def test_feature_set():
return AggregatedFeatureSet(
name="feature_set",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=AggregatedTransform(functions=[
Function(functions.avg, DataType.DOUBLE),
Function(functions.stddev_pop, DataType.DOUBLE),
]),
),
Feature(
name="feature2",
description="test",
transformation=AggregatedTransform(
functions=[Function(functions.count, DataType.INTEGER)]),
),
],
keys=[
KeyFeature(
name="id",
description="The user's Main ID or device ID",
dtype=DataType.BIGINT,
)
],
timestamp=TimestampFeature(),
).with_windows(definitions=["1 week", "2 days"])
def agg_feature_set():
return AggregatedFeatureSet(
name="name",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=AggregatedTransform(
functions=[Function(functions.avg, DataType.DOUBLE)], ),
),
Feature(
name="feature2",
description="test",
transformation=AggregatedTransform(
functions=[Function(functions.avg, DataType.DOUBLE)]),
),
],
keys=[
KeyFeature(
name="id",
description="description",
dtype=DataType.BIGINT,
)
],
timestamp=TimestampFeature(),
)
def test_construct_rolling_windows_with_end_date(
self,
feature_set_dataframe,
rolling_windows_output_feature_set_dataframe_base_date,
):
# given
spark_client = SparkClient()
# arrange
feature_set = AggregatedFeatureSet(
name="feature_set",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=AggregatedTransform(
functions=[
Function(F.avg, DataType.DOUBLE),
Function(F.stddev_pop, DataType.DOUBLE),
],
),
),
Feature(
name="feature2",
description="test",
transformation=AggregatedTransform(
functions=[
Function(F.avg, DataType.DOUBLE),
Function(F.stddev_pop, DataType.DOUBLE),
],
),
),
],
keys=[
KeyFeature(
name="id",
description="The user's Main ID or device ID",
dtype=DataType.INTEGER,
)
],
timestamp=TimestampFeature(),
).with_windows(definitions=["1 day", "1 week"])
# act
output_df = feature_set.construct(
feature_set_dataframe, client=spark_client, end_date="2016-04-18"
).orderBy("timestamp")
target_df = rolling_windows_output_feature_set_dataframe_base_date.orderBy(
feature_set.timestamp_column
).select(feature_set.columns)
# assert
assert_dataframe_equality(output_df, target_df)
def test_feature_set_start_date(
self,
timestamp_c,
feature_set_with_distinct_dataframe,
):
fs = AggregatedFeatureSet(
name="name",
entity="entity",
description="description",
features=[
Feature(
name="feature",
description="test",
transformation=AggregatedTransform(
functions=[Function(functions.sum, DataType.INTEGER)]),
),
],
keys=[
KeyFeature(name="h3",
description="test",
dtype=DataType.STRING)
],
timestamp=timestamp_c,
).with_windows(["10 days", "3 weeks", "90 days"])
# assert
start_date = fs.define_start_date("2016-04-14")
assert start_date == "2016-01-14"
def test_feature_transform_with_distinct(
self,
timestamp_c,
feature_set_with_distinct_dataframe,
target_with_distinct_dataframe,
):
spark_client = SparkClient()
fs = (AggregatedFeatureSet(
name="name",
entity="entity",
description="description",
features=[
Feature(
name="feature",
description="test",
transformation=AggregatedTransform(
functions=[Function(functions.sum, DataType.INTEGER)]),
),
],
keys=[
KeyFeature(name="h3",
description="test",
dtype=DataType.STRING)
],
timestamp=timestamp_c,
).with_windows(["3 days"]).with_distinct(subset=["id"], keep="last"))
# assert
output_df = fs.construct(feature_set_with_distinct_dataframe,
spark_client,
end_date="2020-01-10")
assert_dataframe_equality(output_df, target_with_distinct_dataframe)
def test_h3_feature_set(self, h3_input_df, h3_target_df):
spark_client = SparkClient()
feature_set = AggregatedFeatureSet(
name="h3_test",
entity="h3geolocation",
description="Test",
keys=[
KeyFeature(
name="h3_id",
description="The h3 hash ID",
dtype=DataType.DOUBLE,
transformation=H3HashTransform(
