def test_feature_view_inference_success(test_feature_store, dataframe_source):
with prep_file_source(
df=dataframe_source, event_timestamp_column="ts_1"
) as file_source:
fv1 = FeatureView(
name="fv1",
entities=["id"],
ttl=timedelta(minutes=5),
online=True,
batch_source=file_source,
tags={},
)
fv2 = FeatureView(
name="fv2",
entities=["id"],
ttl=timedelta(minutes=5),
online=True,
batch_source=simple_bq_source_using_table_ref_arg(dataframe_source, "ts_1"),
tags={},
)
fv3 = FeatureView(
name="fv3",
entities=["id"],
ttl=timedelta(minutes=5),
online=True,
batch_source=simple_bq_source_using_query_arg(dataframe_source, "ts_1"),
tags={},
)
test_feature_store.apply([fv1, fv2, fv3]) # Register Feature Views
feature_view_1 = test_feature_store.list_feature_views()[0]
feature_view_2 = test_feature_store.list_feature_views()[1]
feature_view_3 = test_feature_store.list_feature_views()[2]
actual_file_source = {
(feature.name, feature.dtype) for feature in feature_view_1.features
}
actual_bq_using_table_ref_arg_source = {
(feature.name, feature.dtype) for feature in feature_view_2.features
}
actual_bq_using_query_arg_source = {
(feature.name, feature.dtype) for feature in feature_view_3.features
}
expected = {
("float_col", ValueType.DOUBLE),
("int64_col", ValueType.INT64),
("string_col", ValueType.STRING),
}
assert (
expected
== actual_file_source
== actual_bq_using_table_ref_arg_source
== actual_bq_using_query_arg_source
)
test_feature_store.teardown()
def test_update_data_sources_with_inferred_event_timestamp_col(
simple_dataset_1):
df_with_two_viable_timestamp_cols = simple_dataset_1.copy(deep=True)
df_with_two_viable_timestamp_cols["ts_2"] = simple_dataset_1["ts_1"]
with prep_file_source(df=simple_dataset_1) as file_source:
data_sources = [
file_source,
simple_bq_source_using_table_ref_arg(simple_dataset_1),
simple_bq_source_using_query_arg(simple_dataset_1),
]
update_data_sources_with_inferred_event_timestamp_col(
data_sources, RepoConfig(provider="local", project="test"))
actual_event_timestamp_cols = [
source.event_timestamp_column for source in data_sources
]
assert actual_event_timestamp_cols == ["ts_1", "ts_1", "ts_1"]
with prep_file_source(df=df_with_two_viable_timestamp_cols) as file_source:
with pytest.raises(RegistryInferenceFailure):
# two viable event_timestamp_columns
update_data_sources_with_inferred_event_timestamp_col(
[file_source], RepoConfig(provider="local", project="test"))
