Airflow DAG を書き込む

import datetime

from airflow import models

default_dag_args = {
    # The start_date describes when a DAG is valid / can be run. Set this to a
    # fixed point in time rather than dynamically, since it is evaluated every
    # time a DAG is parsed. See:
    # https://airflow.apache.org/faq.html#what-s-the-deal-with-start-date
    "start_date": datetime.datetime(2018, 1, 1),
}

# Define a DAG (directed acyclic graph) of tasks.
# Any task you create within the context manager is automatically added to the
# DAG object.
with models.DAG(
    "composer_sample_simple_greeting",
    schedule_interval=datetime.timedelta(days=1),
    default_args=default_dag_args,
) as dag:

Airflow 1

import datetime

from airflow import models

default_dag_args = {
    # The start_date describes when a DAG is valid / can be run. Set this to a
    # fixed point in time rather than dynamically, since it is evaluated every
    # time a DAG is parsed. See:
    # https://airflow.apache.org/faq.html#what-s-the-deal-with-start-date
    "start_date": datetime.datetime(2018, 1, 1),
}

# Define a DAG (directed acyclic graph) of tasks.
# Any task you create within the context manager is automatically added to the
# DAG object.
with models.DAG(
    "composer_sample_simple_greeting",
    schedule_interval=datetime.timedelta(days=1),
    default_args=default_dag_args,
) as dag:

行う処理を記述するオペレーター。オペレーターをインスタンス化したものは、タスクと呼ばれます。

Airflow 2

from airflow.operators import bash_operator
from airflow.operators import python_operator

    def greeting():
        import logging

        logging.info("Hello World!")

    # An instance of an operator is called a task. In this case, the
    # hello_python task calls the "greeting" Python function.
    hello_python = python_operator.PythonOperator(
        task_id="hello", python_callable=greeting
    )

    # Likewise, the goodbye_bash task calls a Bash script.
    goodbye_bash = bash_operator.BashOperator(
        task_id="bye", bash_command="echo Goodbye."
    )

Airflow 1

from airflow.operators import bash_operator
from airflow.operators import python_operator

    def greeting():
        import logging

        logging.info("Hello World!")

    # An instance of an operator is called a task. In this case, the
    # hello_python task calls the "greeting" Python function.
    hello_python = python_operator.PythonOperator(
        task_id="hello", python_callable=greeting
    )

    # Likewise, the goodbye_bash task calls a Bash script.
    goodbye_bash = bash_operator.BashOperator(
        task_id="bye", bash_command="echo Goodbye."
    )

処理を完了する順序を記述するタスクの関係。

Airflow 2

# Define the order in which the tasks complete by using the >> and <<
# operators. In this example, hello_python executes before goodbye_bash.
hello_python >> goodbye_bash

Airflow 1

# Define the order in which the tasks complete by using the >> and <<
# operators. In this example, hello_python executes before goodbye_bash.
hello_python >> goodbye_bash

Python での完全な DAG ワークフローの例

次のワークフローは、hello_python タスクと goodbye_bash タスクの 2 つのタスクで構成される完全な作業用 DAG テンプレートです。

Airflow 2


import datetime

from airflow import models

from airflow.operators import bash_operator
from airflow.operators import python_operator

default_dag_args = {
    # The start_date describes when a DAG is valid / can be run. Set this to a
    # fixed point in time rather than dynamically, since it is evaluated every
    # time a DAG is parsed. See:
    # https://airflow.apache.org/faq.html#what-s-the-deal-with-start-date
    "start_date": datetime.datetime(2018, 1, 1),
}

# Define a DAG (directed acyclic graph) of tasks.
# Any task you create within the context manager is automatically added to the
# DAG object.
with models.DAG(
    "composer_sample_simple_greeting",
    schedule_interval=datetime.timedelta(days=1),
    default_args=default_dag_args,
) as dag:
    def greeting():
        import logging

        logging.info("Hello World!")