h3_resolutions=[6, 7, 8, 9, 10, 11, 12],
lat_column="lat",
lng_column="lng",
).with_stack(),
)
],
timestamp=TimestampFeature(),
features=[
Feature(
name="house_id",
description="Count of house ids over a day.",
transformation=AggregatedTransform(
functions=[Function(F.count, DataType.BIGINT)]),
),
],
).with_windows(definitions=["1 day"])
output_df = feature_set.construct(h3_input_df,
client=spark_client,
end_date="2016-04-14")
assert_dataframe_equality(output_df, h3_target_df)
def test_aggregations_with_filter_expression(self, spark_context):
# arrange
test_feature = Feature(
name="feature_with_filter",
description="unit test",
transformation=AggregatedTransform(
functions=[
Function(functions.avg, DataType.DOUBLE),
Function(functions.min, DataType.DOUBLE),
Function(functions.max, DataType.DOUBLE),
],
filter_expression="type = 'a'",
),
from_column="feature",
)
target_aggregations = [
agg(
functions.when(functions.expr("type = 'a'"),
functions.col("feature")))
for agg in [functions.avg, functions.min, functions.max]
]
# act
output_aggregations = [
agg.function for agg in test_feature.transformation.aggregations
]
# assert
# cast to string to compare the columns definitions because direct column
# comparison was not working
assert str(target_aggregations) == str(output_aggregations)
def test_feature_transform_with_distinct_empty_subset(
self, timestamp_c, feature_set_with_distinct_dataframe):
spark_client = SparkClient()
with pytest.raises(ValueError,
match="The distinct subset param can't be empty."):
AggregatedFeatureSet(
name="name",
entity="entity",
description="description",
features=[
Feature(
name="feature",
description="test",
transformation=AggregatedTransform(functions=[
Function(functions.sum, DataType.INTEGER)
]),
),
],
keys=[
KeyFeature(name="h3",
description="test",
dtype=DataType.STRING)
],
timestamp=timestamp_c,
).with_windows(["3 days"]).with_distinct(
subset=[],
keep="first").construct(feature_set_with_distinct_dataframe,
spark_client,
end_date="2020-01-10")
def test_construct_without_window(
self,
feature_set_dataframe,
target_df_without_window,
):
# given
spark_client = SparkClient()
# arrange
feature_set = AggregatedFeatureSet(
name="feature_set",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
dtype=DataType.DOUBLE,
transformation=AggregatedTransform(
functions=[Function(F.avg, DataType.DOUBLE)]),
),
Feature(
name="feature2",
description="test",
dtype=DataType.FLOAT,
transformation=AggregatedTransform(
functions=[Function(F.count, DataType.BIGINT)]),
),
],
keys=[
KeyFeature(
name="id",
description="The user's Main ID or device ID",
dtype=DataType.INTEGER,
)
],
timestamp=TimestampFeature(from_column="fixed_ts"),
)
# act
output_df = feature_set.construct(feature_set_dataframe,
client=spark_client)
# assert
assert_dataframe_equality(output_df, target_df_without_window)
def test_unsupported_aggregation(self, feature_set_dataframe):
with pytest.raises(TypeError):
Feature(
name="feature1",
description="unit test",
transformation=AggregatedTransform(
functions=[Function("median", DataType.DOUBLE)]),
)
def test_blank_aggregation(self, feature_set_dataframe):
with pytest.raises(ValueError):
Feature(
name="feature1",
description="unit test",
transformation=AggregatedTransform(
functions=[Function(func="", data_type="")]),
)
def __init__(self):
super(UserChargebacksPipeline, self).__init__(
source=Source(
readers=[
FileReader(
id="chargeback_events",
path="data/order_events/input.csv",
format="csv",
format_options={"header": True},
)
],
query=("""
select
cpf,
timestamp(chargeback_timestamp) as timestamp,
order_id
from
chargeback_events
where
chargeback_timestamp is not null
"""),
),
feature_set=AggregatedFeatureSet(
name="user_chargebacks",
entity="user",
description="Aggregates the total of chargebacks from users in "
