def get_comparison_baselines(outputs_folder: Path, azure_config: AzureConfig,
comparison_blob_storage_paths: List[Tuple[str, str]]) -> \
List[ComparisonBaseline]:
comparison_baselines = []
for (comparison_name, comparison_path) in comparison_blob_storage_paths:
# Discard the experiment part of the run rec ID, if any.
comparison_path = comparison_path.split(":")[-1]
run_rec_id, blob_path_str = comparison_path.split("/", 1)
run_rec_id = strip_prefix(run_rec_id, AZUREML_RUN_FOLDER_PREFIX)
blob_path = Path(
strip_prefix(blob_path_str, DEFAULT_AML_UPLOAD_DIR + "/"))
run = azure_config.fetch_run(run_rec_id)
(comparison_dataset_path,
comparison_metrics_path) = get_comparison_baseline_paths(
outputs_folder, blob_path, run, DATASET_CSV_FILE_NAME)
# If both dataset.csv and metrics.csv were downloaded successfully, read their contents and
# add a tuple to the comparison data.
if comparison_dataset_path is not None and comparison_metrics_path is not None and \
comparison_dataset_path.exists() and comparison_metrics_path.exists():
comparison_baselines.append(
ComparisonBaseline(comparison_name,
pd.read_csv(comparison_dataset_path),
pd.read_csv(comparison_metrics_path),
run_rec_id))
else:
raise ValueError(
f"could not find comparison data for run {run_rec_id}")
return comparison_baselines
def get_first_child_run(azure_config: AzureConfig) -> Run:
"""
Download first child run in order to download data
:param azure_config:
:return: first child run
"""
if not azure_config.run_recovery_id:
raise ValueError("azure_config.run_recovery_id is not provided.")
hyperdrive_run = azure_config.fetch_run(azure_config.run_recovery_id)
child_runs = fetch_child_runs(hyperdrive_run, status=RunStatus.COMPLETED)
return child_runs[0]
