ブログ記事の内容

＜タイトル＞ JupyterLab×Airflow

2025年06月11日 2025年06月11日カテゴリ: 環境構築

#Airflow学習用の環境構築(Airflow×Jupyter)

Airflow学習用にローカル側でDockerコンテナを利用して環境構築をする。Airflowで実行するPythonスクリプトの開発環境用にJupyterを連携して立ち上げる。

#ディレクトリ構造#

myairflow
  - AirFlow            # Airflow側のマウント先ディレクトリ(任意の命名)
  - Mount_Directory    # Jupyter側のマウント先ディレクトリ(任意の命名)
  - .env               # Airflow側の環境変数
  - docker-compose.yml # 立ち上げ用($Docker-compose up -d)
  - Dockerfile         # Jupyter側の環境構築
  - requirements.txt   # Jupyter側で利用するライブラリ

#Docker-compose.yml

# Apache Software Foundation (ASF) のライセンス（Apache License 2.0）
# 開発やテスト目的のみに使ってください（本番環境には非推奨）

# ========================= #
# Airflow の初期化 ==> 起動
# ========================= #
## "docker-compose up airflow-init" ==> "docker-compose up -d"

# ============================== #
# Airflow のデバック(Flower｜CLI)
# ============================== #
## "docker-compose --profile flower up" | "docker-compose --profile debug run airflow-cli XXXX "

# `PythonOperator`等を利用して作成したDAGファイルは、次のディレクトリに配置して再起動すること
# --> 「AirFlow/dags/***」+ $docker-compose up -d --> UI画面にファイルが反映される