"different time windows.",
keys=[
KeyFeature(
name="cpf",
description="User unique identifier, entity key.",
dtype=DataType.STRING,
)
],
timestamp=TimestampFeature(),
features=[
Feature(
name="cpf_chargebacks",
description=
"Total of chargebacks registered on user's CPF",
transformation=AggregatedTransform(functions=[
Function(functions.count, DataType.INTEGER)
]),
from_column="order_id",
),
],
).with_windows(
definitions=["3 days", "7 days", "30 days"]).add_post_hook(
ZeroFillHook()),
sink=Sink(writers=[
LocalHistoricalFSWriter(),
OnlineFeatureStoreWriter(
interval_mode=True,
check_schema_hook=NotCheckSchemaHook(),
debug_mode=True,
),
]),
)
def test_run_agg_with_end_date(self, spark_session):
test_pipeline = FeatureSetPipeline(
spark_client=SparkClient(),
source=Mock(
spec=Source,
readers=[
TableReader(
id="source_a",
database="db",
table="table",
)
],
query="select * from source_a",
),
feature_set=Mock(
spec=AggregatedFeatureSet,
name="feature_set",
entity="entity",
description="description",
keys=[
KeyFeature(
name="user_id",
description="The user's Main ID or device ID",
dtype=DataType.INTEGER,
)
],
timestamp=TimestampFeature(from_column="ts"),
features=[
Feature(
name="listing_page_viewed__rent_per_month",
description="Average of something.",
transformation=AggregatedTransform(functions=[
Function(functions.avg, DataType.FLOAT),
Function(functions.stddev_pop, DataType.FLOAT),
], ),
),
],
),
sink=Mock(
spec=Sink,
writers=[HistoricalFeatureStoreWriter(db_config=None)],
),
)
# feature_set need to return a real df for streaming validation
sample_df = spark_session.createDataFrame([{
"a": "x",
"b": "y",
"c": "3"
}])
test_pipeline.feature_set.construct.return_value = sample_df
test_pipeline.run(end_date="2016-04-18")
test_pipeline.source.construct.assert_called_once()
test_pipeline.feature_set.construct.assert_called_once()
test_pipeline.sink.flush.assert_called_once()
test_pipeline.sink.validate.assert_called_once()
def test_agg_feature_set_with_window(self, key_id, timestamp_c, dataframe,
rolling_windows_agg_dataframe):
spark_client = SparkClient()
fs = AggregatedFeatureSet(
name="name",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="unit test",
transformation=AggregatedTransform(
functions=[Function(functions.avg, DataType.FLOAT)]),
),
Feature(
name="feature2",
description="unit test",
transformation=AggregatedTransform(
functions=[Function(functions.avg, DataType.FLOAT)]),
),
],
keys=[key_id],
timestamp=timestamp_c,
).with_windows(definitions=["1 week"])
# raises without end date
with pytest.raises(ValueError):
_ = fs.construct(dataframe, spark_client)
# filters with date smaller then mocked max
output_df = fs.construct(dataframe,
spark_client,
end_date="2016-04-17")
assert output_df.count() < rolling_windows_agg_dataframe.count()
output_df = fs.construct(dataframe,
spark_client,
end_date="2016-05-01")
assert_dataframe_equality(output_df, rolling_windows_agg_dataframe)
def test_feature_transform(self, feature_set_dataframe, target_df_agg):
test_feature = Feature(
name="feature1",
description="unit test",
transformation=AggregatedTransform(functions=[
Function(functions.avg, DataType.DOUBLE),
Function(functions.stddev_pop, DataType.DOUBLE),
]),
)
# aggregated feature transform won't run transformations
# and depends on the feature set
with pytest.raises(NotImplementedError):
_ = test_feature.transform(feature_set_dataframe)
def test_anonymous_function(self):
with pytest.raises(
AttributeError,
match=
"Anonymous functions are not supported on AggregatedTransform.",
):
Feature(
name="feature1",
description="unit test",
transformation=AggregatedTransform(functions=[
Function(func=partial(functions.count),
data_type=DataType.INTEGER)
]),
).get_output_columns()
