DABs Examples

dabs-cluster-override.yaml

resources:
  jobs:
    <some-unique-programmatic-identifier-for-this-job>:
      # ...
      job_clusters:
        - job_cluster_key: <some-unique-programmatic-identifier-for-this-key>
          new_cluster:
            # Cluster settings.

targets:
  <some-unique-programmatic-identifier-for-this-target>:
    resources:
      jobs:
        <the-matching-programmatic-identifier-for-this-job>:
          # ...
          job_clusters:
            - job_cluster_key: <the-matching-programmatic-identifier-for-this-key>
              # Any more cluster settings to join with the settings from the
              # resources mapping for the matching top-level job_cluster_key.

dabs-dbt-task.yaml

resources:
  jobs:
    my-dbt-job:
      name: my-dbt-job
      tasks:
        - task_key: my-dbt-task
          dbt_task:
            commands:
              - "dbt deps"
              - "dbt seed"
              - "dbt run"
            project_directory: /Users/someone@example.com/Testing
            warehouse_id: 1a111111a1111aa1
          libraries:
            - pypi:
                package: "dbt-databricks>=1.0.0,<2.0.0"

dabs-for-each-task.yaml

resources:
  jobs:
    my_job:
      name: my_job
      tasks:
        - task_key: generate_countries_list
          notebook_task:
            notebook_path: ../src/generate_countries_list.ipnyb
        - task_key: process_countries
          depends_on:
            - task_key: generate_countries_list
          for_each_task:
            inputs: "{{tasks.generate_countries_list.values.countries}}"
            task:
              task_key: process_countries_iteration
              notebook_task:
                notebook_path: ../src/process_countries_notebook.ipnyb

dabs-jar-dependency.yaml

resources:
  jobs:
    my-jar-job:
      name: my-jar-job
      tasks:
        - task_key: my-jar-task
          spark_jar_task:
            main_class_name: org.example.com.Main
          libraries:
            - jar: /Volumes/main/default/my-volume/my-project-0.1.0-SNAPSHOT.jar

dabs-job-overlap-conflict.yaml

# ...
resources:
  jobs:
    my-job:
      name: my-job
      job_clusters:
        - job_cluster_key: my-cluster
          new_cluster:
            spark_version: 13.3.x-scala2.12
            node_type_id: i3.xlarge
            num_workers: 1

targets:
  development:
    resources:
      jobs:
        my-job:
          name: my-job
          job_clusters:
            - job_cluster_key: my-cluster
              new_cluster:
                spark_version: 12.2.x-scala2.12
                num_workers: 2
          # ...

dabs-job-top-level-overlap.yaml

# ...
resources:
  jobs:
    my-job:
      name: my-job
      job_clusters:
        - job_cluster_key: my-cluster
          new_cluster:
            spark_version: 13.3.x-scala2.12

targets:
  development:
    resources:
      jobs:
        my-job:
          name: my-job
          job_clusters:
            - job_cluster_key: my-cluster
              new_cluster:
                node_type_id: i3.xlarge
                num_workers: 1
          # ...

dabs-notebook-task-simple.yaml

resources:
  jobs:
    my-notebook-job:
      name: my-notebook-job
      tasks:
        - task_key: my-notebook-task
          notebook_task:
            notebook_path: ./my-notebook.ipynb
      parameters:
        - name: my_job_run_id
          default: "{{job.run_id}}"

dabs-pipeline-cluster.yaml

# ...
resources:
  pipelines:
    <some-unique-programmatic-identifier-for-this-pipeline>:
      # ...
      clusters:
        - label: default | maintenance
          # Cluster settings.

targets:
  <some-unique-programmatic-identifier-for-this-target>:
    resources:
      pipelines:
        <the-matching-programmatic-identifier-for-this-pipeline>:
          # ...
          clusters:
            - label: default | maintenance
              # Any more cluster settings to join with the settings from the
              # resources mapping for the matching top-level label.
          # ...

dabs-pipeline-overlap-no-conflict.yaml

# ...
resources:
  pipelines:
    my-pipeline:
      clusters:
        - label: default
          node_type_id: i3.xlarge

targets:
  development:
    resources:
      pipelines:
        my-pipeline:
          clusters:
            - label: default
              num_workers: 1
          # ...

dabs-pipeline-overlap-with-conflict.yaml

# ...
resources:
  pipelines:
    my-pipeline:
      clusters:
        - label: default
          node_type_id: i3.xlarge
          num_workers: 1

targets:
  development:
    resources:
      pipelines:
        my-pipeline:
          clusters:
            - label: default
              num_workers: 2
          # ...

dabs-pipeline-task.yaml

resources:
  jobs:
    my-pipeline-job:
      name: my-pipeline-job
      tasks:
        - task_key: my-pipeline-task
          pipeline_task:
            pipeline_id: 11111111-1111-1111-1111-111111111111

dabs-python-script-task.yaml

resources:
  jobs:
    my-python-script-job:
      name: my-python-script-job

      tasks:
        - task_key: my-python-script-task
          spark_python_task:
            python_file: ./my-script.py

dabs-sql-task.yaml

resources:
  jobs:
    my-sql-file-job:
      name: my-sql-file-job
      tasks:
        - task_key: my-sql-file-task
          sql_task:
            file:
              path: /Users/someone@example.com/hello-world.sql
              source: WORKSPACE
            warehouse_id: 1a111111a1111aa1

dabs-task-with-condition.yaml

resources:
  jobs:
    my-job:
      name: my-job
      tasks:
        - task_key: condition_task
          condition_task:
            op: LESS_THAN
            left: "{{job.repair_count}}"
            right: "5"
        - task_key: notebook_task
          depends_on:
            - task_key: condition_task
              outcome: "true"
          notebook_task:
            notebook_path: ../src/notebook.ipynb