release v0.1.0

.github/workflows/format-lint-test.yaml

@@ -0,0 +1,35 @@
+name: "CI: format, lint, and test"
+on:
+  push:
+    branches:
+      - "main"
+      - "develop"
+  pull_request:
+    branches:
+      - "main"
+      - "develop"
+
+jobs:
+  format-lint-test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: 🛎️ Checkout
+        uses: actions/checkout@v4
+
+      - name: 📦 Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: 🐍 Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: ".python-version"
+
+      - name: 🚀 Install just 
+        uses: extractions/setup-just@v2
+
+      - name: 🦾 Install the project
+        run: just dev-sync
+
+      - name: 💅 🧪 Format, Lint and test
+        run: just validate

.gitignore

@@ -0,0 +1,168 @@
+##########################
+# KEDRO PROJECT
+
+# ignore all local configuration
+conf/local/**
+!conf/local/.gitkeep
+.telemetry
+
+# ignore potentially sensitive credentials files
+conf/**/*credentials*
+
+# ignore everything in the following folders
+data/**
+
+# except their sub-folders
+!data/**/
+# except the final report
+!data/08_reporting/images/*
+!data/08_reporting/final_report.md
+
+# also keep all .gitkeep files
+!.gitkeep
+
+# ignore kedro-viz metadata
+.viz
+
+# ignore file based logs
+*.log
+
+##########################
+# Common files
+
+# IntelliJ
+.idea/
+*.iml
+out/
+.idea_modules/
+
+### macOS
+*.DS_Store
+.AppleDouble
+.LSOverride
+.Trashes
+
+# Vim
+*~
+.*.swo
+.*.swp
+
+# emacs
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+
+# VS Code
+.vscode/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# C extensions
+*.so
+
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+.static_storage/
+.media/
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+.ipython/profile_default/history.sqlite
+.ipython/profile_default/startup/README
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# mlflow local runs
+mlruns/*

.pre-commit-config.yaml

@@ -0,0 +1,15 @@
+default_language_version:
+  python: python3.12
+repos:
+  - repo: local
+    hooks:
+      - id: format
+        name: format
+        entry: just format
+        require_serial: true
+        language: system
+        pass_filenames: false
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.8.1
+    hooks:
+      - id: nbstripout

.python-version

@@ -0,0 +1 @@
+3.12

Dockerfile

@@ -0,0 +1,59 @@
+# An example using multi-stage image builds to create a final image without uv.
+# Source: https://github.com/astral-sh/uv-docker-example/blob/main/multistage.Dockerfile
+
+# First, build the application in the `/app` directory.
+# See `Dockerfile` for details.
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim AS builder
+ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
+
+# Install GDAL build dependencies (for fiona Python package)
+USER root
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+        build-essential \
+        gdal-bin \
+        libgdal-dev \
+        python3-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Disable Python downloads, because we want to use the system interpreter
+# across both images. If using a managed Python version, it needs to be
+# copied from the build image into the final image; see `standalone.Dockerfile`
+# for an example.
+ENV UV_PYTHON_DOWNLOADS=0
+
+WORKDIR /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+ADD . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --no-dev
+
+
+# Then, use a final image without uv
+FROM python:3.12-slim-bookworm
+# It is important to use the image that matches the builder, as the path to the
+# Python executable must be the same, e.g., using `python:3.11-slim-bookworm`
+# will fail.
+
+# Install GDAL runtime library (for fiona Python package)
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+        libgdal-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy the application from the builder
+COPY --from=builder --chown=app:app /app /app
+
+# Place executables in the environment at the front of the path
+ENV PATH="/app/.venv/bin:$PATH"
+
+# disable Kedro telemetry
+ENV KEDRO_DISABLE_TELEMETRY=1
+
+WORKDIR /app
+# Run Kedro pipelines
+CMD ["kedro", "run", "--async"]
+

Justfile

@@ -0,0 +1,32 @@
+# https://github.com/casey/just
+
+dev-sync:
+    uv sync --all-extras --cache-dir .uv_cache
+
+prod-sync:
+	uv sync --all-extras --no-dev --cache-dir .uv_cache
+
+install-hooks:
+	uv run pre-commit install
+
+format:
+	uv run ruff format
+
+lint:
+	uv run ruff check --fix
+
+test:
+	uv pip install -e .
+	uv run pytest --verbose --color=yes tests
+
+validate: format lint test
+
+docker-build:
+	docker build -t geolocation-pipeline .
+
+docker-run:
+	# Bind‑mount the host .data/ folder into the container so that the pipelines'
+	# outputs are saved in the host's local .data/ folder
+	docker run --rm \
+		-v "$(pwd)/data:/app/data" \
+		geolocation-pipeline