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)
source_version = _get_git_commit(work_dir)
existing_run = fluent.active_run()
if existing_run:
parent_run_id = existing_run.info.run_uuid
else:
parent_run_id = None
tags = {
MLFLOW_SOURCE_NAME: source_name,
MLFLOW_SOURCE_TYPE: SourceType.to_string(SourceType.PROJECT),
MLFLOW_PROJECT_ENTRY_POINT: entry_point
}
if source_version is not None:
tags[MLFLOW_GIT_COMMIT] = source_version
if parent_run_id is not None:
tags[MLFLOW_PARENT_RUN_ID] = parent_run_id
active_run = tracking.MlflowClient().create_run(experiment_id=experiment_id, tags=tags)
return active_run
def _get_docker_tag_name(project_name, work_dir):
"""Returns an appropriate Docker tag for a project based on name and git hash."""
project_name = project_name if project_name else "docker-project"
# Optionally include first 7 digits of git SHA in tag name, if available.
git_commit = _get_git_commit(work_dir)
version_string = "-" + git_commit[:7] if git_commit else ""
return "mlflow-" + project_name + version_string
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_id,
MLFLOW_DOCKER_IMAGE_NAME, tag_name)
tracking.MlflowClient().set_tag(active_run.info.run_id,
MLFLOW_DOCKER_IMAGE_ID, image[0].id)
return tag_name
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)
existing_run = fluent.active_run()
if existing_run:
parent_run_id = existing_run.info.run_uuid
else:
parent_run_id = None
active_run = tracking.MlflowClient().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,
parent_run_id=parent_run_id)
return active_run