def test_output_columns(self):
test_feature = Feature(
name="feature1",
description="unit test",
transformation=AggregatedTransform(functions=[
Function(functions.avg, DataType.DOUBLE),
Function(functions.stddev_pop, DataType.DOUBLE),
]),
)
df_columns = test_feature.get_output_columns()
assert all([
a == b for a, b in zip(
df_columns,
["feature1__avg", "feature1__stddev_pop"],
)
])
def test_feature_set_with_invalid_feature(self, key_id, timestamp_c,
dataframe):
spark_client = SparkClient()
with pytest.raises(ValueError):
FeatureSet(
name="name",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=AggregatedTransform(
functions=[Function(F.avg, DataType.FLOAT)]),
),
],
keys=[key_id],
timestamp=timestamp_c,
).construct(dataframe, spark_client)
def test_construct_with_pivot(
self,
feature_set_df_pivot,
target_df_pivot_agg,
):
# given
spark_client = SparkClient()
# arrange
feature_set = AggregatedFeatureSet(
name="feature_set",
entity="entity",
description="description",
features=[
Feature(
name="feature",
description="unit test",
transformation=AggregatedTransform(functions=[
Function(F.avg, DataType.FLOAT),
Function(F.stddev_pop, DataType.DOUBLE),
], ),
from_column="feature1",
)
],
keys=[
KeyFeature(
name="id",
description="The user's Main ID or device ID",
dtype=DataType.INTEGER,
)
],
timestamp=TimestampFeature(from_column="fixed_ts"),
).with_pivot("pivot_col", ["S", "N"])
# act
output_df = feature_set.construct(feature_set_df_pivot,
client=spark_client)
# assert
assert_dataframe_equality(output_df, target_df_pivot_agg)
def feature_set_incremental():
key_features = [
KeyFeature(name="id", description="Description", dtype=DataType.INTEGER)
]
ts_feature = TimestampFeature(from_column=TIMESTAMP_COLUMN)
features = [
Feature(
name="feature",
description="test",
transformation=AggregatedTransform(
functions=[Function(functions.sum, DataType.INTEGER)]
),
),
]
return AggregatedFeatureSet(
"feature_set",
"entity",
"description",
keys=key_features,
timestamp=ts_feature,
features=features,
)
def test_construct_rolling_windows_without_end_date(
self, feature_set_dataframe, rolling_windows_output_feature_set_dataframe
):
# given
spark_client = SparkClient()
# arrange
feature_set = AggregatedFeatureSet(
name="feature_set",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=AggregatedTransform(
functions=[
Function(F.avg, DataType.DOUBLE),
Function(F.stddev_pop, DataType.DOUBLE),
],
),
),
],
keys=[
KeyFeature(
name="id",
description="The user's Main ID or device ID",
dtype=DataType.INTEGER,
)
],
timestamp=TimestampFeature(),
).with_windows(definitions=["1 day", "1 week"],)
# act & assert
with pytest.raises(ValueError):
_ = feature_set.construct(feature_set_dataframe, client=spark_client)
def test_feature_transform_with_data_type_array(self, spark_context,
spark_session):
# arrange
input_data = [
{
"id": 1,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature": 10
},
{
"id": 1,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature": 20
},
{
"id": 1,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature": 30
},
{
"id": 2,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature": 10
},
]
target_data = [
{
"id": 1,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature__collect_set": [30.0, 20.0, 10.0],
},
{
"id": 2,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature__collect_set": [10.0],
},
]
input_df = create_df_from_collection(
input_data, spark_context, spark_session).withColumn(
"timestamp",
functions.to_timestamp(functions.col("timestamp")))
target_df = create_df_from_collection(
target_data, spark_context, spark_session).withColumn(
"timestamp",
functions.to_timestamp(functions.col("timestamp")))
fs = AggregatedFeatureSet(
name="name",
entity="entity",
description="description",
keys=[
