def resolve_metric_bundle(
self,
metric_fn_bundle: Iterable[Tuple[MetricConfiguration, Any, dict, dict]],
) -> Dict[Tuple[str, str, str], Any]:
"""For every metric in a set of Metrics to resolve, obtains necessary metric keyword arguments and builds
bundles of the metrics into one large query dictionary so that they are all executed simultaneously. Will fail
if bundling the metrics together is not possible.
Args:
metric_fn_bundle (Iterable[Tuple[MetricConfiguration, Callable, dict]): \
A Dictionary containing a MetricProvider's MetricConfiguration (its unique identifier), its metric provider function
(the function that actually executes the metric), and the arguments to pass to the metric provider function.
A dictionary of metrics defined in the registry and corresponding arguments
Returns:
A dictionary of metric names and their corresponding now-queried values.
"""
resolved_metrics = {}
# We need a different query for each domain (where clause).
queries: Dict[Tuple, dict] = {}
for (
metric_to_resolve,
engine_fn,
compute_domain_kwargs,
accessor_domain_kwargs,
metric_provider_kwargs,
) in metric_fn_bundle:
if not isinstance(compute_domain_kwargs, IDDict):
compute_domain_kwargs = IDDict(compute_domain_kwargs)
domain_id = compute_domain_kwargs.to_id()
if domain_id not in queries:
queries[domain_id] = {
"select": [],
"ids": [],
"domain_kwargs": compute_domain_kwargs,
}
if self.engine.dialect.name == "clickhouse":
queries[domain_id]["select"].append(
engine_fn.label(
metric_to_resolve.metric_name.join(
random.choices(string.ascii_lowercase, k=2)
)
)
)
else:
queries[domain_id]["select"].append(
engine_fn.label(metric_to_resolve.metric_name)
)
queries[domain_id]["ids"].append(metric_to_resolve.id)
for query in queries.values():
domain_kwargs = query["domain_kwargs"]
selectable = self.get_domain_records(
domain_kwargs=domain_kwargs,
)
assert len(query["select"]) == len(query["ids"])
try:
"""
If a custom query is passed, selectable will be TextClause and not formatted
as a subquery wrapped in "(subquery) alias". TextClause must first be converted
to TextualSelect using sa.columns() before it can be converted to type Subquery
"""
if TextClause and isinstance(selectable, TextClause):
res = self.engine.execute(
sa.select(query["select"]).select_from(
selectable.columns().subquery()
)
).fetchall()
else:
res = self.engine.execute(
sa.select(query["select"]).select_from(selectable)
).fetchall()
logger.debug(
f"SqlAlchemyExecutionEngine computed {len(res[0])} metrics on domain_id {IDDict(domain_kwargs).to_id()}"
)
except OperationalError as oe:
exception_message: str = "An SQL execution Exception occurred. "
exception_traceback: str = traceback.format_exc()
exception_message += f'{type(oe).__name__}: "{str(oe)}". Traceback: "{exception_traceback}".'
logger.error(exception_message)
raise ExecutionEngineError(message=exception_message)
assert (
len(res) == 1
), "all bundle-computed metrics must be single-value statistics"
assert len(query["ids"]) == len(
res[0]
), "unexpected number of metrics returned"
for idx, id in enumerate(query["ids"]):
resolved_metrics[id] = convert_to_json_serializable(res[0][idx])
return resolved_metrics
def resolve_metric_bundle(
self, metric_fn_bundle: Iterable[Tuple[MetricConfiguration, Any, dict, dict]],
) -> dict:
"""For every metrics in a set of Metrics to resolve, obtains necessary metric keyword arguments and builds a
bundles the metrics into one large query dictionary so that they are all executed simultaneously. Will fail if
bundling the metrics together is not possible.
Args:
metric_fn_bundle (Iterable[Tuple[MetricConfiguration, Callable, dict]): \
A Dictionary containing a MetricProvider's MetricConfiguration (its unique identifier), its metric provider function
(the function that actually executes the metric), and the arguments to pass to the metric provider function.
metrics (Dict[Tuple, Any]): \
A dictionary of metrics defined in the registry and corresponding arguments
Returns:
A dictionary of metric names and their corresponding now-queried values.
"""
resolved_metrics = dict()
# We need a different query for each domain (where clause).
queries: Dict[Tuple, dict] = dict()
for (
metric_to_resolve,
engine_fn,
compute_domain_kwargs,
accessor_domain_kwargs,
metric_provider_kwargs,
) in metric_fn_bundle:
if not isinstance(compute_domain_kwargs, IDDict):
compute_domain_kwargs = IDDict(compute_domain_kwargs)
domain_id = compute_domain_kwargs.to_id()
if domain_id not in queries:
queries[domain_id] = {
"select": [],
"ids": [],
"domain_kwargs": compute_domain_kwargs,
}
queries[domain_id]["select"].append(
engine_fn.label(metric_to_resolve.metric_name)
)
queries[domain_id]["ids"].append(metric_to_resolve.id)
for query in queries.values():
selectable, compute_domain_kwargs, _ = self.get_compute_domain(
query["domain_kwargs"], domain_type="identity"
)
assert len(query["select"]) == len(query["ids"])
res = self.engine.execute(
sa.select(query["select"]).select_from(selectable)
).fetchall()
logger.debug(
f"SqlAlchemyExecutionEngine computed {len(res[0])} metrics on domain_id {IDDict(compute_domain_kwargs).to_id()}"
)
assert (
len(res) == 1
), "all bundle-computed metrics must be single-value statistics"
assert len(query["ids"]) == len(
res[0]
), "unexpected number of metrics returned"
for idx, id in enumerate(query["ids"]):
resolved_metrics[id] = convert_to_json_serializable(res[0][idx])
# Convert metrics to be serializable
return resolved_metrics