def test_output_columns(self):
# arrange
h3_feature = Feature(
name="new_feature",
description="unit test",
dtype=DataType.STRING,
transformation=H3HashTransform(
h3_resolutions=[6, 7, 8, 9, 10, 11, 12],
lat_column="lat",
lng_column="lng",
),
)
target_columns = [
"lat_lng__h3_hash__6",
"lat_lng__h3_hash__7",
"lat_lng__h3_hash__8",
"lat_lng__h3_hash__9",
"lat_lng__h3_hash__10",
"lat_lng__h3_hash__11",
"lat_lng__h3_hash__12",
]
# act
output_columns = h3_feature.get_output_columns()
# assert
assert sorted(output_columns) == sorted(target_columns)
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(
self, feature_set_dataframe, fixed_windows_output_feature_set_dataframe
):
# given
spark_client = SparkClient()
# arrange
feature_set = FeatureSet(
name="feature_set",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=SparkFunctionTransform(
functions=[
Function(F.avg, DataType.FLOAT),
Function(F.stddev_pop, DataType.FLOAT),
]
).with_window(
partition_by="id",
order_by=TIMESTAMP_COLUMN,
mode="fixed_windows",
window_definition=["2 minutes", "15 minutes"],
),
),
Feature(
name="divided_feature",
description="unit test",
dtype=DataType.FLOAT,
transformation=CustomTransform(
transformer=divide, column1="feature1", column2="feature2",
),
),
],
keys=[
KeyFeature(
name="id",
description="The user's Main ID or device ID",
dtype=DataType.INTEGER,
)
],
timestamp=TimestampFeature(),
)
output_df = (
feature_set.construct(feature_set_dataframe, client=spark_client)
.orderBy(feature_set.timestamp_column)
.select(feature_set.columns)
)
target_df = fixed_windows_output_feature_set_dataframe.orderBy(
feature_set.timestamp_column
).select(feature_set.columns)
# assert
assert_dataframe_equality(output_df, target_df)
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 __init__(self):
super(FirstPipeline, self).__init__(
source=Source(
readers=[TableReader(id="t", database="db", table="table",)],
query=f"select * from t", # noqa
),
feature_set=FeatureSet(
name="first",
entity="entity",
description="description",
features=[
Feature(name="feature1", description="test", dtype=DataType.FLOAT,),
Feature(
name="feature2",
description="another test",
dtype=DataType.STRING,
),
],
keys=[
KeyFeature(
name="id", description="identifier", dtype=DataType.BIGINT,
)
],
timestamp=TimestampFeature(),
),
sink=Sink(
writers=[HistoricalFeatureStoreWriter(), OnlineFeatureStoreWriter()]
),
)
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_transform_with_dtype(self, feature_set_dataframe):
test_feature = Feature(
name="feature",
description="unit test",
dtype=DataType.TIMESTAMP,
)
df = test_feature.transform(feature_set_dataframe)
assert dict(df.dtypes).get("feature") == "timestamp"
def test_feature_get_output_columns_without_transformations(self):
test_feature = Feature(
name="feature",
from_column="origin",
description="unit test",
dtype=DataType.BIGINT,
)
assert test_feature.get_output_columns() == [test_feature.name]
def test_feature_transform_invalid_output(self, feature_set_dataframe):
with pytest.raises(Exception):
test_feature = Feature(
name="feature1_plus_a",
description="unit test",
dtype=DataType.FLOAT,
transformation=SQLExpressionTransform(
expression="feature2 + a"),
)
test_feature.transform(feature_set_dataframe).collect()
def test_feature_transform(self, feature_set_dataframe, target_df_spark):
test_feature = Feature(
name="feature",
description="unit test",
transformation=SparkFunctionTransform(
functions=[Function(functions.cos, DataType.DOUBLE)], ),
from_column="feature1",
)
output_df = test_feature.transform(feature_set_dataframe)
assert_dataframe_equality(output_df, target_df_spark)
def test_feature_transform_no_from_column(self, feature_set_dataframe):
test_feature = Feature(
name="feature",
description="unit test feature without transformation",
dtype=DataType.BIGINT,
)
df = test_feature.transform(feature_set_dataframe)
assert all([
a == b for a, b in zip(df.columns, feature_set_dataframe.columns)
])
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_feature_transform_output(self, feature_set_dataframe):
test_feature = Feature(
name="feature1_over_feature2",
description="unit test",
dtype=DataType.FLOAT,
transformation=SQLExpressionTransform(
expression="feature1/feature2"),
)
df = test_feature.transform(feature_set_dataframe).collect()
assert df[0]["feature1_over_feature2"] == 1
assert df[1]["feature1_over_feature2"] == 1
assert df[2]["feature1_over_feature2"] == 1
assert df[3]["feature1_over_feature2"] == 1
def test_output_columns(self, feature_set_dataframe):
test_feature = Feature(
name="feature",
description="unit test",
dtype=DataType.BIGINT,
transformation=CustomTransform(
transformer=divide, column1="feature1", column2="feature2",
),
)
df_columns = test_feature.get_output_columns()
assert isinstance(df_columns, list)
assert df_columns == ["feature"]
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_feature_get_output_columns_with_transformations(