# ================================ #
# {環境変数名}/{意味}/{デフォルト値}
# ================================ #
## AIRFLOW_IMAGE_NAME          ｜使用する Docker イメージ  ｜apache/airflow:2.10.5
## AIRFLOW_UID                 ｜Airflow の実行ユーザーID  ｜50000
## AIRFLOW_PROJ_DIR            ｜ホスト側のベースディレクトリ｜.
## _AIRFLOW_WWW_USER_USERNAME  ｜Airflow の管理者ユーザー名 ｜airflow
## _AIRFLOW_WWW_USER_PASSWORD  ｜Airflow の管理者パスワード ｜airflow
## _PIP_ADDITIONAL_REQUIREMENTS｜起動時に追加インストールするPythonパッケージ｜空文字
#
# =================================================================== #
# Airflow クラスタ構成（CeleryExecutor + Redis + PostgreSQL）：共通設定
# =================================================================== #
---
x-airflow-common:
  &airflow-common
  image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.10.5}
  depends_on:
    &airflow-common-depends-on
    redis:
      condition: service_healthy
    postgres:
      condition: service_healthy
  user: "${AIRFLOW_UID:-50000}:0"
  volumes:
    - ${AIRFLOW_PROJ_DIR:-.}/dags:/opt/airflow/dags
    - ${AIRFLOW_PROJ_DIR:-.}/logs:/opt/airflow/logs
    - ${AIRFLOW_PROJ_DIR:-.}/config:/opt/airflow/config
    - ${AIRFLOW_PROJ_DIR:-.}/plugins:/opt/airflow/plugins
  environment:
    &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
    AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0
    AIRFLOW__CORE__FERNET_KEY: ''
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
    AIRFLOW__CORE__LOAD_EXAMPLES: 'false' # 'true'
    AIRFLOW__API__AUTH_BACKENDS: 'airflow.api.auth.backend.basic_auth,airflow.api.auth.backend.session'
    AIRFLOW__SCHEDULER__ENABLE_HEALTH_CHECK: 'true'
    _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:-}
    # AIRFLOW_CONFIG: '/opt/airflow/config/airflow.cfg'
# ============================ #
# Airflow マウント設定{volumes}
# ============================ #
## /opt/airflow/dags    | DAGファイルを置く場所
## /opt/airflow/logs    | ログ出力先
## /opt/airflow/config  | 設定ファイル用（任意）
## /opt/airflow/plugins | プラグインなどの拡張コード
#
# ============================= #
# Airflow 動作設定{environment}
# ============================= #
## AIRFLOW__CORE__EXECUTOR                    | `CeleryExecutor`を使用する
## AIRFLOW__DATABASE__SQL_ALCHEMY_CONN        | `PostgreSQL`をDBに設定する
## AIRFLOW__CELERY__RESULT_BACKEND            | `Celery`の結果保存先をDBに設定する
## AIRFLOW__CELERY__BROKER_URL                | `Celery`のブローカーとして`Redis`を使用する
## AIRFLOW__CORE__FERNET_KEY                  | 暗号化キー（未設定）
## AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION | `DAG`は初期状態で一時停止する
## AIRFLOW__CORE__LOAD_EXAMPLES               | `サンプルDAG`を読み込むか否か
## AIRFLOW__API__AUTH_BACKENDS                | `Basic認証`と`セッション認証`を有効化する
## _PIP_ADDITIONAL_REQUIREMENTS               | コンテナ起動時に追加パッケージ
services:
  # ===================== #
  # Airflow のメタデータDB
  # ===================== #
  postgres:
    image: postgres:13
    environment:
      POSTGRES_USER: airflow
      POSTGRES_PASSWORD: airflow
      POSTGRES_DB: airflow
    volumes:
      - postgres-db-volume:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "airflow"]
      interval: 10s
      retries: 5
      start_period: 5s
    restart: always
  # ======================================================= #
  # Celery Executor（分散処理）のメッセージキューとして利用する
  # ======================================================= #
  redis:
    image: redis:7.2-bookworm # # https://redis.io/blog/redis-adopts-dual-source-available-licensing/
    expose:
      - 6379
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 30s
      retries: 50
      start_period: 30s
    restart: always
  # =================== #
  # AirflowのWeb UI画面
  # =================== #
  airflow-webserver:
    <<: *airflow-common
    command: webserver
    ports:
      - "8080:8080"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
  # ================================ #
  # Airflow：DAGのスケジューリング処理
  # ================================ #
  airflow-scheduler:
    <<: *airflow-common
    command: scheduler
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8974/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
  # ========================================== #
  # Airflow：DAG内のタスクをCelery経由で実行する
  # ========================================== #
  airflow-worker:
    <<: *airflow-common
    command: celery worker
    healthcheck:
      test:
        - "CMD-SHELL"
        - 'celery --app airflow.providers.celery.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}" || celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"'
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    environment:
      <<: *airflow-common-env
      DUMB_INIT_SETSID: "0"
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
  # ========================================== #
  # Event-driven DAG：Triggerer 処理を実行する
  # ========================================== #
  airflow-triggerer:
    <<: *airflow-common
    command: triggerer
    healthcheck:
      test: ["CMD-SHELL", 'airflow jobs check --job-type TriggererJob --hostname "$${HOSTNAME}"']
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
  # ============================================ #
  # 初期化専用：DBマイグレーションやユーザー作成など
  # ============================================ #
  airflow-init:
    <<: *airflow-common
    entrypoint: /bin/bash
    command:
      - -c
      - |
        if [[ -z "${AIRFLOW_UID}" ]]; then
          echo
          echo -e "\033[1;33mWARNING!!!: AIRFLOW_UID not set!\e[0m"
          echo "If you are on Linux, you SHOULD follow the instructions below to set "
          echo "AIRFLOW_UID environment variable, otherwise files will be owned by root."
          echo "For other operating systems you can get rid of the warning with manually created .env file:"
          echo "    See: https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#setting-the-right-airflow-user"
          echo
        fi
        one_meg=1048576
        mem_available=$$(($$(getconf _PHYS_PAGES) * $$(getconf PAGE_SIZE) / one_meg))
        cpus_available=$$(grep -cE 'cpu[0-9]+' /proc/stat)
        disk_available=$$(df / | tail -1 | awk '{print $$4}')
        warning_resources="false"
        if (( mem_available < 4000 )) ; then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough memory available for Docker.\e[0m"
          echo "At least 4GB of memory required. You have $$(numfmt --to iec $$((mem_available * one_meg)))"
          echo
          warning_resources="true"
        fi
        if (( cpus_available < 2 )); then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough CPUS available for Docker.\e[0m"
          echo "At least 2 CPUs recommended. You have $${cpus_available}"
          echo
          warning_resources="true"
        fi
        if (( disk_available < one_meg * 10 )); then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough Disk space available for Docker.\e[0m"
          echo "At least 10 GBs recommended. You have $$(numfmt --to iec $$((disk_available * 1024 )))"
          echo
          warning_resources="true"
        fi
        if [[ $${warning_resources} == "true" ]]; then
          echo
          echo -e "\033[1;33mWARNING!!!: You have not enough resources to run Airflow (see above)!\e[0m"
          echo "Please follow the instructions to increase amount of resources available:"
          echo "   https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#before-you-begin"
          echo
        fi
        mkdir -p /sources/logs /sources/dags /sources/plugins
        chown -R "${AIRFLOW_UID}:0" /sources/{logs,dags,plugins}
        exec /entrypoint airflow version
    environment:
      <<: *airflow-common-env
      _AIRFLOW_DB_MIGRATE: 'true'
      _AIRFLOW_WWW_USER_CREATE: 'true'
      _AIRFLOW_WWW_USER_USERNAME: ${_AIRFLOW_WWW_USER_USERNAME:-airflow}
      _AIRFLOW_WWW_USER_PASSWORD: ${_AIRFLOW_WWW_USER_PASSWORD:-airflow}
      _PIP_ADDITIONAL_REQUIREMENTS: ''
    user: "0:0"
    volumes:
      - ${AIRFLOW_PROJ_DIR:-.}:/sources
  # ================================ #
  # airflow コマンド：デバッグやCLI用
  # ================================ #
  airflow-cli:
    <<: *airflow-common
    profiles:
      - debug
    environment:
      <<: *airflow-common-env
      CONNECTION_CHECK_MAX_COUNT: "0"
    command:
      - bash
      - -c
      - airflow
  # ================================ #
  # Celeryタスク：モニタリングツール
  # ================================ #
  flower:
    <<: *airflow-common
    command: celery flower
    profiles:
      - flower
    ports:
      - "5555:5555"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:5555/"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
  # ================== #
  # JupyterLab(連携用)
  # ================== #
  datasciense:
    container_name: jupyterlab
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "9678:8888"
    volumes:
      - ./Mount_Directory:/Mount_Directory
    environment:
      - LANG=ja_JP.UTF-8
      - TZ=Asia/Tokyo
    command: jupyter lab --ip=0.0.0.0 --allow-root --NotebookApp.token=''