KeyFeature(name="id",
description="test",
dtype=DataType.INTEGER)
],
timestamp=TimestampFeature(),
features=[
Feature(
name="feature",
description="aggregations with ",
dtype=DataType.BIGINT,
transformation=AggregatedTransform(functions=[
Function(functions.collect_set, DataType.ARRAY_FLOAT),
], ),
from_column="feature",
),
],
)
# act
output_df = fs.construct(input_df, SparkClient())
# assert
assert_dataframe_equality(target_df, output_df)
def test_feature_transform_with_filter_expression(self, spark_context,
spark_session):
# arrange
input_data = [
{
"id": 1,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature": 10,
"type": "a",
},
{
"id": 1,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature": 20,
"type": "a",
},
{
"id": 1,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature": 30,
"type": "b",
},
{
"id": 2,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature": 10,
"type": "a",
},
]
target_data = [
{
"id": 1,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature_only_type_a__avg": 15.0,
"feature_only_type_a__min": 10,
"feature_only_type_a__max": 20,
},
{
"id": 2,
"timestamp": "2020-04-22T00:00:00+00:00",
"feature_only_type_a__avg": 10.0,
"feature_only_type_a__min": 10,
"feature_only_type_a__max": 10,
},
]
input_df = create_df_from_collection(
input_data, spark_context, spark_session).withColumn(
"timestamp",
functions.to_timestamp(functions.col("timestamp")))
target_df = create_df_from_collection(
target_data, spark_context, spark_session).withColumn(
"timestamp",
functions.to_timestamp(functions.col("timestamp")))
fs = AggregatedFeatureSet(
name="name",
entity="entity",
description="description",
keys=[
KeyFeature(name="id",
description="test",
dtype=DataType.INTEGER)
],
timestamp=TimestampFeature(),
features=[
Feature(
name="feature_only_type_a",
description="aggregations only when type = a",
dtype=DataType.BIGINT,
transformation=AggregatedTransform(
functions=[
Function(functions.avg, DataType.FLOAT),
Function(functions.min, DataType.FLOAT),
Function(functions.max, DataType.FLOAT),
],
filter_expression="type = 'a'",
),
from_column="feature",
),
],
)
# act
output_df = fs.construct(input_df, SparkClient())
# assert
assert_dataframe_equality(target_df, output_df)
def test_get_schema(self):
expected_schema = [
{
"column_name": "id",
"type": LongType(),
"primary_key": True
},
{
"column_name": "timestamp",
"type": TimestampType(),
"primary_key": False
},
{
"column_name": "feature1__avg_over_1_week_rolling_windows",
"type": DoubleType(),
"primary_key": False,
},
{
"column_name": "feature1__avg_over_2_days_rolling_windows",
"type": DoubleType(),
"primary_key": False,
},
{
"column_name":
"feature1__stddev_pop_over_1_week_rolling_windows",
"type": FloatType(),
"primary_key": False,
},
{
"column_name":
"feature1__stddev_pop_over_2_days_rolling_windows",
"type": FloatType(),
"primary_key": False,
},
{
"column_name": "feature2__count_over_1_week_rolling_windows",
"type": ArrayType(StringType(), True),
"primary_key": False,
},
{
"column_name": "feature2__count_over_2_days_rolling_windows",
"type": ArrayType(StringType(), True),
"primary_key": False,
},
]
feature_set = AggregatedFeatureSet(
name="feature_set",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=AggregatedTransform(functions=[
Function(functions.avg, DataType.DOUBLE),
Function(functions.stddev_pop, DataType.FLOAT),
], ),
),
Feature(
name="feature2",
description="test",
transformation=AggregatedTransform(functions=[
Function(functions.count, DataType.ARRAY_STRING)
]),
),
],
keys=[
KeyFeature(
name="id",
description="The user's Main ID or device ID",
dtype=DataType.BIGINT,
)
],
timestamp=TimestampFeature(),
).with_windows(definitions=["1 week", "2 days"])
schema = feature_set.get_schema()
assert schema == expected_schema