Merge pull request #215 from qiyunzhu/toml

Upgrading Python packaging mechanism

.github/workflows/main.yml

@@ -16,8 +16,8 @@ jobs:
     strategy:
       max-parallel: 5
       matrix:
-        os: ['ubuntu']
-        python-version: ['3.8', '3.12']
+        os: ['ubuntu', 'macos', 'windows']
+        python-version: ['3.8', '3.10', '3.12']
 
     steps:
       - name: Check out repo
@@ -28,13 +28,10 @@ jobs:
         with:
           auto-update-conda: true
           python-version: ${{ matrix.python-version }}
-          channels: conda-forge
-
-      - name: Install dependencies
-        run: conda install --file ci/conda_requirements.txt 
+          environment-file: environment.yml
 
       - name: Install CI packages
-        run: conda install pycodestyle coverage
+        run: conda install -c conda-forge pycodestyle coverage
 
       - name: Install program
         run: pip install -e .
@@ -48,6 +45,7 @@ jobs:
           coverage run -m unittest && coverage lcov
 
       - name: Coveralls
+        if: ${{ matrix.os == 'ubuntu' && matrix.python-version == '3.12' }}
         uses: coverallsapp/github-action@v2
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}

CHANGELOG.md

@@ -4,10 +4,12 @@
 
 ### Added
 - Formally adopted the NumPy + Numba solution in the ordinal mapper. This significantly accelerated the algorithm ([#209](https://github.com/qiyunzhu/woltka/pull/209)).
+- Accelerated command-line interface loading ([#215](https://github.com/qiyunzhu/woltka/pull/215)).
 
 ### Changed
 - Changed default output subject coverage (`--outcov`) coordinates into BED-like (0-based, exclusive end). The output can be directly parsed by programs like bedtools. Also added support for GFF-like and other custom formats, as controled by paramter `--outcov-fmt` ([#204](https://github.com/qiyunzhu/woltka/pull/204) and [#205](https://github.com/qiyunzhu/woltka/pull/205)).
 - Default chunk size is now 1024 for plain and range mapeprs, and 2 ** 20 = 1048576 for ordinal mapper. The latter represents the number of valid query-subject pairs ([#209](https://github.com/qiyunzhu/woltka/pull/209)).
+- Updated packaging method ([#215](https://github.com/qiyunzhu/woltka/pull/215)).
 
 
 ## Version 0.1.6 (2/22/2024)

LICENSE

@@ -1,6 +1,6 @@
 BSD 3-Clause License
 
-Copyright (c) 2020, Qiyun Zhu
+Copyright (c) 2020--, Qiyun Zhu
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

doc/install.md

@@ -46,7 +46,7 @@ Option 4: Install from a local copy:
 Download this [repository](https://github.com/qiyunzhu/woltka/archive/main.zip) or any of the previous [releases](https://github.com/qiyunzhu/woltka/releases). Unzip and navigate to the package directory. Then execute:
 
 ```bash
-python setup.py install
+pip install .
 ```
 
 Type `woltka` to check if installation is successful, in which case command-line help information will be displayed on the screen.

environment.yml

@@ -0,0 +1,7 @@
+name: woltka
+channels:
+  - conda-forge
+dependencies:
+  - python >=3.6
+  - numba
+  - biom-format

pyproject.toml

@@ -0,0 +1,52 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "woltka"
+dynamic = ["version"]
+dependencies = [
+  "numba",
+  "biom-format",
+]
+requires-python = ">=3.6"
+authors = [
+  {name = "Qiyun Zhu", email = "qiyunzhu@gmail.com"}
+]
+maintainers = [
+  {name = "Qiyun Zhu", email = "qiyunzhu@gmail.com"}
+]
+description = "versatile meta-omic data classifier"
+readme = "README.md"
+license = {file = "LICENSE"}
+keywords = ["bioinformatics", "metagenomics", "microbiome"]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "License :: OSI Approved :: BSD License",
+  "Topic :: Scientific/Engineering",
+  "Topic :: Scientific/Engineering :: Bio-Informatics",
+  "Intended Audience :: Science/Research",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Operating System :: OS Independent",
+  "Operating System :: POSIX :: Linux",
+  "Operating System :: MacOS :: MacOS X",
+  "Operating System :: Microsoft :: Windows",
+]
+
+[project.urls]
+Homepage = "https://github.com/qiyunzhu/woltka"
+Documentation = "https://github.com/qiyunzhu/woltka/blob/main/README.md"
+Repository = "https://github.com/qiyunzhu/woltka.git"
+Issues = "https://github.com/qiyunzhu/woltka/issues"
+Changelog = "https://github.com/qiyunzhu/woltka/blob/main/CHANGELOG.md"
+
+[project.scripts]
+woltka = "woltka.cli:cli"
+
+[project.entry-points."qiime2.plugins"]
+q2-woltka = "woltka.q2.plugin_setup:plugin"
+
+[tool.hatch.version]
+path = "woltka/__init__.py"

woltka/cli.py

@@ -14,8 +14,6 @@
 import click
 
 from . import __version__
-from .workflow import workflow
-from .tools import normalize_wf, filter_wf, merge_wf, collapse_wf, coverage_wf
 
 
 class NaturalOrderGroup(click.Group):
@@ -197,6 +195,7 @@ def cli():
 def classify_cmd(**kwargs):
     """Main classification workflow: Alignments => profile(s).
     """
+    from .workflow import workflow
     workflow(**kwargs)
 
