def test_purge(self):
key = "patient_id"
fset = fs.FeatureSet("purge",
entities=[Entity(key)],
timestamp_key="timestamp")
path = os.path.relpath(str(self.assets_path / "testdata.csv"))
source = CSVSource(
"mycsv",
path=path,
time_field="timestamp",
)
targets = [
CSVTarget(),
CSVTarget(name="specified-path",
path="v3io:///bigdata/csv-purge-test.csv"),
ParquetTarget(partitioned=True, partition_cols=["timestamp"]),
NoSqlTarget(),
]
fset.set_targets(
targets=targets,
with_defaults=False,
)
fs.ingest(fset, source)
verify_purge(fset, targets)
fs.ingest(fset, source)
targets_to_purge = targets[:-1]
verify_purge(fset, targets_to_purge)
def test_ordered_pandas_asof_merge(self):
targets = [ParquetTarget(), NoSqlTarget()]
left_set, left = prepare_feature_set(
"left", "ticker", trades, timestamp_key="time", targets=targets
)
right_set, right = prepare_feature_set(
"right", "ticker", quotes, timestamp_key="time", targets=targets
)
features = ["left.*", "right.*"]
feature_vector = fs.FeatureVector("test_fv", features, description="test FV")
res = fs.get_offline_features(feature_vector, entity_timestamp_column="time")
res = res.to_dataframe()
assert res.shape[0] == left.shape[0]
def test_overwrite(self):
df1 = pd.DataFrame({"name": ["ABC", "DEF", "GHI"], "value": [1, 2, 3]})
df2 = pd.DataFrame({"name": ["JKL", "MNO", "PQR"], "value": [4, 5, 6]})
fset = fs.FeatureSet(name="overwrite-fs", entities=[fs.Entity("name")])
fs.ingest(fset, df1, targets=[CSVTarget(), ParquetTarget(), NoSqlTarget()])
features = ["overwrite-fs.*"]
fvec = fs.FeatureVector("overwrite-vec", features=features)
csv_path = fset.get_target_path(name="csv")
csv_df = pd.read_csv(csv_path)
assert (
df1.set_index(keys="name")
.sort_index()
.equals(csv_df.set_index(keys="name").sort_index())
)
parquet_path = fset.get_target_path(name="parquet")
parquet_df = pd.read_parquet(parquet_path)
assert df1.set_index(keys="name").sort_index().equals(parquet_df.sort_index())
svc = fs.get_online_feature_service(fvec)
resp = svc.get(entity_rows=[{"name": "GHI"}])
assert resp[0]["value"] == 3
svc.close()
fs.ingest(fset, df2)
csv_path = fset.get_target_path(name="csv")
csv_df = pd.read_csv(csv_path)
assert (
df1.set_index(keys="name")
.sort_index()
.equals(csv_df.set_index(keys="name").sort_index())
)
parquet_path = fset.get_target_path(name="parquet")
parquet_df = pd.read_parquet(parquet_path)
assert df2.set_index(keys="name").sort_index().equals(parquet_df.sort_index())
svc = fs.get_online_feature_service(fvec)
resp = svc.get(entity_rows=[{"name": "GHI"}])
assert resp[0] is None
resp = svc.get(entity_rows=[{"name": "PQR"}])
assert resp[0]["value"] == 6
svc.close()
def test_overwrite_specified_nosql_path(self):
df1 = pd.DataFrame({"name": ["ABC", "DEF", "GHI"], "value": [1, 2, 3]})
df2 = pd.DataFrame({"name": ["JKL", "MNO", "PQR"], "value": [4, 5, 6]})
targets = [NoSqlTarget(path="v3io:///bigdata/overwrite-spec")]
fset = fs.FeatureSet(name="overwrite-spec-path",
entities=[fs.Entity("name")])
features = ["overwrite-spec-path.*"]
fvec = fs.FeatureVector("overwrite-spec-path-fvec", features=features)
fs.ingest(fset, df1, targets=targets)
fs.ingest(fset, df2, targets=targets)
svc = fs.get_online_feature_service(fvec)
resp = svc.get(entity_rows=[{"name": "PQR"}])
assert resp[0]["value"] == 6
resp = svc.get(entity_rows=[{"name": "ABC"}])
assert resp[0] is None
svc.close()
def test_schedule_on_filtered_by_time(self, partitioned):
name = f"sched-time-{str(partitioned)}"
now = datetime.now()
path = "v3io:///bigdata/bla.parquet"
fsys = fsspec.filesystem(v3iofs.fs.V3ioFS.protocol)
pd.DataFrame({
"time": [
pd.Timestamp("2021-01-10 10:00:00"),
pd.Timestamp("2021-01-10 11:00:00"),
],
"first_name": ["moshe", "yosi"],
"data": [2000, 10],
}).to_parquet(path=path, filesystem=fsys)
cron_trigger = "*/2 * * * *"
source = ParquetSource("myparquet",
path=path,
time_field="time",
schedule=cron_trigger)
feature_set = fs.FeatureSet(
name=name,
entities=[fs.Entity("first_name")],
timestamp_key="time",
engine="spark",
)
if partitioned:
targets = [
NoSqlTarget(),
ParquetTarget(
name="tar1",
path="v3io:///bigdata/fs1/",
partitioned=True,
partition_cols=["time"],
),
]
else:
targets = [
ParquetTarget(name="tar2",
path="v3io:///bigdata/fs2/",
partitioned=False),
NoSqlTarget(),
]
fs.ingest(
feature_set,
source,
run_config=fs.RunConfig(local=False),
targets=targets,
spark_context=self.spark_service,
)
# ingest starts every second minute and it takes ~90 seconds to finish.
if (now.minute % 2) == 0:
sleep(60 - now.second + 60 + 90)
else:
sleep(60 - now.second + 90)
features = [f"{name}.*"]
vec = fs.FeatureVector("sched_test-vec", features)
svc = fs.get_online_feature_service(vec)
resp = svc.get([{"first_name": "yosi"}, {"first_name": "moshe"}])
assert resp[0]["data"] == 10
assert resp[1]["data"] == 2000
pd.DataFrame({
"time": [
pd.Timestamp("2021-01-10 12:00:00"),
pd.Timestamp("2021-01-10 13:00:00"),
now + pd.Timedelta(minutes=10),
pd.Timestamp("2021-01-09 13:00:00"),
],
"first_name": ["moshe", "dina", "katya", "uri"],
"data": [50, 10, 25, 30],
}).to_parquet(path=path)
sleep(120)
resp = svc.get([
{
"first_name": "yosi"
},
{
"first_name": "moshe"
},
{
"first_name": "katya"
},
{
"first_name": "dina"
},
{
"first_name": "uri"
},
])
assert resp[0]["data"] == 10
assert resp[1]["data"] == 50
assert resp[2] is None
assert resp[3]["data"] == 10
assert resp[4] is None
svc.close()
# check offline
resp = fs.get_offline_features(vec)
assert len(resp.to_dataframe() == 4)
assert "uri" not in resp.to_dataframe(
) and "katya" not in resp.to_dataframe()