def _get_run_link(self, tracking_uri, run_id):
# if using the default Databricks tracking URI and in a notebook, we can automatically
# figure out the run-link.
if is_databricks_default_tracking_uri(tracking_uri) and (
is_in_databricks_notebook() or is_in_databricks_job()):
# use DBUtils to determine workspace information.
workspace_host, workspace_id = get_workspace_info_from_dbutils()
else:
# in this scenario, we're not able to automatically extract the workspace ID
# to proceed, and users will need to pass in a databricks profile with the scheme:
# databricks://scope:prefix and store the host and workspace-ID as a secret in the
# Databricks Secret Manager with scope=<scope> and key=<prefix>-workspaceid.
workspace_host, workspace_id = get_workspace_info_from_databricks_secrets(
tracking_uri)
if not workspace_id:
print(
"No workspace ID specified; if your Databricks workspaces share the same"
" host URL, you may want to specify the workspace ID (along with the host"
" information in the secret manager) for run lineage tracking. For more"
" details on how to specify this information in the secret manager,"
" please refer to the model registry documentation.")
# retrieve experiment ID of the run for the URL
experiment_id = self.get_run(run_id).info.experiment_id
if workspace_host and run_id and experiment_id:
return construct_run_url(workspace_host, experiment_id, run_id,
workspace_id)
def test_no_throw():
"""
Outside of Databricks the databricks_utils methods should never throw and should only return
None.
"""
assert not databricks_utils.is_in_databricks_notebook()
assert not databricks_utils.is_in_databricks_job()
assert not databricks_utils.is_dbfs_fuse_available()
def request_headers(self):
request_headers = {}
if databricks_utils.is_in_databricks_notebook():
request_headers["notebook_id"] = databricks_utils.get_notebook_id()
if databricks_utils.is_in_databricks_job():
request_headers["job_id"] = databricks_utils.get_job_id()
request_headers["job_run_id"] = databricks_utils.get_job_run_id()
request_headers["job_type"] = databricks_utils.get_job_type()
if databricks_utils.is_in_cluster():
request_headers["cluster_id"] = databricks_utils.get_cluster_id()
return request_headers
def is_flavor_supported_for_associated_package_versions(flavor_name):
"""
:return: True if the specified flavor is supported for the currently-installed versions of its
associated packages
"""
module_name, module_key = FLAVOR_TO_MODULE_NAME_AND_VERSION_INFO_KEY[
flavor_name]
actual_version = importlib.import_module(module_name).__version__
# In Databricks, treat 'pyspark 3.x.y.dev0' as 'pyspark 3.x.y'
if module_name == "pyspark" and (is_in_databricks_notebook()
or is_in_databricks_job()):
actual_version = _strip_dev_version_suffix(actual_version)
if _violates_pep_440(actual_version) or _is_pre_or_dev_release(
actual_version):
return False
min_version, max_version, _ = get_min_max_version_and_pip_release(
module_key)
return _check_version_in_range(actual_version, min_version, max_version)
def in_context(self):
return databricks_utils.is_in_databricks_job()
def in_context(self):
return (databricks_utils.is_in_cluster()
or databricks_utils.is_in_databricks_notebook()
or databricks_utils.is_in_databricks_job())
def in_context(self):
return (databricks_utils.is_in_databricks_job()
and databricks_utils.get_job_type_info() == "NORMAL")
