Merge pull request #80 from daisybio/development

New version including DIPK

.github/workflows/labeler.yml

@@ -14,6 +14,6 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Run Labeler
-        uses: crazy-max/ghaction-github-labeler@v5.0.0
+        uses: crazy-max/ghaction-github-labeler@v5.1.0
         with:
           skip-delete: true

.github/workflows/publish-docker.yml

@@ -0,0 +1,64 @@
+name: Create and publish a Docker image
+
+# Configures this workflow to run every time a release is published
+on:
+  release:
+    types: [published]
+
+# Defines two custom environment variables for the workflow.
+# These are used for the Container registry domain, and a name for the Docker image that this workflow builds.
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+
+    # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
+    permissions:
+      contents: read
+      packages: write
+      attestations: write
+      id-token: write
+
+    steps:
+      # Necessary for buildx
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup QEMU
+        uses: docker/setup-qemu-action@v3
+
+      # Set up BuildKit Docker container builder to be able to build
+      # multi-platform images and export cache
+      # https://github.com/docker/setup-buildx-action
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      # This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
+      # It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
+      # It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          platforms: linux/amd64,linux/arm64

.github/workflows/python-package.yml

@@ -18,22 +18,32 @@ jobs:
         python-version: ["3.9", "3.10", "3.11"]
 
     steps:
-      - uses: actions/checkout@v4
+      - name: Check out the repository
+        uses: actions/checkout@v4
+
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+
+      - name: Install Poetry
+        run: |
+          pipx install poetry
+          poetry --version
+
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip
-          python -m pip install flake8 pytest
-          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+          poetry install --with development
+
+      - name: Build package
+        run: poetry build --ansi
+
       - name: Lint with flake8
         run: |
           # stop the build if there are Python syntax errors or undefined names
-          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+          poetry run 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 --ignore W503
+          poetry run flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics --ignore W503,D212
       - name: Test with pytest
         run: |
-          pytest
+          poetry run pytest

.github/workflows/python-publish.yml

@@ -32,7 +32,7 @@ jobs:
       - name: Build package
         run: python -m build
       - name: Publish package
-        uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+        uses: pypa/gh-action-pypi-publish@15c56dba361d8335944d31a2ecd17d700fc7bcbc
         with:
           user: __token__
           password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/run_tests.yml

@@ -3,8 +3,6 @@ name: Run drevalpy Tests
 on:
   push:
     branches:
-      - development
-      - main
       - "release/*"
   pull_request:
     branches:
@@ -23,7 +21,6 @@ jobs:
           - { python-version: "3.10", os: ubuntu-latest, session: "mypy" }
           - { python-version: "3.10", os: ubuntu-latest, session: "tests" }
           - { python-version: "3.10", os: windows-latest, session: "tests" }
-          - { python-version: "3.10", os: macos-latest, session: "tests" }
           - { python-version: "3.10", os: ubuntu-latest, session: "typeguard" }
           - { python-version: "3.10", os: ubuntu-latest, session: "xdoctest" }
           - { python-version: "3.10", os: ubuntu-latest, session: "docs-build" }
@@ -130,4 +127,6 @@ jobs:
         run: nox --force-color --session=coverage -- xml -i
 
       - name: Upload coverage report
-        uses: codecov/[email protected]
+        uses: codecov/[email protected]
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}

.pre-commit-config.yaml

@@ -35,7 +35,7 @@ repos:
         types: [python]
         require_serial: true
         args:
-          - --ignore=W503
+          - --ignore=D212,W503,C901
       - id: pyupgrade
         name: pyupgrade
         description: Automatically upgrade syntax for newer versions.

