Skip to content
This repository has been archived by the owner on Jun 8, 2023. It is now read-only.
/ databricks-api Public archive

A simplified, autogenerated API client interface using the databricks-cli package

License

Notifications You must be signed in to change notification settings

crflynn/databricks-api

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

databricks-api

Please switch to the official Databricks SDK for Python (https://github.com/databricks/databricks-sdk-py) by running the following command:

pip install databricks-sdk

pypi pyversions

[This documentation is auto-generated]

This package provides a simplified interface for the Databricks REST API. The interface is autogenerated on instantiation using the underlying client library used in the official databricks-cli python package.

Install using

pip install databricks-api

The docs here describe the interface for version 0.17.0 of the databricks-cli package for API version 2.0.

The databricks-api package contains a DatabricksAPI class which provides instance attributes for the databricks-cli ApiClient, as well as each of the available service instances. The attributes of a DatabricksAPI instance are:

  • DatabricksAPI.client <databricks_cli.sdk.api_client.ApiClient>
  • DatabricksAPI.jobs <databricks_cli.sdk.service.JobsService>
  • DatabricksAPI.cluster <databricks_cli.sdk.service.ClusterService>
  • DatabricksAPI.policy <databricks_cli.sdk.service.PolicyService>
  • DatabricksAPI.managed_library <databricks_cli.sdk.service.ManagedLibraryService>
  • DatabricksAPI.dbfs <databricks_cli.sdk.service.DbfsService>
  • DatabricksAPI.workspace <databricks_cli.sdk.service.WorkspaceService>
  • DatabricksAPI.secret <databricks_cli.sdk.service.SecretService>
  • DatabricksAPI.groups <databricks_cli.sdk.service.GroupsService>
  • DatabricksAPI.token <databricks_cli.sdk.service.TokenService>
  • DatabricksAPI.instance_pool <databricks_cli.sdk.service.InstancePoolService>
  • DatabricksAPI.delta_pipelines <databricks_cli.sdk.service.DeltaPipelinesService>
  • DatabricksAPI.repos <databricks_cli.sdk.service.ReposService>

To instantiate the client, provide the databricks host and either a token or user and password. Also shown is the full signature of the underlying ApiClient.__init__

from databricks_api import DatabricksAPI

# Provide a host and token
db = DatabricksAPI(
    host="example.cloud.databricks.com",
    token="dpapi123..."
)

# OR a host and user and password
db = DatabricksAPI(
    host="example.cloud.databricks.com",
    user="[email protected]",
    password="password"
)

# Full __init__ signature
db = DatabricksAPI(
    user=None,
    password=None,
    host=None,
    token=None,
    api_version='2.0',
    default_headers={},
    verify=True,
    command_name='',
    jobs_api_version=None
)

Refer to the official documentation on the functionality and required arguments of each method below.

Each of the service instance attributes provides the following public methods:

DatabricksAPI.jobs

db.jobs.cancel_run(
    run_id,
    headers=None,
    version=None,
)

db.jobs.create_job(
    name=None,
    existing_cluster_id=None,
    new_cluster=None,
    libraries=None,
    email_notifications=None,
    timeout_seconds=None,
    max_retries=None,
    min_retry_interval_millis=None,
    retry_on_timeout=None,
    schedule=None,
    notebook_task=None,
    spark_jar_task=None,
    spark_python_task=None,
    spark_submit_task=None,
    max_concurrent_runs=None,
    tasks=None,
    headers=None,
    version=None,
)

db.jobs.delete_job(
    job_id,
    headers=None,
    version=None,
)

db.jobs.delete_run(
    run_id=None,
    headers=None,
    version=None,
)

db.jobs.export_run(
    run_id,
    views_to_export=None,
    headers=None,
    version=None,
)

db.jobs.get_job(
    job_id,
    headers=None,
    version=None,
)

db.jobs.get_run(
    run_id=None,
    headers=None,
    version=None,
)

db.jobs.get_run_output(
    run_id,
    headers=None,
    version=None,
)

db.jobs.list_jobs(
    job_type=None,
    expand_tasks=None,
    limit=None,
    offset=None,
    headers=None,
    version=None,
)

db.jobs.list_runs(
    job_id=None,
    active_only=None,
    completed_only=None,
    offset=None,
    limit=None,
    headers=None,
    version=None,
)

db.jobs.reset_job(
    job_id,
    new_settings,
    headers=None,
    version=None,
)

db.jobs.run_now(
    job_id=None,
    jar_params=None,
    notebook_params=None,
    python_params=None,
    spark_submit_params=None,
    python_named_params=None,
    idempotency_token=None,
    headers=None,
    version=None,
)

db.jobs.submit_run(
    run_name=None,
    existing_cluster_id=None,
    new_cluster=None,
    libraries=None,
    notebook_task=None,
    spark_jar_task=None,
    spark_python_task=None,
    spark_submit_task=None,
    timeout_seconds=None,
    tasks=None,
    headers=None,
    version=None,
)

