Skip to main content

Databricks API client interface.

Project description

[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.

The docs here describe the interface for version 0.8.2 of the databricks-cli package for API version 2.0. Assuming there are no major changes to the databricks-cli package structure, this package should continue to work without a required update.

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.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>

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="me@example.com",
    password="password"
)

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

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

DatabricksAPI.jobs.cancel_run(run_id)

DatabricksAPI.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
)

DatabricksAPI.jobs.delete_job(job_id)

DatabricksAPI.jobs.delete_run(run_id=None)

DatabricksAPI.jobs.export_run(
    run_id,
    views_to_export=None
)

DatabricksAPI.jobs.get_job(job_id)

DatabricksAPI.jobs.get_run(run_id=None)

DatabricksAPI.jobs.get_run_output(run_id)

DatabricksAPI.jobs.list_jobs()

DatabricksAPI.jobs.list_runs(
    job_id=None,
    active_only=None,
    completed_only=None,
    offset=None,
    limit=None
)

DatabricksAPI.jobs.reset_job(
    job_id,
    new_settings
)

DatabricksAPI.jobs.run_now(
    job_id=None,
    jar_params=None,
    notebook_params=None,
    python_params=None,
    spark_submit_params=None
)

DatabricksAPI.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
)

DatabricksAPI.cluster

DatabricksAPI.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
)

DatabricksAPI.cluster.delete_cluster(cluster_id)

DatabricksAPI.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
)

DatabricksAPI.cluster.get_cluster(cluster_id)

DatabricksAPI.cluster.list_available_zones()

DatabricksAPI.cluster.list_clusters()

DatabricksAPI.cluster.list_node_types()

DatabricksAPI.cluster.list_spark_versions()

DatabricksAPI.cluster.resize_cluster(
    cluster_id,
    num_workers=None,
    autoscale=None
)

DatabricksAPI.cluster.restart_cluster(cluster_id)

DatabricksAPI.cluster.start_cluster(cluster_id)

DatabricksAPI.managed_library

DatabricksAPI.managed_library.all_cluster_statuses()

DatabricksAPI.managed_library.cluster_status(cluster_id)

DatabricksAPI.managed_library.install_libraries(
    cluster_id,
    libraries=None
)

DatabricksAPI.managed_library.uninstall_libraries(
    cluster_id,
    libraries=None
)

DatabricksAPI.dbfs

DatabricksAPI.dbfs.add_block(
    handle,
    data
)

DatabricksAPI.dbfs.close(handle)

DatabricksAPI.dbfs.create(
    path,
    overwrite=None
)

DatabricksAPI.dbfs.delete(
    path,
    recursive=None
)

DatabricksAPI.dbfs.get_status(path)

DatabricksAPI.dbfs.list(path)

DatabricksAPI.dbfs.mkdirs(path)

DatabricksAPI.dbfs.move(
    source_path,
    destination_path
)

DatabricksAPI.dbfs.put(
    path,
    contents=None,
    overwrite=None
)

DatabricksAPI.dbfs.read(
    path,
    offset=None,
    length=None
)

DatabricksAPI.workspace

DatabricksAPI.workspace.delete(
    path,
    recursive=None
)

DatabricksAPI.workspace.export_workspace(
    path,
    format=None,
    direct_download=None
)

DatabricksAPI.workspace.get_status(path)

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

DatabricksAPI.workspace.list(path)

DatabricksAPI.workspace.mkdirs(path)

DatabricksAPI.secret

DatabricksAPI.secret.create_scope(
    scope,
    initial_manage_principal=None
)

DatabricksAPI.secret.delete_acl(
    scope,
    principal
)

DatabricksAPI.secret.delete_scope(scope)

DatabricksAPI.secret.delete_secret(
    scope,
    key
)

DatabricksAPI.secret.get_acl(
    scope,
    principal
)

DatabricksAPI.secret.list_acls(scope)

DatabricksAPI.secret.list_scopes()

DatabricksAPI.secret.list_secrets(scope)

DatabricksAPI.secret.put_acl(
    scope,
    principal,
    permission
)

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

DatabricksAPI.groups

DatabricksAPI.groups.add_to_group(
    parent_name,
    user_name=None,
    group_name=None
)

DatabricksAPI.groups.create_group(group_name)

DatabricksAPI.groups.get_group_members(group_name)

DatabricksAPI.groups.get_groups()

DatabricksAPI.groups.get_groups_for_principal(
    user_name=None,
    group_name=None
)

DatabricksAPI.groups.remove_from_group(
    parent_name,
    user_name=None,
    group_name=None
)

DatabricksAPI.groups.remove_group(group_name)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

databricks-api-0.1.0.tar.gz (5.5 kB view hashes)

Uploaded Source

Built Distribution

databricks_api-0.1.0-py2.py3-none-any.whl (4.3 kB view hashes)

Uploaded Python 2 Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page