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 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__get_features_columns(self):
# arrange
feature_1 = Feature("feature1", "description", DataType.FLOAT)
feature_1.get_output_columns = Mock(return_value=["col_a", "col_b"])
feature_2 = Feature("feature2", "description", DataType.FLOAT)
feature_2.get_output_columns = Mock(return_value=["col_c"])
feature_3 = Feature("feature3", "description", DataType.FLOAT)
feature_3.get_output_columns = Mock(return_value=["col_d"])
target_features_columns = ["col_a", "col_b", "col_c", "col_d"]
# act
result_features_columns = FeatureSet._get_features_columns(
feature_1, feature_2, feature_3)
# assert
assert target_features_columns == result_features_columns
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_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_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_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_output_columns(self):
test_feature = Feature(
name="feature1",
description="unit test",
transformation=SparkFunctionTransform(functions=[
Function(functions.avg, DataType.DOUBLE)
], ).with_window(
partition_by="id",
mode="fixed_windows",
window_definition=["7 days", "2 weeks"],
),
)
df_columns = test_feature.get_output_columns()
assert all([
a == b for a, b in zip(
df_columns,
[
"feature1__avg_over_7_days_fixed_windows",
"feature1__avg_over_2_weeks_fixed_windows",
],
)
])