# Airflow本体やDAGなどの永続化
volumes:
  postgres-db-volume:

＃.env

# AirflowユーザーのUID (Linuxユーザーなら id -u で確認)
AIRFLOW_UID=50000

# プロジェクトのルートパス（通常はカレントディレクトリ）| .
AIRFLOW_PROJ_DIR=./AirFlow

# Airflow イメージの指定（任意。カスタムビルドしてる場合に使う）
AIRFLOW_IMAGE_NAME=apache/airflow:2.10.5

# Airflow Web UI の初期ユーザー名とパスワード
_AIRFLOW_WWW_USER_USERNAME=admin
_AIRFLOW_WWW_USER_PASSWORD=password

# Airflow サンプルデータの有無{'true' or 'false'}
# AIRFLOW__CORE__LOAD_EXAMPLES: 'false'

# 追加でインストールする Python パッケージ (例: google-cloud-storage, pandas 等)
# _PIP_ADDITIONAL_REQUIREMENTS=

# （必要に応じて）Airflowの設定ファイルを直接指定する場合
# AIRFLOW_CONFIG=/opt/airflow/config/airflow.cfg

#Dockerfile

FROM ubuntu:22.04

ENV TZ=Asia/Tokyo
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone

## 必要なパッケージ(apt-get) ##
RUN apt-get update && apt-get install -yq --no-install-recommends \
  python3-pip \
  python3-dev \
  sudo \
  vim \
  curl \
  wget \
  unzip \
  tzdata \
  git \
apt-get clean && \
rm -rf /var/lib/apt/lists/*

## 必要なパッケージ(pip) 
COPY requirements.txt .
RUN pip install --upgrade pip && \
    pip install --break-system-packages -r requirements.txt
  
## Jupyter NotebookのPDF出力を日本語に対応する
RUN sed -i 's/\\documentclass\[11pt\]{article}/\\documentclass\[xelatex,ja=standard\]{bxjsarticle}/' \
   /usr/local/share/jupyter/nbconvert/templates/latex/index.tex.j2  

## JupyterLab 作業ディレクトリ
WORKDIR /Mount_Directory
CMD ["jupyter", "lab", "--ip=0.0.0.0", "--allow-root", "--LabApp.token=''"]

#requirements.txt

# 共通 (JupyterLab)
jupyterlab==4.2.5
jupyterlab-language-pack-ja-JP

# データサイエンス
numpy==2.1.1
pandas==2.2.2
matplotlib==3.9.2

＜タイトル＞ JupyterLab×Airflow

#Airflow学習用の環境構築(Airflow×Jupyter)

#ディレクトリ構造#

#Docker-compose.yml

＃.env

#requirements.txt

#参考URL#

コメント（一覧）

コメント（入力画面）

空港MAP(#WIKI)

バックナンバー(年別)

＜タイトル＞ JupyterLab×Airflow

#Airflow学習用の環境構築(Airflow×Jupyter)

#ディレクトリ構造#

#Docker-compose.yml

＃.env

#requirements.txt

#参考URL#

▲ コメント（一覧）

▲ コメント（入力画面）

カテゴリ一覧

空港MAP(#WIKI)

コミュニティ(#準備中#)

バックナンバー(年別)

コメント（一覧）

コメント（入力画面）