    # An instance of an operator is called a task. In this case, the
    # hello_python task calls the "greeting" Python function.
    hello_python = python_operator.PythonOperator(
        task_id="hello", python_callable=greeting
    )

    # Likewise, the goodbye_bash task calls a Bash script.
    goodbye_bash = bash_operator.BashOperator(
        task_id="bye", bash_command="echo Goodbye."
    )

    # Define the order in which the tasks complete by using the >> and <<
    # operators. In this example, hello_python executes before goodbye_bash.
    hello_python >> goodbye_bash

Airflow 1


import datetime

from airflow import models

from airflow.operators import bash_operator
from airflow.operators import python_operator

default_dag_args = {
    # The start_date describes when a DAG is valid / can be run. Set this to a
    # fixed point in time rather than dynamically, since it is evaluated every
    # time a DAG is parsed. See:
    # https://airflow.apache.org/faq.html#what-s-the-deal-with-start-date
    "start_date": datetime.datetime(2018, 1, 1),
}

# Define a DAG (directed acyclic graph) of tasks.
# Any task you create within the context manager is automatically added to the
# DAG object.
with models.DAG(
    "composer_sample_simple_greeting",
    schedule_interval=datetime.timedelta(days=1),
    default_args=default_dag_args,
) as dag:
    def greeting():
        import logging

        logging.info("Hello World!")

    # An instance of an operator is called a task. In this case, the
    # hello_python task calls the "greeting" Python function.
    hello_python = python_operator.PythonOperator(
        task_id="hello", python_callable=greeting
    )

    # Likewise, the goodbye_bash task calls a Bash script.
    goodbye_bash = bash_operator.BashOperator(
        task_id="bye", bash_command="echo Goodbye."
    )

    # Define the order in which the tasks complete by using the >> and <<
    # operators. In this example, hello_python executes before goodbye_bash.
    hello_python >> goodbye_bash

Airflow のチュートリアルとコンセプト

Airflow DAG の定義に関する詳細については、Airflow チュートリアルと Airflow のコンセプトをご覧ください。

Airflow オペレータ

次の例は、いくつかの一般的な Airflow オペレーターを示しています。Airflow オペレーターの信頼できるリファレンスについては、Apache Airflow API リファレンスをご覧になるか、core、contrib、providers のオペレーターのソースコードをご覧ください。

BashOperator

BashOperator を使用してコマンドラインプログラムを実行します。

Airflow 2

from airflow.operators import bash

    # Create BigQuery output dataset.
    make_bq_dataset = bash.BashOperator(
        task_id="make_bq_dataset",
        # Executing 'bq' command requires Google Cloud SDK which comes
        # preinstalled in Cloud Composer.
        bash_command=f"bq ls {bq_dataset_name} || bq mk {bq_dataset_name}",
    )

Airflow 1

from airflow.operators import bash_operator

    # Create BigQuery output dataset.
    make_bq_dataset = bash_operator.BashOperator(
        task_id="make_bq_dataset",
        # Executing 'bq' command requires Google Cloud SDK which comes
        # preinstalled in Cloud Composer.
        bash_command=f"bq ls {bq_dataset_name} || bq mk {bq_dataset_name}",
    )

Cloud Composer では、ワーカーの bash スクリプトで、指定されたコマンドが実行されます。ワーカーは Debian ベースの Docker コンテナであり、いくつかのパッケージが含まれています。

PythonOperator

PythonOperator を使用して任意の Python コードを実行します。

環境で使用される Cloud Composer イメージのバージョンのパッケージを含むコンテナ内で、Cloud Composer によって Python コードが実行されます。

追加の Python パッケージをインストールするには、Python 依存関係のインストールをご覧ください。

Google Cloud のオペレーター

Google Cloud プロダクトを使用するタスクを実行するには、Google Cloud Airflow のオペレーターを使用します。Cloud Composer によって環境のプロジェクトへの Airflow 接続が自動的に構成されます。

BigQuery のオペレーターは、BigQuery でデータのクエリ、処理を行います。

Airflow 2

from airflow.providers.google.cloud.operators import bigquery
from airflow.providers.google.cloud.transfers import bigquery_to_gcs

    bq_recent_questions_query = bigquery.BigQueryInsertJobOperator(
        task_id="bq_recent_questions_query",
        configuration={
            "query": {
                "query": RECENT_QUESTIONS_QUERY,
                "useLegacySql": False,
                "destinationTable": {
                    "projectId": project_id,
                    "datasetId": bq_dataset_name,
                    "tableId": bq_recent_questions_table_id,
                },
            }
        },
        location=location,
    )

