Merge branch 'enhancement/pypi_integration' into 'dev'

Use only PyPI dependencies and make QSPRpred installable from it

Closes #42

See merge request cdd/QSPRpred!185

.github/workflows/docs_ci.yml

@@ -4,7 +4,8 @@ on:
   push:
     branches:
       - dev
-      - main
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+'
 
 env:
   CI_COMMIT_AUTHOR: ${{ github.event.head_commit.author.name }}

.github/workflows/pypi-test.yml

@@ -0,0 +1,55 @@
+name: Publish Python 🐍 distribution 📦 to TestPyPI
+
+on:
+  push:
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+.alpha[0-9]+'
+      - 'v[0-9]+.[0-9]+.[0-9]+.beta[0-9]+'
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.x"
+      - name: Install pypa/build
+        run: >-
+          python3 -m
+          pip install
+          build
+          --user
+      - name: Build a binary wheel and a source tarball
+        run: python3 -m build
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v3
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish-to-pypi-test:
+    name: >-
+      Publish Python 🐍 distribution 📦 to TestPyPI
+    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi-test # IMPORTANT: mandatory for trusted publishing
+      url: https://test.pypi.org/p/qsprpred  # Replace <package-name> with your PyPI project name
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v3
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Publish distribution 📦 to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/

.github/workflows/pypi.yml

@@ -0,0 +1,52 @@
+name: Publish Python 🐍 distribution 📦 to PyPI
+
+on:
+  push:
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.x"
+      - name: Install pypa/build
+        run: >-
+          python3 -m
+          pip install
+          build
+          --user
+      - name: Build a binary wheel and a source tarball
+        run: python3 -m build
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v3
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish-to-pypi:
+    name: >-
+      Publish Python 🐍 distribution 📦 to PyPI
+    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi # IMPORTANT: mandatory for trusted publishing
+      url: https://pypi.org/p/qsprpred  # Replace <package-name> with your PyPI project name
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v3
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Publish distribution 📦 to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

.gitlab-ci.yml

@@ -19,11 +19,13 @@ stages:
     - export MAFFT_BINARIES=$PWD/mafft-linux64/mafftdir/libexec/
     - clustalo --version  # For debugging clustalo version
     - mafft --version  # For debugging mafft version
-    - pip install ".[full]" --no-cache-dir
+    #    - pip config set global.index-url https://pypi.org/simple/
+    #    - pip config set global.extra-index-url https://test.pypi.org/simple/
+    - python -m pip install ".[full]" --no-cache-dir
     - python -c "import qsprpred; print(qsprpred.__version__)" # For debugging package version
-    - pip install pytest
-    - pip install jupyterlab
-    - pip freeze # For debugging environment
+    - python -m pip install pytest
+    - python -m pip install jupyterlab
+    - python -m pip freeze # For debugging environment
   script:
     - cd testing && QSPPRED_TEST_SPLIT_UNITS=true QSPRPRED_VERBOSE_LOGGING=true ./run.sh
 

CHANGELOG.md

@@ -17,6 +17,13 @@ From v3.0.1 to v3.0.2
 
 ## Changes
 
+
+- Restrictions on `numpy` versions were removed to allow for more flexibility in
+  package installations. However, the `BorutaFilter` feature selection method does not
+  function with `numpy` versions 1.24.0 and above. Therefore, this functionality now
+  requires a downgrade to `numpy` version 1.23.0 or lower. This was reflected in the
+  documentation and `numpy` itself outputs a reasonable error message if the version is
+  incompatible.
 - Data type in `MlChemADWrapper` is now set to `float64` by default, instead of `float32`.
 
 ## New Features
@@ -25,6 +32,7 @@ From v3.0.1 to v3.0.2
   custom descriptor sets.
 - Added the `prepMols` method to `DescriptorSet` to allow separated customization of
   molecule preparation before descriptor calculation.
+- The package can now be installed from the PyPI repository 🐍📦.
 
 ## Removed Features
 

README.md

@@ -1,6 +1,8 @@
-[**Main**](https://github.com/CDDLeiden/QSPRpred/) [![Build and Deploy Documentation](https://github.com/CDDLeiden/QSPRpred/actions/workflows/docs_ci.yml/badge.svg?branch=main)](https://github.com/CDDLeiden/QSPRpred/actions/workflows/docs_ci.yml)[![Multi-OS Complete Test](https://github.com/CDDLeiden/QSPRpred/actions/workflows/dev_ci.yml/badge.svg?branch=main)](https://github.com/CDDLeiden/QSPRpred/actions/workflows/dev_ci.yml)
+[**Main
+**](https://github.com/CDDLeiden/QSPRpred/) [![Build and Deploy Documentation](https://github.com/CDDLeiden/QSPRpred/actions/workflows/docs_ci.yml/badge.svg?branch=main)](https://github.com/CDDLeiden/QSPRpred/actions/workflows/docs_ci.yml)[![Multi-OS Complete Test](https://github.com/CDDLeiden/QSPRpred/actions/workflows/dev_ci.yml/badge.svg?branch=main)](https://github.com/CDDLeiden/QSPRpred/actions/workflows/dev_ci.yml)
 
-[**Dev**](https://github.com/CDDLeiden/QSPRpred/tree/dev) [![Build and Deploy Documentation](https://github.com/CDDLeiden/QSPRpred/actions/workflows/docs_ci.yml/badge.svg?branch=dev)](https://github.com/CDDLeiden/QSPRpred/actions/workflows/docs_ci.yml)[![Multi-OS Complete Test](https://github.com/CDDLeiden/QSPRpred/actions/workflows/dev_ci.yml/badge.svg?branch=dev)](https://github.com/CDDLeiden/QSPRpred/actions/workflows/dev_ci.yml)
+[**Dev
+**](https://github.com/CDDLeiden/QSPRpred/tree/dev) [![Build and Deploy Documentation](https://github.com/CDDLeiden/QSPRpred/actions/workflows/docs_ci.yml/badge.svg?branch=dev)](https://github.com/CDDLeiden/QSPRpred/actions/workflows/docs_ci.yml)[![Multi-OS Complete Test](https://github.com/CDDLeiden/QSPRpred/actions/workflows/dev_ci.yml/badge.svg?branch=dev)](https://github.com/CDDLeiden/QSPRpred/actions/workflows/dev_ci.yml)
 
 QSPRpred
 ====================
@@ -42,15 +44,15 @@ Quick Start
 QSPRpred can be installed with pip like so (with python >= 3.10):
 
 ```bash
-pip install git+https://github.com/CDDLeiden/QSPRpred.git@main
+pip install qsprpred
 ```
 
 Note that this will install the basic dependencies, but not the optional dependencies.
 If you want to use the optional dependencies, you can install the package with an
 option:
 
 ```bash
-pip install git+https://github.com/CDDLeiden/QSPRpred.git@main#egg=qsprpred[<option>]
+pip install qsprpred[<option>]
 ```
 
 The following options are available:
@@ -66,7 +68,7 @@ The following options are available:
 
 ### Note on PCM Modelling
 
-If you plan to optionally use QSPRPred to calculate protein descriptors for PCM, make
+If you plan to optionally use QSPRpred to calculate protein descriptors for PCM, make
 sure to also install Clustal Omega. You can get it via `conda` (**for Linux and MacOS
 only**):
 

docs/features.rst

@@ -118,7 +118,7 @@ Overview of available features
 
                 * :class:`~qsprpred.data.processing.feature_filters.HighCorrelationFilter`: HighCorrelationFilter
                 * :class:`~qsprpred.data.processing.feature_filters.LowVarianceFilter`: LowVarianceFilter
-                * :class:`~qsprpred.data.processing.feature_filters.BorutaFilter`: BorutaFilter
+                * :class:`~qsprpred.data.processing.feature_filters.BorutaFilter`: BorutaFilter (:code:`numpy` version restricted to :code:`numpy<1.24.0`)
 
     .. dropdown:: Models
 

docs/install.rst

@@ -7,7 +7,7 @@ You do not need anything special to install the package . Just run the following
 
 ..  code-block::
 
-    pip install git+https://github.com/CDDLeiden/QSPRpred.git@main
+    pip install qsprpred
 
 You can also get tags and development snapshots by varying the :code:`@main` part (i.e. :code:`@1.0.0`). After that you can start building models (see :ref:`cli-usage`).
 
