAME2 = os.path.join(
-#    os.path.dirname(__file__), "data", "4eiy_anisouchunk.cif"
-# )
-TESTDATA_FILENAME2 = os.path.join(
-    os.path.dirname(__file__), "data", "4eiy.cif"
-)
-TESTDATA_FILENAME_GZ = os.path.join(
-    os.path.dirname(__file__), "data", "3eiy.cif.gz"
-)
-
-TESTDATA_FILENAME_AF2_V4 = os.path.join(
-    os.path.dirname(__file__), "data", "AF-Q5VSL9-F1-model_v4.cif"
-)
-TESTDATA_FILENAME_AF2_V3 = os.path.join(
-    os.path.dirname(__file__), "data", "AF-Q5VSL9-F1-model_v3.cif"
-)
+# TESTDATA_FILENAME2 = str(TEST_DATA.joinpath("4eiy_anisouchunk.cif"))
+TESTDATA_FILENAME2 = str(TEST_DATA.joinpath("4eiy.cif"))
+TESTDATA_FILENAME_GZ = str(TEST_DATA.joinpath("3eiy.cif.gz"))
+
+TESTDATA_FILENAME_AF2_V4 = str(TEST_DATA.joinpath("AF-Q5VSL9-F1-model_v4.cif"))
+TESTDATA_FILENAME_AF2_V3 = str(TEST_DATA.joinpath("AF-Q5VSL9-F1-model_v3.cif"))
 
 ATOM_DF_COLUMNS = [
     "B_iso_or_equiv",

biopandas/mmcif/tests/data/2d7t.cif tests/mmcif/data/2d7t.cif

@@ -4,17 +4,26 @@
 # Project Website: http://rasbt.github.io/biopandas/
 # Code Repository: https://github.com/rasbt/biopandas
 
-import os
+import sys
+
+if sys.version_info >= (3, 9):
+    import importlib.resources as pkg_resources
+else:
+    import importlib_resources as pkg_resources
 
 import pytest
+
+import tests.mmcif.data
 from biopandas.mmcif import PandasMmcif
 
-TESTDATA_1t48 = os.path.join(os.path.dirname(__file__), "data", "1t48.cif")
-TESTDATA_1t49 = os.path.join(os.path.dirname(__file__), "data", "1t49.cif")
-# TESTDATA_lig1 = os.path.join(os.path.dirname(__file__), "data", "lig_conf_1.pdb")
-# TESTDATA_lig2 = os.path.join(os.path.dirname(__file__), "data", "lig_conf_2.pdb")
+TEST_DATA = pkg_resources.files(tests.mmcif.data)
+
+TESTDATA_1t48 = str(TEST_DATA.joinpath("1t48.cif"))
+TESTDATA_1t49 = str(TEST_DATA.joinpath("1t49.cif"))
+# TESTDATA_lig1 = str(TEST_DATA.joinpath("lig_conf_1.pdb"))
+# TESTDATA_lig2 = str(TEST_DATA.joinpath("lig_conf_2.pdb"))
 
-TESTDATA_rna = os.path.join(os.path.dirname(__file__), "data", "1ehz.cif")
+TESTDATA_rna = str(TEST_DATA.joinpath("1ehz.cif"))
 
 p1t48 = PandasMmcif()
 p1t48.read_mmcif(TESTDATA_1t48)