def set_run_tags(run: Run, azure_config: AzureConfig, model_config_overrides: str) -> None:
"""
Set metadata for the run
:param run: Run to set metadata for.
:param azure_config: The configurations for the present AzureML job
:param model_config_overrides: A string that describes which model parameters were overwritten by commandline
arguments in the present run.
"""
git_information = azure_config.get_git_information()
run.set_tags({
"tag": azure_config.tag,
"model_name": azure_config.model,
"execution_mode": ModelExecutionMode.TRAIN.value if azure_config.train else ModelExecutionMode.TEST.value,
RUN_RECOVERY_ID_KEY_NAME: azure_util.create_run_recovery_id(run=run),
RUN_RECOVERY_FROM_ID_KEY_NAME: azure_config.run_recovery_id,
"build_number": str(azure_config.build_number),
"build_user": azure_config.build_user,
"build_user_email": azure_config.build_user_email,
"source_repository": git_information.repository,
"source_branch": git_information.branch,
"source_id": git_information.commit_id,
"source_message": git_information.commit_message,
"source_author": git_information.commit_author,
"source_dirty": str(git_information.is_dirty),
"overrides": model_config_overrides,
CROSS_VALIDATION_SPLIT_INDEX_TAG_KEY: -1,
})
def set_run_tags(run: Run, azure_config: AzureConfig,
commandline_args: str) -> None:
"""
Set metadata for the run
:param run: Run to set metadata for.
:param azure_config: The configurations for the present AzureML job
:param commandline_args: A string that holds all commandline arguments that were used for the present run.
"""
git_information = get_git_tags(azure_config)
run.set_tags({
"tag":
azure_config.tag,
"model_name":
azure_config.model,
"execution_mode":
ModelExecutionMode.TRAIN.value
if azure_config.train else ModelExecutionMode.TEST.value,
RUN_RECOVERY_ID_KEY_NAME:
azure_util.create_run_recovery_id(run=run),
RUN_RECOVERY_FROM_ID_KEY_NAME:
azure_config.run_recovery_id,
"build_number":
str(azure_config.build_number),
"build_user":
azure_config.build_user,
"build_user_email":
azure_config.build_user_email,
**git_information,
"commandline_args":
commandline_args,
CROSS_VALIDATION_SPLIT_INDEX_TAG_KEY:
-1,
})
# get parent run id, experiment name from file & workspace obj
# create child run (id )
with open(job_info_path, 'r') as f:
job_info_dict = json.load(f)
print("Dictionary read from file " + job_info_dict + "\n")
run_id = job_info_dict["run_id"]
ws = get_ws() # TODO set path and auth
exp = Experiment(workspace=ws, name=experiment_name)
run = Run(exp, run_id)
run.child_run(name=run_name) # TODO: add the step's name
tags = {
"mlflow.source.type": "JOB",
"mlflow.source.name": "train.py",
"mlflow.user": "******"
}
run.set_tags(tags)
# log environment variables
env_dictionary["MLFLOW_EXPERIMENT_ID"] = exp._id
env_dictionary["MLFLOW_RUN_ID"] = run_id
env_dictionary["MLFLOW_TRACKING_URI"] = _get_mlflow_tracking_uri(ws)
env_dictionary["HOME"] = "~/"
else:
# start run
ws = get_ws()
exp = Experiment(workspace=ws, name=experiment_name)
run = exp.start_logging(snapshot_directory="/scripts")
run.child_run(name=run_name) # TODO: add the step's name
tags = {
"mlflow.source.type": "JOB",
"mlflow.source.name": "train.py",
"mlflow.user": "******"
def update_run_tags(run: Run, tags: Dict[str, Any]) -> None:
"""Updates tags for the given run with the provided dictionary"""
run.set_tags({**run.get_tags(), **tags})
