Adding scaffold

.dockerignore

@@ -0,0 +1,165 @@
+.git
+.github
+mlruns
+outputs
+bento
+
+# 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
+.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/

.env

@@ -0,0 +1,37 @@
+# Project 
+PROJECT_NAME=time-series-airflow-kafka-spark
+
+# Airflow 
+AIRFLOW_TAG=2.8.2-python3.10
+
+# Spark
+SPARK_TAG=3.5
+
+# Kafka
+KAFKA_TAG=6.2.0
+
+# Python
+PYTHON_TAG=3.10.13-bullseye
+
+# BentoML
+BENTOML_HOME=/workspace/bento
+BENTOML_CONFIG=/workspace/bentoml_configuration.yaml
+
+# Postgres
+POSTGRES_TAG=15.3-bullseye
+DB_NAME=$PROJECT_NAME
+DB_USER=user
+DB_PASSWORD=password
+
+# Adminer
+ADMINER_TAG=4.7.9-standalone
+
+# MLFlow
+MLFLOW_BACKEND_STORE_URI=postgresql://${DB_USER}:${DB_PASSWORD}@postgres:5432/${DB_NAME}
+
+# Minio
+MINIO_TAG=RELEASE.2023-05-27T05-56-19Z
+MINIO_MC_TAG=RELEASE.2023-05-30T22-41-38Z
+
+# Container
+GITHUB_CONTAINER_REPO=ghcr.io/jbris/${PROJECT_NAME}:1.0.0

.github/workflows/build.yaml

@@ -0,0 +1,29 @@
+name: Docker Build
+
+on: 
+  workflow_dispatch: {}
+
+permissions:
+  actions: write
+  packages: write
+
+jobs:
+  build-server:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up QEMU
+      uses: docker/setup-qemu-action@v3
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+    - name: Docker build
+      run: bash ./scripts/build.sh
+    - name: Login to GitHub Package Registry
+      uses: docker/login-action@v2
+      with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GHCR_TOKEN }}
+    - name: Docker push
+      run: bash ./scripts/push.sh

.gitignore

@@ -120,7 +120,6 @@ celerybeat.pid
 *.sage.py
 
 # Environments
-.env
 .venv
 env/
 venv/
@@ -158,3 +157,7 @@ cython_debug/
 #  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/
+
+mlruns
+outputs
+bento

.vscode/settings.json

@@ -0,0 +1,10 @@
+{
+    "editor.formatOnSave": false,
+    "python.linting.lintOnSave": true,
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.insertSpaces": true,
+        "editor.tabSize": 4,
+        "editor.formatOnSave": true
+    },
+}

Dockerfile

@@ -0,0 +1,33 @@
+ARG PYTHON_TAG
+
+FROM python:${PYTHON_TAG} as base
+
+WORKDIR /workspace
+
+RUN apt-get update \
+    && apt-get install -y build-essential libpq-dev openjdk-17-jdk \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* \
+    && rm -rf /tmp/downloaded_packages
+
+FROM base as builder
+
+ENV POETRY_NO_INTERACTION=1 \
+    POETRY_VIRTUALENVS_IN_PROJECT=1 \
+    POETRY_VIRTUALENVS_CREATE=1 \
+    POETRY_CACHE_DIR=/tmp/poetry_cache \
+    PATH="/root/.local/bin:$PATH"
+
+COPY pyproject.toml poetry.lock ./
+
+RUN curl -sSL https://install.python-poetry.org | python3 -\
+    && poetry install --no-root \
+    && rm -rf $POETRY_CACHE_DIR \
+    && curl -sSL https://install.python-poetry.org | python3 - --uninstall
+
+FROM base as runtime
+
+ENV VIRTUAL_ENV=/workspace/.venv \
+    PATH="/workspace/.venv/bin:$PATH"
+
+COPY --from=builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}

README.md

@@ -1 +1,3 @@
-# time-series-airflow-kafka-spark
+# TAKS
+
+A simple demonstration of a Time Series-Airflow-Kafka-Spark (TAKS) stack.

bentoml_configuration.yaml

@@ -0,0 +1,3 @@
+version: 1
+api_server:
+  workers: 4