Merge pull request #78 from MachineLearningLifeScience/feature-better…

…-testing

Test using `docker` & add `RaSP` to testing

.github/workflows/python-tox-testing-including-conda-on-master.yml

@@ -0,0 +1,38 @@
+name: Test (master, conda, python 3.9)
+
+on:
+  pull_request:
+    branches:
+      - master
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.9'
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        python -m pip install tox
+    - name: Test linting with tox
+      run: |
+        tox -c tox.master.ini -e lint
+    - name: Test poli-base with tox
+      run: |
+        tox -c tox.master.ini -e poli-base-py39
+    - name: Test poli-chem with tox
+      run: |
+        tox -c tox.master.ini -e poli-chem-py39
+    - name: Test poli-protein with tox
+      run: |
+        tox -c tox.master.ini -e poli-protein-py39

.github/workflows/python-tox-testing-including-conda.yml

@@ -1,4 +1,4 @@
-name: Test (conda, python 3.9)
+name: Test (dev, conda, python 3.9)
 
 on: [push]
 
@@ -23,13 +23,7 @@ jobs:
         python -m pip install tox
     - name: Test linting with tox
       run: |
-        tox -e lint
-    - name: Test poli-base with tox
+        tox -c tox.dev.ini -e lint
+    - name: Test poli-base with tox (ignoring RaSP)
       run: |
-        tox -e poli-base-py39
-    - name: Test poli-chem with tox
-      run: |
-        tox -e poli-chem-py39
-    - name: Test poli-protein with tox
-      run: |
-        tox -e poli-protein-py39
+        tox -c tox.dev.ini -e poli-base-py39 -- --ignore=src/poli/tests/registry/proteins/test_rasp.py

CONTRIBUTING.md

@@ -20,15 +20,28 @@ pip install black
 black ./path/to/files
 ```
 
-## Testing your changes
+## Testing your changes for `dev``
 
 Since we are testing multiple conda environments, we settled for using a combination of `tox` and `pytest`.
 