Dockerfile

@@ -0,0 +1,53 @@
+# I followed this article's recommendations
+# https://medium.com/@albertazzir/blazing-fast-python-docker-builds-with-poetry-a78a66f5aed0
+
+# The builder image, used to build the virtual environment
+FROM python:3.10-buster as builder
+
+RUN pip install poetry==1.8.4
+
+# POETRY_VIRTUALENVS_CREATE=1: Makes sure that environment will be as isolated as possible and above all that
+# installation will not mess up with the system Python or, even worse, with Poetry itself.
+# POETRY_CACHE_DIR: When removing the cache folder, make sure this is done in the same RUN command. If it’s done in a
+# separate RUN command, the cache will still be part of the previous Docker layer (the one containing poetry install )
+# effectively rendering your optimization useless.
+
+ENV POETRY_NO_INTERACTION=1 \
+    POETRY_VIRTUALENVS_IN_PROJECT=1 \
+    POETRY_VIRTUALENVS_CREATE=1 \
+    POETRY_CACHE_DIR=/tmp/poetry_cache
+
+WORKDIR /root
+
+COPY pyproject.toml poetry.lock ./
+
+# First, we install only the dependencies. This way, we can cache this layer and avoid re-installing dependencies
+# every time we change our application code.
+# Because poetry will complain if a README.md is not found, we create a dummy one.
+RUN touch README.md
+
+RUN poetry install --without dev --no-root && rm -rf $POETRY_CACHE_DIR
+
+# The runtime image, used to run the code
+FROM python:3.10-slim-buster as runtime
+
+LABEL image.author.name="Judith Bernett"
+LABEL image.author.email="[email protected]"
+
+ENV VIRTUAL_ENV=/root/.venv \
+    PATH="/root/.venv/bin:$PATH"
+
+COPY --from=builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+
+# Copy all relevant code
+
+COPY drevalpy ./drevalpy
+COPY create_report.py ./
+COPY README.md ./
+COPY run_suite.py ./
+COPY setup.py ./
+COPY pyproject.toml ./
+COPY poetry.lock ./
+
+# Install drevalpy
+RUN pip install .

README.md

@@ -42,7 +42,7 @@ pip install drevalpy
 From Source:
 
 ```bash
-conda env create -f models/simple_neural_network/env.yml
+conda env create -f models/SimpleNeuralNetwork/env.yml
 pip install .
 ```
 

README.rst

@@ -15,10 +15,10 @@ DrEvalPy: Python Cancer Cell Line Drug Response Prediction Suite
 .. |Read the Docs| image:: https://img.shields.io/readthedocs/drevalpy/latest.svg?label=Read%20the%20Docs
    :target: https://drevalpy.readthedocs.io/
    :alt: Read the documentation at https://drevalpy.readthedocs.io/
-.. |Build| image:: https://github.com/daisybio/drevalpy/workflows/Build%20drevalpy%20Package/badge.svg
+.. |Build| image:: https://github.com/daisybio/drevalpy/actions/workflows/build_package.yml/badge.svg
    :target: https://github.com/daisybio/drevalpy/actions?workflow=Package
    :alt: Build Package Status
-.. |Tests| image:: https://github.com/daisybio/drevalpy/workflows/Run%20drevalpy%20Tests/badge.svg
+.. |Tests| image:: https://github.com/daisybio/drevalpy/actions/workflows/run_tests.yml/badge.svg
    :target: https://github.com/daisybio/drevalpy/actions?workflow=Tests
    :alt: Run Tests Status
 .. |Codecov| image:: https://codecov.io/gh/daisybio/drevalpy/branch/main/graph/badge.svg

create_report.py

@@ -3,6 +3,8 @@
 import argparse
 import os
 
+import pandas as pd
+
 from drevalpy.visualization import (
     CorrelationComparisonScatter,
     CriticalDifferencePlot,
@@ -14,8 +16,10 @@
 from drevalpy.visualization.utils import create_html, create_index_html, parse_results, prep_results, write_results
 
 
-def create_output_directories(custom_id):
-    """If they do not exist yet, make directories for the visualization files.
+def create_output_directories(custom_id: str) -> None:
+    """
+    If they do not exist yet, make directories for the visualization files.
+
     :param custom_id: run id passed via command line
     """
     os.makedirs(f"results/{custom_id}/violin_plots", exist_ok=True)
@@ -26,13 +30,22 @@ def create_output_directories(custom_id):
     os.makedirs(f"results/{custom_id}/critical_difference_plots", exist_ok=True)
 
