def transform_df_to_metric(self, data: pd.DataFrame) -> Optional[Metric]:
if data.empty or self.tsdb_column not in data.columns:
return None
values = data[self.tsdb_column].reset_index().to_numpy()
describe = data[self.tsdb_column].describe().to_dict()
return Metric(
name=self.metric_name,
start_timestamp=str(data.index[0]),
end_timestamp=str(data.index[-1]),
headers=self.headers,
values=[(str(timestamp), float(value)) for timestamp, value in values],
min=describe["min"],
avg=describe["mean"],
max=describe["max"],
)
def get_endpoint_metrics(
self,
access_key: str,
project: str,
endpoint_id: str,
metrics: List[str],
start: str = "now-1h",
end: str = "now",
) -> Dict[str, Metric]:
if not metrics:
raise MLRunInvalidArgumentError("Metric names must be provided")
path = config.model_endpoint_monitoring.store_prefixes.default.format(
project=project, kind=mlrun.api.schemas.ModelMonitoringStoreKinds.EVENTS
)
_, container, path = parse_model_endpoint_store_prefix(path)
client = get_frames_client(
token=access_key, address=config.v3io_framesd, container=container,
)
data = client.read(
backend="tsdb",
table=path,
columns=["endpoint_id", *metrics],
filter=f"endpoint_id=='{endpoint_id}'",
start=start,
end=end,
)
data_dict = data.to_dict()
metrics_mapping = {}
for metric in metrics:
metric_data = data_dict.get(metric)
if metric_data is None:
continue
values = [
(str(timestamp), value) for timestamp, value in metric_data.items()
]
metrics_mapping[metric] = Metric(name=metric, values=values)
return metrics_mapping
async def get_endpoint_metrics(
access_key: str,
project: str,
endpoint_id: str,
metrics: List[str],
start: str = "now-1h",
end: str = "now",
) -> Dict[str, Metric]:
if not metrics:
raise MLRunInvalidArgumentError("Metric names must be provided")
client = get_frames_client(
token=access_key,
address=config.v3io_framesd,
container=config.model_endpoint_monitoring.container,
)
data = await run_in_threadpool(
client.read,
backend="tsdb",
table=f"{project}/{ENDPOINT_EVENTS_TABLE_PATH}",
columns=["endpoint_id", *metrics],
filter=f"endpoint_id=='{endpoint_id}'",
start=start,
end=end,
)
data_dict = data.to_dict()
metrics_mapping = {}
for metric in metrics:
metric_data = data_dict.get(metric)
if metric_data is None:
continue
values = [(str(timestamp), value) for timestamp, value in metric_data.items()]
metrics_mapping[metric] = Metric(name=metric, values=values)
return metrics_mapping