 
@@ -236,6 +235,7 @@ def classify_cmd(**kwargs):
 def collapse_cmd(**kwargs):
     """Collapse a profile by feature mapping and/or hierarchy.
     """
+    from .tools import collapse_wf
     collapse_wf(**kwargs)
 
 
@@ -263,6 +263,7 @@ def collapse_cmd(**kwargs):
 def normalize_cmd(**kwargs):
     """Normalize a profile to fractions and/or by feature sizes.
     """
+    from .tools import normalize_wf
     normalize_wf(**kwargs)
 
 
@@ -284,6 +285,7 @@ def normalize_cmd(**kwargs):
 def filter_cmd(**kwargs):
     """Filter a profile by per-sample abundance.
     """
+    from .tools import filter_wf
     filter_wf(**kwargs)
 
 
@@ -300,6 +302,7 @@ def filter_cmd(**kwargs):
 def merge_cmd(**kwargs):
     """Merge multiple profiles into one profile.
     """
+    from .tools import merge_wf
     merge_wf(**kwargs)
 
 
@@ -330,20 +333,9 @@ def merge_cmd(**kwargs):
 def coverage_cmd(**kwargs):
     """Calculate per-sample coverage of feature groups.
     """
+    from .tools import coverage_wf
     coverage_wf(**kwargs)
 
 
-# the "tools" menu is for backward compatibility
-@cli.group('tools', cls=NaturalOrderGroup)
-def tools():
-    """Entries to the same commands for backward compatibility (deprecated).
-    """
-    pass  # pragma: no cover
-
-
-for cmd in collapse_cmd, normalize_cmd, filter_cmd, merge_cmd, coverage_cmd:
-    tools.add_command(cmd)
-
-
 if __name__ == '__main__':
     cli()  # pragma: no cover

woltka/tests/test_biom.py

@@ -72,7 +72,8 @@ def test_table_to_biom(self):
             'G5\t0\t7\t5\t\t\t\n'),
             sep='\t', index_col=0, na_filter=False)
         assert_frame_equal(
-            obs.to_dataframe(dense=True).astype(int), exp.iloc[:, :3])
+            obs.to_dataframe(dense=True).astype(int),
+            exp.iloc[:, :3].astype(int))
         assert_frame_equal(
             obs.metadata_to_dataframe('observation')[[
                 'Name', 'Rank', 'Lineage']], exp.iloc[:, -3:])

woltka/tests/test_cli.py

@@ -81,12 +81,12 @@ def _test_params(params, exp):
         # check read maps
         for i in range(1, 6):
             outmap_fp = join(self.tmpdir, f'S0{i}.txt.gz')
-            with gzip.open(outmap_fp, 'r') as f:
-                obs = f.read()
+            with gzip.open(outmap_fp, 'rt') as f:
+                obs = [x.rstrip() for x in f.readlines()]
             with gzip.open(join(self.outdir, 'burst.genus.map',
-                                f'S0{i}.txt.gz'), 'r') as f:
-                exp = f.read()
-            self.assertEqual(obs, exp)
+                                f'S0{i}.txt.gz'), 'rt') as f:
+                exp = [x.rstrip() for x in f.readlines()]
+            self.assertListEqual(obs, exp)
             remove(outmap_fp)
 
         # blastn, family-level classification, report relative abundance (%)

woltka/tests/test_workflow.py

@@ -679,7 +679,7 @@ def test_write_profiles(self):
         write_profiles(data, fp, is_biom=True)
         obs = load_table(fp).to_dataframe(dense=True).astype(int)
         exp = pd.DataFrame([[1, 3], [2, 0], [0, 2]], index=['G1', 'G2', 'G3'],
-                           columns=['S1', 'S2'])
+                           columns=['S1', 'S2']).astype(int)
         assert_frame_equal(obs, exp)
 
         # multiple profiles in BIOM format (default)
@@ -695,7 +695,7 @@ def test_write_profiles(self):
         fp = join(self.tmpdir, 'free.biom')
         obs = load_table(fp).to_dataframe(dense=True).astype(int)
         exp = pd.DataFrame([[3, 1], [0, 2]], index=['Ecoli', 'Strep'],
-                           columns=['S1', 'S2'])
+                           columns=['S1', 'S2']).astype(int)
         assert_frame_equal(obs, exp)
         remove(fp)