Airflow 1

from airflow.contrib.operators import bigquery_operator

    # Query recent StackOverflow questions.
    bq_recent_questions_query = bigquery_operator.BigQueryOperator(
        task_id="bq_recent_questions_query",
        sql="""
        SELECT owner_display_name, title, view_count
        FROM `bigquery-public-data.stackoverflow.posts_questions`
        WHERE creation_date < CAST('{max_date}' AS TIMESTAMP)
            AND creation_date >= CAST('{min_date}' AS TIMESTAMP)
        ORDER BY view_count DESC
        LIMIT 100
        """.format(
            max_date=max_query_date, min_date=min_query_date
        ),
        use_legacy_sql=False,
        destination_dataset_table=bq_recent_questions_table_id,
    )

Dataflow のオペレーターは、Dataflow で Apache Beam ジョブを実行します。
Cloud Data Fusion のオペレーターは、Cloud Data Fusion パイプラインの管理と実行を行います。
Dataproc のオペレーターは、Dataproc で Hadoop ジョブと Spark ジョブを実行します。
Datastore のオペレーターは、Datastore でデータの読み取りと書き込みを実行します。
AI Platform のオペレーターは、AI Platform でトレーニングジョブと予測ジョブを実行します。
Cloud Storage のオペレーターは、Cloud Storage でデータの読み取りと書き込みを実行します。

EmailOperator

DAG からメールを送信するには、EmailOperator を使用します。Cloud Composer 環境からメールを送信するには、SendGrid を使用するように環境を構成する必要があります。

Airflow 2

from airflow.operators import email

    # Send email confirmation (you will need to set up the email operator
    # See https://cloud.google.com/composer/docs/how-to/managing/creating#notification
    # for more info on configuring the email operator in Cloud Composer)
    email_summary = email.EmailOperator(
        task_id="email_summary",
        to="{{var.value.email}}",
        subject="Sample BigQuery notify data ready",
        html_content="""
        Analyzed Stack Overflow posts data from {min_date} 12AM to {max_date}
        12AM. The most popular question was '{question_title}' with
        {view_count} views. Top 100 questions asked are now available at:
        {export_location}.
        """.format(
            min_date=min_query_date,
            max_date=max_query_date,
            question_title=(
                "{{ ti.xcom_pull(task_ids='bq_read_most_popular', "
                "key='return_value')[0][0] }}"
            ),
            view_count=(
                "{{ ti.xcom_pull(task_ids='bq_read_most_popular', "
                "key='return_value')[0][1] }}"
            ),
            export_location=output_file,
        ),
    )

Airflow 1

from airflow.operators import email_operator

    # Send email confirmation
    email_summary = email_operator.EmailOperator(
        task_id="email_summary",
        to="{{var.value.email}}",
        subject="Sample BigQuery notify data ready",
        html_content="""
        Analyzed Stack Overflow posts data from {min_date} 12AM to {max_date}
        12AM. The most popular question was '{question_title}' with
        {view_count} views. Top 100 questions asked are now available at:
        {export_location}.
        """.format(
            min_date=min_query_date,
            max_date=max_query_date,
            question_title=(
                "{{ ti.xcom_pull(task_ids='bq_read_most_popular', "
                "key='return_value')[0][0] }}"
            ),
            view_count=(
                "{{ ti.xcom_pull(task_ids='bq_read_most_popular', "
                "key='return_value')[0][1] }}"
            ),
            export_location=output_file,
        ),
    )

通知

DAG 内のオペレーターが失敗したときにメール通知を送信するには、email_on_failure を True に設定します。Cloud Composer 環境からメール通知を送信するには、SendGrid を使用するように環境を構成する必要があります。

Airflow 2

from airflow import models

default_dag_args = {
    "start_date": yesterday,
    # Email whenever an Operator in the DAG fails.
    "email": "{{var.value.email}}",
    "email_on_failure": True,
    "email_on_retry": False,
    "retries": 1,
    "retry_delay": datetime.timedelta(minutes=5),
    "project_id": project_id,
}

with models.DAG(
    "composer_sample_bq_notify",
    schedule_interval=datetime.timedelta(weeks=4),
    default_args=default_dag_args,
) as dag:

Airflow 1