def _ingest_quotes_featureset(self):
quotes_set = FeatureSet("stock-quotes", entities=[Entity("ticker")])
flow = quotes_set.graph
flow.to("MyMap", multiplier=3).to("storey.Extend",
_fn="({'z': event['bid'] * 77})").to(
"storey.Filter",
"filter",
_fn="(event['bid'] > 51.92)").to(
FeaturesetValidator())
quotes_set.add_aggregation("asks", "ask", ["sum", "max"], ["1h", "5h"],
"10m")
quotes_set.add_aggregation("bids", "bid", ["min", "max"], ["1h"],
"10m")
df = fs.infer_metadata(
quotes_set,
quotes,
entity_columns=["ticker"],
timestamp_key="time",
options=fs.InferOptions.default(),
)
self._logger.info(f"quotes spec: {quotes_set.spec.to_yaml()}")
assert df["zz"].mean() == 9, "map didnt set the zz column properly"
quotes_set["bid"].validator = MinMaxValidator(min=52, severity="info")
quotes_set.plot(str(self.results_path / "pipe.png"),
rankdir="LR",
with_targets=True)
df = fs.ingest(quotes_set, quotes, return_df=True)
self._logger.info(f"output df:\n{df}")
assert quotes_set.status.stats.get("asks_sum_1h"), "stats not created"
def test_feature_set():
myset = FeatureSet("set1", entities=[Entity("key")])
myset["f1"] = Feature(ValueType.INT64, description="my f1")
assert list(myset.spec.entities.keys()) == ["key"], "index wasnt set"
assert list(myset.spec.features.keys()) == ["f1"], "feature wasnt set"