DatabricksAPI.cluster

db.cluster.create_cluster(
    num_workers=None,
    autoscale=None,
    cluster_name=None,
    spark_version=None,
    spark_conf=None,
    aws_attributes=None,
    node_type_id=None,
    driver_node_type_id=None,
    ssh_public_keys=None,
    custom_tags=None,
    cluster_log_conf=None,
    spark_env_vars=None,
    autotermination_minutes=None,
    enable_elastic_disk=None,
    cluster_source=None,
    instance_pool_id=None,
    headers=None,
)

db.cluster.delete_cluster(
    cluster_id,
    headers=None,
)

db.cluster.edit_cluster(
    cluster_id,
    num_workers=None,
    autoscale=None,
    cluster_name=None,
    spark_version=None,
    spark_conf=None,
    aws_attributes=None,
    node_type_id=None,
    driver_node_type_id=None,
    ssh_public_keys=None,
    custom_tags=None,
    cluster_log_conf=None,
    spark_env_vars=None,
    autotermination_minutes=None,
    enable_elastic_disk=None,
    cluster_source=None,
    instance_pool_id=None,
    headers=None,
)

db.cluster.get_cluster(
    cluster_id,
    headers=None,
)

db.cluster.get_events(
    cluster_id,
    start_time=None,
    end_time=None,
    order=None,
    event_types=None,
    offset=None,
    limit=None,
    headers=None,
)

db.cluster.list_available_zones(headers=None)

db.cluster.list_clusters(headers=None)

db.cluster.list_node_types(headers=None)

db.cluster.list_spark_versions(headers=None)

db.cluster.permanent_delete_cluster(
    cluster_id,
    headers=None,
)

db.cluster.pin_cluster(
    cluster_id,
    headers=None,
)

db.cluster.resize_cluster(
    cluster_id,
    num_workers=None,
    autoscale=None,
    headers=None,
)

db.cluster.restart_cluster(
    cluster_id,
    headers=None,
)

db.cluster.start_cluster(
    cluster_id,
    headers=None,
)

db.cluster.unpin_cluster(
    cluster_id,
    headers=None,
)

DatabricksAPI.policy

db.policy.create_policy(
    policy_name,
    definition,
    headers=None,
)

db.policy.delete_policy(
    policy_id,
    headers=None,
)

db.policy.edit_policy(
    policy_id,
    policy_name,
    definition,
    headers=None,
)

db.policy.get_policy(
    policy_id,
    headers=None,
)

db.policy.list_policies(headers=None)

DatabricksAPI.managed_library

db.managed_library.all_cluster_statuses(headers=None)

db.managed_library.cluster_status(
    cluster_id,
    headers=None,
)

db.managed_library.install_libraries(
    cluster_id,
    libraries=None,
    headers=None,
)

db.managed_library.uninstall_libraries(
    cluster_id,
    libraries=None,
    headers=None,
)

DatabricksAPI.dbfs

db.dbfs.add_block(
    handle,
    data,
    headers=None,
)

db.dbfs.add_block_test(
    handle,
    data,
    headers=None,
)

db.dbfs.close(
    handle,
    headers=None,
)

db.dbfs.close_test(
    handle,
    headers=None,
)

db.dbfs.create(
    path,
    overwrite=None,
    headers=None,
)

db.dbfs.create_test(
    path,
    overwrite=None,
    headers=None,
)

db.dbfs.delete(
    path,
    recursive=None,
    headers=None,
)

db.dbfs.delete_test(
    path,
    recursive=None,
    headers=None,
)

db.dbfs.get_status(
    path,
    headers=None,
)

db.dbfs.get_status_test(
    path,
    headers=None,
)

db.dbfs.list(
    path,
    headers=None,
)

db.dbfs.list_test(
    path,
    headers=None,
)

db.dbfs.mkdirs(
    path,
    headers=None,
)

db.dbfs.mkdirs_test(
    path,
    headers=None,
)

db.dbfs.move(
    source_path,
    destination_path,
    headers=None,
)

db.dbfs.move_test(
    source_path,
    destination_path,
    headers=None,
)

db.dbfs.put(
    path,
    contents=None,
    overwrite=None,
    headers=None,
    src_path=None,
)

db.dbfs.put_test(
    path,
    contents=None,
    overwrite=None,
    headers=None,
    src_path=None,
)

db.dbfs.read(
    path,
    offset=None,
    length=None,
    headers=None,
)

db.dbfs.read_test(
    path,
    offset=None,
    length=None,
    headers=None,
)