@@ -17,7 +17,7 @@ option:
 
 ..  code-block::
     
-    pip install git+https://github.com/CDDLeiden/QSPRpred.git@main#egg=qsprpred[<option>]
+    pip install qsprpred[<option>]
 
 The following options are available:
 
@@ -32,6 +32,13 @@ The following options are available:
 
 You can test the installation by running the unit test suite:
 
-..  code-block::
+..  code-block:: bash
+
+    python -m unittest discover qsprpred
+
+Note that this can potentially take a long time and some tests may require you to have
+additional dependencies installed. However, you can also test each module separately:
+
+..  code-block:: bash
 
-    python -m unittest discover qsprpred
+    python -m unittest qsprpred.data.tables.tests

pyproject.toml

@@ -40,7 +40,7 @@ classifiers = [
 dependencies = [
     "parameterized",
     "pebble",
-    "numpy >= 1.19, <1.24.0",
+    "numpy",
     "scikit-learn >= 1.0.2",
     "pandas >= 1.2.2",
     "matplotlib >= 2.0",
@@ -51,18 +51,18 @@ dependencies = [
     "xgboost",
     "boruta",
     "tqdm",
-    "ml2json @ git+https://github.com/HellevdM/ml2json.git",
+    "ml2json",
     "jsonpickle",
-    "papyrus_scripts @ git+https://github.com/OlivierBeq/Papyrus-scripts.git",
-    "gbmt-splits @ git+https://github.com/sohviluukkonen/gbmt-splits@0.0.4",
+    "papyrus_scripts",
+    "gbmtsplits",
     "mlchemad",
     "mols2grid"
 ]
 
 [project.optional-dependencies]
 
 extra = [
-    "mold2-pywrapper @ git+https://github.com/OlivierBeq/Mold2_pywrapper.git@master",
+    "mold2-pywrapper",
     "padel-pywrapper >= 1.0.2.post1", "Mordred", "biopython", "prodec", "Signature-pywrapper",
 ]
 pyboost = ["py-boost"]
@@ -74,9 +74,9 @@ dev = ["qsprpred[full]", "pre-commit", "isort", "yapf", "ruff", "pytest"]
 where = ["."]
 
 [project.urls]
-homepage = "https://github.com/CDDLeiden/QSPRPred"
-repository = "https://github.com/CDDLeiden/QSPRPred"
-documentation = "https://cddleiden.github.io/QSPRPred/docs/"
+homepage = "https://github.com/CDDLeiden/QSPRpred"
+repository = "https://github.com/CDDLeiden/QSPRpred"
+documentation = "https://cddleiden.github.io/QSPRpred/docs/"
 
 [tool.setuptools]
 include-package-data = true

qsprpred/data/processing/feature_filters.py

@@ -89,7 +89,9 @@ def __call__(self, df: pd.DataFrame, y_col: pd.DataFrame = None) -> pd.DataFrame
 class BorutaFilter(FeatureFilter, Randomized):
     """Boruta filter from BorutaPy: Boruta all-relevant feature selection.
 
-    Uses BorutaPy implementation from https://github.com/scikit-learn-contrib/boruta_py
+    Uses BorutaPy implementation from https://github.com/scikit-learn-contrib/boruta_py.
+    Note that the `boruta` package is not compatible with numpy 1.24.0 and above.
+    Therefore, make sure to downgrade numpy to 1.23.0 or older before using this filter.
 
     Attributes:
         featSelector (BorutaPy): BorutaPy feature selector

qsprpred/data/processing/tests.py

@@ -1,5 +1,6 @@
 import copy
 import itertools
+from unittest import skipIf
 
 import numpy as np
 import pandas as pd
@@ -224,6 +225,10 @@ def testHighCorrelationFilter(self, use_index_cols):
             (False,),
         ]
     )
+    @skipIf(
+        int(np.__version__.split(".")[1]) >= 24,
+        "numpy 1.24.0 not compatible with boruta",
+    )
     def testBorutaFilter(self, use_index_cols):
         """Test the Boruta filter, which removes the features which are statistically as
         relevant as random features."""