 ```bash
 pip install tox
-tox              # from root of project
+
+# To test linting (from the root of the project)
+tox -c tox.dev.ini -e lint
+
+# To test in the base environment for poli
+tox -c tox.dev.ini -e poli-base-py39
 ```
 
+If you want to run tests in all environments, remove `-e poli-base-py39` and just run `tox`.
+
+## More thorough testing
+
+In many cases, testing with the instructions above should be enough. However, since we are dealing with creating conda environments, the definite test comes by building the Docker image specified in `Dockerfile.test`, and running it.
+
+When contributing to the `@master` branch (i.e. to release), we will run these tests.
+
 ## Create a pull request to dev
 
 Once all tests pass and you are ready to share your changes, create a pull request to the `dev` branch.

Dockerfile.test

@@ -0,0 +1,34 @@
+# This dockerfile allows us to run the tests in a container
+FROM --platform=linux/amd64 continuumio/anaconda3:latest
+
+# Set working directory
+WORKDIR /app
+
+# Copying the files from the host to the container
+COPY ./src /app/src
+COPY ./pyproject.toml /app/
+COPY ./setup.cfg /app/
+COPY ./requirements.txt /app/
+COPY ./requirements-dev.txt /app/
+COPY ./tox.ini /app/
+
+# Installing distutils
+RUN apt-get update && \
+    apt-get install build-essential -y && \
+    apt-get install -y python3.9-distutils
+
+# Installing python dependencies
+RUN conda --version
+RUN pip install -r requirements.txt
+RUN pip install -r requirements-dev.txt
+
+# Creating the relevant conda environments
+# For chem
+RUN conda env create --file src/poli/objective_repository/rdkit_qed/environment.yml
+
+# For proteins
+RUN conda env create --file src/poli/objective_repository/foldx_stability/environment.yml
+RUN conda env create --file src/poli/objective_repository/rasp/environment.yml
+
+# Running the tests
+CMD ["tox"]

requirements-dev.txt

@@ -1,2 +1,3 @@
 black
 tox
+setuptools

requirements.txt

@@ -1,2 +1 @@
-python
 numpy

src/poli/core/util/proteins/rasp/rasp_interface.py

@@ -32,6 +32,7 @@
 import os, stat
 import subprocess
 import logging
+import traceback
 
 import pandas as pd
 import numpy as np
@@ -138,6 +139,8 @@ def get_and_compile_reduce(self):
                     check=True,
                 )
             except subprocess.CalledProcessError:
+                # Printing the traceback
+                traceback.print_exc()
                 raise RuntimeError(
                     "Could not clone the reduce repository. "
                     "Please check your internet connection."
@@ -153,6 +156,7 @@ def get_and_compile_reduce(self):
                 )
             except subprocess.CalledProcessError:
                 # TODO: should we be purging it ourselves?
+                traceback.print_exc()
                 raise RuntimeError(
                     "Something went wrong while compiling reduce. "
                     "Purge the folder ~/.poli_objectives/rasp/reduce "

src/poli/objective_repository/__init__.py

@@ -4,10 +4,6 @@
 from .white_noise.register import WhiteNoiseProblemFactory
 from .aloha.register import AlohaProblemFactory
 
-# These have more complex dependencies
-# from .super_mario_bros.register import SuperMarioBrosBlackBox
-# from .rdkit_qed.register import QEDBlackBox
-
 
 THIS_DIR = Path(__file__).parent.resolve()
 

src/poli/objective_repository/foldx_sasa/environment.yml

@@ -1,8 +1,10 @@
 name: poli__protein
 channels:
   - defaults
+  - conda-forge
 dependencies:
   - python=3.9
+  - gcc
   - pip
   - pip:
     - biopython

src/poli/objective_repository/foldx_stability/environment.yml

@@ -1,8 +1,10 @@
 name: poli__protein
 channels:
   - defaults
+  - conda-forge
 dependencies:
   - python=3.9
+  - gcc
   - pip
   - pip:
     - biopython

src/poli/objective_repository/foldx_stability_and_sasa/environment.yml

@@ -1,8 +1,10 @@
 name: poli__protein
 channels:
   - defaults
+  - conda-forge
 dependencies:
   - python=3.9
+  - gcc
   - pip
   - pip:
     - biopython

src/poli/objective_repository/rasp/environment.yml

@@ -12,6 +12,8 @@ dependencies:
   - mpl-scatter-density
   - clang
   - cmake
+  - make
+  - gcc
   - pip
   - pip:
     - "git+https://github.com/MachineLearningLifeScience/poli.git@dev"

src/poli/tests/registry/basic_objectives/test_basic_objectives.py

@@ -0,0 +1,21 @@
+from pathlib import Path
+
+import numpy as np
+
+from poli import objective_factory