DatabricksAPI.workspace

db.workspace.delete(
    path,
    recursive=None,
    headers=None,
)

db.workspace.export_workspace(
    path,
    format=None,
    direct_download=None,
    headers=None,
)

db.workspace.get_status(
    path,
    headers=None,
)

db.workspace.import_workspace(
    path,
    format=None,
    language=None,
    content=None,
    overwrite=None,
    headers=None,
)

db.workspace.list(
    path,
    headers=None,
)

db.workspace.mkdirs(
    path,
    headers=None,
)

DatabricksAPI.secret

db.secret.create_scope(
    scope,
    initial_manage_principal=None,
    scope_backend_type=None,
    backend_azure_keyvault=None,
    headers=None,
)

db.secret.delete_acl(
    scope,
    principal,
    headers=None,
)

db.secret.delete_scope(
    scope,
    headers=None,
)

db.secret.delete_secret(
    scope,
    key,
    headers=None,
)

db.secret.get_acl(
    scope,
    principal,
    headers=None,
)

db.secret.list_acls(
    scope,
    headers=None,
)

db.secret.list_scopes(headers=None)

db.secret.list_secrets(
    scope,
    headers=None,
)

db.secret.put_acl(
    scope,
    principal,
    permission,
    headers=None,
)

db.secret.put_secret(
    scope,
    key,
    string_value=None,
    bytes_value=None,
    headers=None,
)

DatabricksAPI.groups

db.groups.add_to_group(
    parent_name,
    user_name=None,
    group_name=None,
    headers=None,
)

db.groups.create_group(
    group_name,
    headers=None,
)

db.groups.get_group_members(
    group_name,
    headers=None,
)

db.groups.get_groups(headers=None)

db.groups.get_groups_for_principal(
    user_name=None,
    group_name=None,
    headers=None,
)

db.groups.remove_from_group(
    parent_name,
    user_name=None,
    group_name=None,
    headers=None,
)

db.groups.remove_group(
    group_name,
    headers=None,
)

DatabricksAPI.token

db.token.create_token(
    lifetime_seconds=None,
    comment=None,
    headers=None,
)

db.token.list_tokens(headers=None)

db.token.revoke_token(
    token_id,
    headers=None,
)

DatabricksAPI.instance_pool

db.instance_pool.create_instance_pool(
    instance_pool_name=None,
    min_idle_instances=None,
    max_capacity=None,
    aws_attributes=None,
    node_type_id=None,
    custom_tags=None,
    idle_instance_autotermination_minutes=None,
    enable_elastic_disk=None,
    disk_spec=None,
    preloaded_spark_versions=None,
    headers=None,
)

db.instance_pool.delete_instance_pool(
    instance_pool_id=None,
    headers=None,
)

db.instance_pool.edit_instance_pool(
    instance_pool_id,
    instance_pool_name=None,
    min_idle_instances=None,
    max_capacity=None,
    aws_attributes=None,
    node_type_id=None,
    custom_tags=None,
    idle_instance_autotermination_minutes=None,
    enable_elastic_disk=None,
    disk_spec=None,
    preloaded_spark_versions=None,
    headers=None,
)

db.instance_pool.get_instance_pool(
    instance_pool_id=None,
    headers=None,
)

db.instance_pool.list_instance_pools(headers=None)

DatabricksAPI.delta_pipelines

db.delta_pipelines.create(
    id=None,
    name=None,
    storage=None,
    configuration=None,
    clusters=None,
    libraries=None,
    trigger=None,
    filters=None,
    allow_duplicate_names=None,
    headers=None,
)

db.delta_pipelines.delete(
    pipeline_id=None,
    headers=None,
)

db.delta_pipelines.deploy(
    pipeline_id=None,
    id=None,
    name=None,
    storage=None,
    configuration=None,
    clusters=None,
    libraries=None,
    trigger=None,
    filters=None,
    allow_duplicate_names=None,
    headers=None,
)

db.delta_pipelines.get(
    pipeline_id=None,
    headers=None,
)

db.delta_pipelines.list(
    pagination=None,
    headers=None,
)

db.delta_pipelines.reset(
    pipeline_id=None,
    headers=None,
)

db.delta_pipelines.run(
    pipeline_id=None,
    headers=None,
)

db.delta_pipelines.start_update(
    pipeline_id=None,
    full_refresh=None,
    headers=None,
)

db.delta_pipelines.stop(
    pipeline_id=None,
    headers=None,
)

DatabricksAPI.repos

db.repos.create_repo(
    url,
    provider,
    path=None,
    headers=None,
)

db.repos.delete_repo(
    id,
    headers=None,
)

db.repos.get_repo(
    id,
    headers=None,
)

db.repos.list_repos(
    path_prefix=None,
    next_page_token=None,
    headers=None,
)

db.repos.update_repo(
    id,
    branch=None,
    tag=None,
    headers=None,
)

About

A simplified, autogenerated API client interface using the databricks-cli package

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •