def _create_run(uri, experiment_id, work_dir, entry_point):
"""
Create a ``Run`` against the current MLflow tracking server, logging metadata (e.g. the URI,
entry point, and parameters of the project) about the run. Return an ``ActiveRun`` that can be
used to report additional data about the run (metrics/params) to the tracking server.
"""
if _is_local_uri(uri):
source_name = tracking.utils._get_git_url_if_present(_expand_uri(uri))
else:
source_name = _expand_uri(uri)
active_run = tracking.get_service().create_run(
experiment_id=experiment_id,
source_name=source_name,
source_version=_get_git_commit(work_dir),
entry_point_name=entry_point,
source_type=SourceType.PROJECT)
return active_run
def _build_docker_image(work_dir, project, active_run):
"""
Build a docker image containing the project in `work_dir`, using the base image and tagging the
built image with the project name specified by `project`.
"""
if not project.name:
raise ExecutionException(
"Project name in MLProject must be specified when using docker "
"for image tagging.")
tag_name = "mlflow-{name}-{version}".format(
name=(project.name if project.name else "docker-project"),
version=_get_git_commit(work_dir)[:7],
)
dockerfile = ("FROM {imagename}\n"
"LABEL Name={tag_name}\n"
"COPY {build_context_path}/* /mlflow/projects/code/\n"
"WORKDIR /mlflow/projects/code/\n").format(
imagename=project.docker_env.get('image'),
tag_name=tag_name,
build_context_path=_PROJECT_TAR_ARCHIVE_NAME)
build_ctx_path = _create_docker_build_ctx(work_dir, dockerfile)
with open(build_ctx_path, 'rb') as docker_build_ctx:
_logger.info("=== Building docker image %s ===", tag_name)
client = docker.from_env()
image = client.images.build(tag=tag_name,
forcerm=True,
dockerfile=posixpath.join(
_PROJECT_TAR_ARCHIVE_NAME,
_GENERATED_DOCKERFILE_NAME),
fileobj=docker_build_ctx,
custom_context=True,
encoding="gzip")
try:
os.remove(build_ctx_path)
except Exception: # pylint: disable=broad-except
_logger.info("Temporary docker context file %s was not deleted.",
build_ctx_path)
tracking.MlflowClient().set_tag(active_run.info.run_uuid,
MLFLOW_DOCKER_IMAGE_NAME, tag_name)
tracking.MlflowClient().set_tag(active_run.info.run_uuid,
MLFLOW_DOCKER_IMAGE_ID, image[0].id)
return tag_name
def run_databricks(uri, entry_point, version, parameters, experiment_id,
cluster_spec, git_username, git_password):
"""
Runs the project at the specified URI on Databricks, returning a `SubmittedRun` that can be
used to query the run's status or wait for the resulting Databricks Job run to terminate.
"""
tracking_uri = tracking.get_tracking_uri()
_before_run_validations(tracking_uri, cluster_spec)
work_dir = _fetch_and_clean_project(uri=uri,
version=version,
git_username=git_username,
git_password=git_password)
project = _project_spec.load_project(work_dir)
project.get_entry_point(entry_point)._validate_parameters(parameters)
dbfs_fuse_uri = _upload_project_to_dbfs(work_dir, experiment_id)
remote_run = tracking.get_service().create_run(
experiment_id=experiment_id,
source_name=_expand_uri(uri),
source_version=_get_git_commit(work_dir),
entry_point_name=entry_point,
source_type=SourceType.PROJECT)
env_vars = {
tracking._TRACKING_URI_ENV_VAR: tracking_uri,
tracking._EXPERIMENT_ID_ENV_VAR: experiment_id,
}
run_id = remote_run.info.run_uuid
eprint("=== Running entry point %s of project %s on Databricks. ===" %
(entry_point, uri))
# Launch run on Databricks
with open(cluster_spec, 'r') as handle:
try:
cluster_spec = json.load(handle)
except ValueError:
eprint(
"Error when attempting to load and parse JSON cluster spec from file "
"%s. " % cluster_spec)
raise
command = _get_databricks_run_cmd(dbfs_fuse_uri, run_id, entry_point,
parameters)
db_run_id = _run_shell_command_job(uri, command, env_vars, cluster_spec)
return DatabricksSubmittedRun(db_run_id, run_id)