+
+THIS_DIR = Path(__file__).parent.resolve()
+
+
+def test_registering_white_noise():
+    _, f, _, _, _ = objective_factory.create(name="white_noise")
+    x = np.array([["A", "B", "C", "D"]])
+    f(x)
+    f.terminate()
+
+
+def test_registering_aloha():
+    _, f, _, y0, _ = objective_factory.create(name="aloha")
+    x = np.array([list("ALOOF")])
+    assert f(x) == 3
+    f.terminate()

src/poli/tests/registry/chemistry/test_chemistry_objectives.py

@@ -0,0 +1,148 @@
+import pytest
+from pathlib import Path
+
+import numpy as np
+
+from poli import objective_factory
+
+THIS_DIR = Path(__file__).parent.resolve()
+
+
+def test_qed_is_available():
+    """
+    We test whether the qed problem is available
+    when rdkit and selfies are installed.
+    """
+    _ = pytest.importorskip("rdkit")
+    _ = pytest.importorskip("selfies")
+    from poli.objective_repository import AVAILABLE_PROBLEM_FACTORIES
+
+    assert "rdkit_qed" in AVAILABLE_PROBLEM_FACTORIES
+
+
+def test_logp_is_available():
+    """
+    We test whether the logp problem is available
+    when rdkit and selfies are installed.
+    """
+    _ = pytest.importorskip("rdkit")
+    _ = pytest.importorskip("selfies")
+    from poli.objective_repository import AVAILABLE_PROBLEM_FACTORIES
+
+    assert "rdkit_logp" in AVAILABLE_PROBLEM_FACTORIES
+
+
+def test_force_registering_qed():
+    """
+    We test whether we can force-register the qed problem
+    if rdkit and selfies are not installed.
+    """
+    alphabet = ["", "C", "..."]
+    _, f, _, y0, _ = objective_factory.create(
+        name="rdkit_qed",
+        alphabet=alphabet,
+        force_register=True,
+    )
+
+    # Asserting that the QED of a single carbon
+    # is close to 0.35978494 (according to RDKit).
+    assert np.isclose(y0, 0.35978494).all()
+    f.terminate()
+
+
+def test_force_registering_qed_with_context_manager():
+    """
+    Tests the objective_factory.start method on QED.
+    """
+    with objective_factory.start(
+        name="rdkit_qed",
+        force_register=True,
+        force_isolation=True,
+        path_to_alphabet=THIS_DIR / "alphabet_qed.json",
+    ) as f:
+        x = np.array([["C"]])
+        y = f(x)
+        assert np.isclose(y, 0.35978494).all()
+
+
+def test_force_registering_logp():
+    """
+    We test whether we can force-register the logp problem
+    if rdkit and selfies are not installed.
+    """
+    alphabet = ["", "C", ""]
+    _, f, _, y0, _ = objective_factory.create(
+        name="rdkit_logp",
+        alphabet=alphabet,
+        # path_to_alphabet=THIS_DIR / "alphabet_qed.json",
+        force_register=True,
+    )
+
+    # Asserting that a single carbon atom has logp close
+    # to 0.6361. (according to RDKit)
+    assert np.isclose(y0, 0.6361).all()
+    f.terminate()
+
+
+def test_registering_qed():
+    """
+    Testing whether we can register the qed problem
+    if rdkit and selfies are installed.
+    """
+    _ = pytest.importorskip("rdkit")
+    _ = pytest.importorskip("selfies")
+    np = pytest.importorskip("numpy")
+
+    _, f, _, y0, _ = objective_factory.create(
+        name="rdkit_qed",
+        path_to_alphabet=THIS_DIR / "alphabet_qed.json",
+    )
+    x = np.array([["C"]])
+    y = f(x)
+
+    # Asserting that the QED of a single carbon
+    # is close to 0.35978494 (according to RDKit).
+    assert np.isclose(y, 0.35978494).all()
+
+    f.terminate()
+
+
+def test_registering_logp():
+    """
+    Testing whether we can register the logp problem
+    if rdkit and selfies are installed.
+    """
+    rdkit = pytest.importorskip("rdkit")
+    selfies = pytest.importorskip("selfies")
+    np = pytest.importorskip("numpy")
+
+    _, f, _, y0, _ = objective_factory.create(
+        name="rdkit_logp",
+        path_to_alphabet=THIS_DIR / "alphabet_qed.json",
+    )
+    x = np.array([[1]])
+    f(x)
+
+    # Asserting that a single carbon atom has logp close
+    # to 0.6361. (according to RDKit)
+    assert np.isclose(y0, 0.6361).all()
+
+    f.terminate()
+
+
+def test_penalized_logp_lambo():
+    """
+    Testing whether we can register the logp problem
+    from lambo.
+    """
+    from poli import objective_factory
+
+    _ = pytest.importorskip("lambo")
+
+    # Using create
+    _, f, x0, y0, _ = objective_factory.create(
+        name="penalized_logp_lambo", force_register=True
+    )
+    print(x0)
+    print(y0)
+    f.terminate()