self, feature_set_dataframe):
some_transformation = Mock()
some_transformation.output_columns = feature_set_dataframe.columns
test_feature = Feature(
name="feature",
from_column="origin",
description="unit test",
transformation=some_transformation,
dtype=DataType.BIGINT,
)
assert test_feature.get_output_columns(
) == feature_set_dataframe.columns
def test_overwriting_column(self, spark_session):
# arrange
input_df = spark_session.sql("select 0 as feature")
feature_with_same_name = Feature(
name="feature",
description="description",
dtype=DataType.INTEGER,
transformation=SQLExpressionTransform(expression="feature + 1"),
)
target_df = spark_session.sql("select 1 as feature")
# act
output_df = feature_with_same_name.transform(input_df)
# assert
assert_dataframe_equality(output_df, 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_output_columns(self):
test_feature = Feature(
name="feature1_over_feature2",
description="unit test",
dtype=DataType.FLOAT,
transformation=SQLExpressionTransform(
expression="feature1/feature2"),
)
df_columns = test_feature.get_output_columns()
assert all(
[a == b for a, b in zip(
df_columns,
["feature1_over_feature2"],
)])
def test_custom_transform_output(self, feature_set_dataframe):
test_feature = Feature(
name="feature",
description="unit test",
dtype=DataType.BIGINT,
transformation=CustomTransform(
transformer=divide, column1="feature1", column2="feature2",
),
)
df = test_feature.transform(feature_set_dataframe).collect()
assert df[0]["feature"] == 1
assert df[1]["feature"] == 1
assert df[2]["feature"] == 1
assert df[3]["feature"] == 1
def ratio_order_amount_and_items():
return Feature(name="ratio_order_amount_by_items_val",
description="ratio order amount by items count",
dtype=DataType.DOUBLE,
transformation=CustomTransform(transformer=divide,
column1="order_total_amount",
column2="items_qtd"))
def test_columns_not_in_dataframe(self, spark_context, spark_session):
# arrange
input_df = create_df_from_collection(self.input_data, spark_context,
spark_session)
feature = Feature(
name="id",
description="stack transformation",
dtype=DataType.STRING,
transformation=StackTransform("id_c", "id_d"),
)
# act and assert
with pytest.raises(ValueError,
match="Columns not found, columns in df: "):
feature.transform(input_df)
def test_feature_transform_with_from_column(self, feature_set_dataframe):
test_feature = Feature(
name="new_feature",
from_column="feature",
description="unit test",
dtype=DataType.BIGINT,
)
df = test_feature.transform(feature_set_dataframe)
assert all([
a == b for a, b in zip(
sorted(df.columns),
sorted(["new_feature", "id", TIMESTAMP_COLUMN, "feature"]),
)
])
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_2_minutes_fixed_windows",
"type": FloatType(),
"primary_key": False,
},
{
"column_name": "feature1__avg_over_15_minutes_fixed_windows",
"type": FloatType(),
"primary_key": False,
},
{
"column_name": "feature1__stddev_pop_over_2_minutes_fixed_windows",
"type": DoubleType(),
"primary_key": False,
},
{
"column_name": "feature1__stddev_pop_over_15_minutes_fixed_windows",
"type": DoubleType(),
"primary_key": False,
},
]
feature_set = FeatureSet(
name="feature_set",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=SparkFunctionTransform(
functions=[
Function(F.avg, DataType.FLOAT),
Function(F.stddev_pop, DataType.DOUBLE),
]
).with_window(
partition_by="id",
order_by=TIMESTAMP_COLUMN,
mode="fixed_windows",
window_definition=["2 minutes", "15 minutes"],
),
),
],
keys=[
KeyFeature(
name="id",
description="The user's Main ID or device ID",
dtype=DataType.BIGINT,
)
],
timestamp=TimestampFeature(),
)
schema = feature_set.get_schema()
assert schema == expected_schema
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 feature_set():
feature_set = FeatureSet(
name="feature_set",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=SparkFunctionTransform(functions=[
Function(functions.avg, DataType.FLOAT),
Function(functions.stddev_pop, DataType.DOUBLE),
]).with_window(
partition_by="id",
order_by=TIMESTAMP_COLUMN,
mode="fixed_windows",
window_definition=["2 minutes", "15 minutes"],
),
),
],
keys=[
KeyFeature(
name="id",
description="The user's Main ID or device ID",
dtype=DataType.BIGINT,
)
],
timestamp=TimestampFeature(),
)
return feature_set
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_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_feature_set_with_invalid_feature(self, key_id, timestamp_c,
dataframe):
spark_client = SparkClient()
with pytest.raises(ValueError):
AggregatedFeatureSet(
name="name",
entity="entity",
description="description",
features=[
Feature(
name="feature1",
description="test",
transformation=SparkFunctionTransform(functions=[
Function(functions.avg, DataType.FLOAT)
], ).with_window(
partition_by="id",
mode="row_windows",
window_definition=["2 events"],
),
),
],
keys=[key_id],
timestamp=timestamp_c,
).construct(dataframe, spark_client)
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)