 
-def draw_setting_plots(lpo_lco_ldo, ev_res, ev_res_per_drug, ev_res_per_cell_line, custom_id):
-    """Draw all plots for a specific setting (LPO, LCO, LDO).
+def draw_setting_plots(
+    lpo_lco_ldo: str,
+    ev_res: pd.DataFrame,
+    ev_res_per_drug: pd.DataFrame,
+    ev_res_per_cell_line: pd.DataFrame,
+    custom_id: str,
+) -> list[str]:
+    """
+    Draw all plots for a specific setting (LPO, LCO, LDO).
+
     :param lpo_lco_ldo: setting
     :param ev_res: overall evaluation results
     :param ev_res_per_drug: evaluation results per drug
     :param ev_res_per_cell_line: evaluation results per cell line
     :param custom_id: run id passed via command line
+    :returns: list of unique algorithms
     """
     ev_res_subset = ev_res[ev_res["LPO_LCO_LDO"] == lpo_lco_ldo]
     # PIPELINE: SAVE_TABLES
@@ -99,8 +112,12 @@ def draw_setting_plots(lpo_lco_ldo, ev_res, ev_res_per_drug, ev_res_per_cell_lin
     return eval_results_preds["algorithm"].unique()
 
 
-def draw_per_grouping_setting_plots(grouping, ev_res_per_group, lpo_lco_ldo, custom_id):
-    """Draw plots for a specific grouping (drug or cell line) for a specific setting (LPO, LCO, LDO).
+def draw_per_grouping_setting_plots(
+    grouping: str, ev_res_per_group: pd.DataFrame, lpo_lco_ldo: str, custom_id: str
+) -> None:
+    """
+    Draw plots for a specific grouping (drug or cell line) for a specific setting (LPO, LCO, LDO).
+
     :param grouping: drug or cell_line
     :param ev_res_per_group: evaluation results per drug or per cell line
     :param lpo_lco_ldo: setting
@@ -132,15 +149,17 @@ def draw_per_grouping_setting_plots(grouping, ev_res_per_group, lpo_lco_ldo, cus
 
 
 def draw_algorithm_plots(
-    model,
-    ev_res,
-    ev_res_per_drug,
-    ev_res_per_cell_line,
-    t_vs_p,
-    lpo_lco_ldo,
-    custom_id,
-):
-    """Draw all plots for a specific algorithm.
+    model: str,
+    ev_res: pd.DataFrame,
+    ev_res_per_drug: pd.DataFrame,
+    ev_res_per_cell_line: pd.DataFrame,
+    t_vs_p: pd.DataFrame,
+    lpo_lco_ldo: str,
+    custom_id: str,
+) -> None:
+    """
+    Draw all plots for a specific algorithm.
+
     :param model: name of the model/algorithm
     :param ev_res: overall evaluation results
     :param ev_res_per_drug: evaluation results per drug
@@ -194,15 +213,17 @@ def draw_algorithm_plots(
 
 
 def draw_per_grouping_algorithm_plots(
-    grouping_slider,
-    grouping_scatter_table,
-    model,
-    ev_res_per_group,
-    t_v_p,
-    lpo_lco_ldo,
-    custom_id,
+    grouping_slider: str,
+    grouping_scatter_table: str,
+    model: str,
+    ev_res_per_group: pd.DataFrame,
+    t_v_p: pd.DataFrame,
+    lpo_lco_ldo: str,
+    custom_id: str,
 ):
-    """Draw plots for a specific grouping (drug or cell line) for a specific algorithm.
+    """
+    Draw plots for a specific grouping (drug or cell line) for a specific algorithm.
+
     :param grouping_slider: the grouping variable for the regression plots
     :param grouping_scatter_table: the grouping variable for the scatter plots.
             If grouping_slider is drug, this should be cell_line and vice versa
@@ -320,8 +341,8 @@ def draw_per_grouping_algorithm_plots(
                 custom_id=run_id,
             )
         # get all html files from results/{run_id}
-        all_files = []
-        for _, _, files in os.walk(f"results/{run_id}"):
+        all_files: list[str] = []
+        for _, _, files in os.walk(f"results/{run_id}"):  # type: ignore[assignment]
             for file in files:
                 if file.endswith(".html") and file not in ["index.html", "LPO.html", "LCO.html", "LDO.html"]:
                     all_files.append(file)