Simplify and optimize Docker image

.dockerignore

@@ -0,0 +1,4 @@
+.git
+slides/
+.DS_Store
+__pycache__/

.github/workflows/docker-build.yml

@@ -0,0 +1,37 @@
+---
+name: Build Tutorial Container
+
+on:
+  push:
+    branches:
+      - main
+    paths-ignore:
+      - "*.md"
+      - slides/**
+      - images/**
+      - .gitignore
+  workflow_dispatch:
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build the Docker image
+        run: |
+          docker build -t ghcr.io/${{ github.repository }}:latest .
+
+      - name: Push the Docker image
+        run: |
+          docker push ghcr.io/${{ github.repository }}:latest

Dockerfile

@@ -0,0 +1,51 @@
+# Use the jupyter/minimal-notebook as the base image
+FROM quay.io/jupyter/minimal-notebook:latest
+
+# Metadata labels
+LABEL org.opencontainers.image.title="Python Tutorial"
+LABEL org.opencontainers.image.description="A containerized Python tutorial environment with Jupyter Lab."
+LABEL org.opencontainers.image.authors="Empa Scientific IT <scientificit@empa.ch>"
+LABEL org.opencontainers.image.url="https://github.com/empa-scientific-it/python-tutorial"
+LABEL org.opencontainers.image.source="https://github.com/empa-scientific-it/python-tutorial"
+LABEL org.opencontainers.image.version="1.0.0"
+LABEL org.opencontainers.image.licenses="MIT"
+
+# Set environment variables for the tutorial and repository
+ENV BASENAME="python-tutorial"
+ENV REPO=${HOME}/${BASENAME}
+ENV IPYTHONDIR="${HOME}/.ipython"
+
+# Switch to root user to install additional dependencies
+USER root
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+    build-essential \
+    gcc \
+    g++ \
+    libffi-dev && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Switch back to the default notebook user
+USER ${NB_UID}
+
+# Set up the Conda environment
+COPY docker/environment.yml /tmp/environment.yml
+RUN mamba env update -n base -f /tmp/environment.yml && \
+    mamba clean --all -f -y && \
+    fix-permissions "${CONDA_DIR}" && \
+    fix-permissions "/home/${NB_USER}"
+
+# Prepare IPython configuration (move earlier in the build)
+RUN mkdir -p ${HOME}/.ipython/profile_default
+COPY --chown=${NB_UID}:${NB_GID} binder/ipython_config.py ${HOME}/.ipython/profile_default/
+
+# Copy the repository late in the build process
+RUN mkdir -p ${REPO}
+COPY --chown=${NB_UID}:${NB_GID} . ${REPO}/
+
+# Set the working directory to the repository
+WORKDIR ${REPO}
+
+# Use the default ENTRYPOINT from the base image to start Jupyter Lab
+ENTRYPOINT ["tini", "-g", "--", "start.sh"]

docker/activate-custom-env.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+conda activate python-tutorial

docker/environment.yml

@@ -0,0 +1,26 @@
+---
+name: base
+channels:
+  - conda-forge
+dependencies:
+  - pip
+  - pip:
+      - numpy
+      - matplotlib
+      - pandas
+      - ipywidgets
+      - ipynbname
+      - jupyterlab
+      - pytest
+      - pytest-timeout
+      - markdown
+      - pre-commit
+      - geostatspy
+      - gstools
+      - scikit-learn
+      - attrs
+      - multiprocess
+      - openai
+      - tenacity
+      - markdown2
+      - python-dotenv

docker/post-build.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+set -e
+
+mkdir -p ${HOME}/.ipython/profile_default
+cp binder/ipython_config.py ${HOME}/.ipython/profile_default/

docker/setup_custom_env.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+import json
+import os
+import sys
+from pathlib import Path
+
+# Retrieve the environment name from the command-line arguments
+env_name = sys.argv[1]
+
+# Get the Conda directory from the environment variables
+CONDA_DIR = os.environ["CONDA_DIR"]
+
+# Define the path to the kernel.json file
+kernel_dir = Path.home() / f".local/share/jupyter/kernels/{env_name}"
+kernel_file = kernel_dir / "kernel.json"
+
+# Ensure the kernel directory exists
+kernel_dir.mkdir(parents=True, exist_ok=True)
+
+# Define default kernel.json content
+default_content = {
+    "argv": [
+        f"{CONDA_DIR}/envs/{env_name}/bin/python",
+        "-m",
+        "ipykernel_launcher",
+        "-f",
+        "{connection_file}",
+    ],
+    "display_name": f"Python ({env_name})",
+    "language": "python",
+}
+
+# If the kernel.json file doesn't exist, create it with default content
+if not kernel_file.exists():
+    kernel_file.write_text(json.dumps(default_content, indent=1))
+
+# Read the existing kernel.json content
+content = json.loads(kernel_file.read_text())
+
+# Add the environment variables to the kernel configuration
+content["env"] = {
+    "XML_CATALOG_FILES": "",
+    "PATH": f"{CONDA_DIR}/envs/{env_name}/bin:$PATH",
+    "CONDA_PREFIX": f"{CONDA_DIR}/envs/{env_name}",
+    "CONDA_PROMPT_MODIFIER": f"({env_name}) ",
+    "CONDA_SHLVL": "2",
+    "CONDA_DEFAULT_ENV": env_name,
+    "CONDA_PREFIX_1": CONDA_DIR,
+}
+
+# Write the updated content back to the kernel.json file
+kernel_file.write_text(json.dumps(content, indent=1))