Updating Dockerfiles and build scripts, pinning pyarrow, and fixing some pre-commit issues

.github/workflows/tool-release.yml

@@ -6,27 +6,14 @@ env:
 
 on:
   workflow_dispatch:
-    inputs:
-      num-commits:
-        description: "The of commits to check for updated packages. If 0, the action will check all commits on the branch. For any larger value, the action will check the last n commits for any updated packages."
-        required: true
-        default: 1
-        type: number
-      ignore-missing-dev:
-        description: "If true, the action will ignore packages that do not have a dev version. Otherwise, the action will fail if any package does not have a dev version."
-        required: true
-        default: true
-        type: boolean
 
 permissions:
   contents: write
 
 jobs:
   tools-release:
-    name: Call workflow from image-tools
+    name: Tool Release
     uses: polusai/image-tools/.github/workflows/package-release.yml@master
     with:
-      num-commits: ${{ github.event.inputs.num-commits }}
-      ignore-missing-dev: ${{ github.event.inputs.ignore-missing-dev }}
       repo_name: "tabular-tools"
     secrets: inherit

.github/workflows/tool-tests.yml

@@ -17,5 +17,5 @@ permissions:
 
 jobs:
   tools-tests:
-    name: Call workflow from image-tools
+    name: Tool Tests
     uses: polusai/image-tools/.github/workflows/package-tests.yml@master

clustering/feature-subsetting-tool/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.2.1-dev0
+current_version = 0.2.2-dev0
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<dev>\d+))?
@@ -21,6 +21,7 @@ search = version = "{current_version}"
 replace = version = "{new_version}"
 
 [bumpversion:file:plugin.json]
+
 [bumpversion:file:README.md]
 
 [bumpversion:file:VERSION]

clustering/feature-subsetting-tool/.gitignore

@@ -0,0 +1,179 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# vscode
+.vscode
+
+# test data directory
+data
+
+# local manifests
+src/polus/plugins/_plugins/manifests/*
+
+# allow python scripts inside manifests dir
+!src/polus/plugins/_plugins/manifests/*.py
+
+#macOS
+*.DS_Store
+
+
+#husky
+node_modules

clustering/feature-subsetting-tool/Dockerfile

@@ -9,13 +9,17 @@ ENV POLUS_LOG="INFO"
 # Work directory defined in the base container
 WORKDIR ${EXEC_DIR}
 
-COPY pyproject.toml ${EXEC_DIR}
-COPY VERSION ${EXEC_DIR}
-COPY README.md ${EXEC_DIR}
-COPY src ${EXEC_DIR}/src
+# TODO: Change the tool_dir to the tool directory
+ENV TOOL_DIR="clustering/feature-subsetting-tool"
 
-RUN pip3 install ${EXEC_DIR} --no-cache-dir
+# Copy the repository into the container
+RUN mkdir tabular-tools
+COPY . ${EXEC_DIR}/tabular-tools
 
+# Install the tool
+RUN pip3 install "${EXEC_DIR}/tabular-tools/${TOOL_DIR}" --no-cache-dir
 
+# Set the entrypoint
+# TODO: Change the entrypoint to the tool entrypoint
 ENTRYPOINT ["python3", "-m", "polus.tabular.clustering.feature_subsetting"]
 CMD ["--help"]

clustering/feature-subsetting-tool/README.md

@@ -1,4 +1,4 @@
-# Feature Data Subset(v0.2.1-dev0)
+# Feature Data Subset(v0.2.2-dev0)
 
 This WIPP plugin subsets data based on a given feature. It works in conjunction with the `polus-feature-extraction-plugin`, where the feature extraction plugin can be used to extract the features such as the mean intensity of every image in the input image collection.
 

clustering/feature-subsetting-tool/VERSION

@@ -1 +1 @@
-0.2.1-dev0
+0.2.2-dev0

clustering/feature-subsetting-tool/build-docker.sh

@@ -1,4 +1,22 @@
 #!/bin/bash
 
+# TODO: Change the name of the tool here
+tool_dir="clustering"
+tool_name="feature-subsetting-tool"
+
+# The version is read from the VERSION file
 version=$(<VERSION)
-docker build . -t polusai/feature-subsetting-tool:${version}
+tag="polusai/${tool_name}:${version}"
+echo "Building docker image with tag: ${tag}"
+
+# The current directory and the repository root are saved in variables
+cur_dir=$(pwd)
+repo_root=$(git rev-parse --show-toplevel)
+
+# The Dockerfile and .dockerignore files are copied to the repository root before building the image
+cd ${repo_root}
+cp ./${tool_dir}/${tool_name}/Dockerfile .
+cp .gitingore .dockerignore
+docker build . -t ${tag}
+rm Dockerfile .dockerignore
+cd ${cur_dir}

clustering/feature-subsetting-tool/plugin.json

@@ -1,14 +1,14 @@
 {
   "name": "Feature Subsetting",
-  "version": "0.2.1-dev0",
+  "version": "0.2.2-dev0",
   "title": "Feature Subsetting",
   "description": "Subset data using a given feature.",
   "author": "Gauhar Bains (gauhar.bains@labshare.org) and Hamdah Shafqat Abbasi (hamdahshafqat.abbasi@nih.gov)",
   "institution": "National Center for Advancing Translational Sciences, National Institutes of Health",
   "repository": "https://github.com/PolusAI/tabular-tools",
   "website": "https://ncats.nih.gov/preclinical/core/informatics",
   "citation": "",
-  "containerId": "polusai/feature-subsetting-plugin:0.2.1-dev0",
+  "containerId": "polusai/feature-subsetting-plugin:0.2.2-dev0",
   "baseCommand": [
     "python3",
     "-m",
@@ -170,4 +170,4 @@
       "required": "False"
     }
   }
-}
+}

clustering/feature-subsetting-tool/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "polus-tabular-clustering-feature-subsetting"
-version = "0.2.1-dev0"
+version = "0.2.2-dev0"
 description = "Subset data using a given feature."
 authors = [
            "Gauhar Bains <gauhar.bains@labshare.org>",
@@ -15,6 +15,7 @@ filepattern = "^2.0.4"
 typer = "^0.7.0"
 tqdm = "^4.64.1"
 vaex = "^4.17.0"
+pyarrow = ">=16.0,<17.0"
 
 
 [tool.poetry.group.dev.dependencies]

clustering/feature-subsetting-tool/src/polus/tabular/clustering/feature_subsetting/__init__.py

@@ -1,3 +1,3 @@
 """Feature Subsetting Tool."""
 
-__version__ = "0.2.1-dev0"
+__version__ = "0.2.2-dev0"

clustering/hdbscan-clustering-tool/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.8-dev1
+current_version = 0.4.9-dev0
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<dev>\d+))?
@@ -23,6 +23,7 @@ replace = version = "{new_version}"
 [bumpversion:file:plugin.json]
 
 [bumpversion:file:VERSION]
+
 [bumpversion:file:README.md]
 
 [bumpversion:file:src/polus/tabular/clustering/hdbscan_clustering/__init__.py]