def test_combiner_computation(self,
data,
expected_accumulator_output,
expected_extract_output,
compute_idf=True):
combiner = categorical_encoding._CategoricalEncodingCombiner(
compute_idf=compute_idf)
expected_accumulator = combiner._create_accumulator()
expected_accumulator = self.update_accumulator(
expected_accumulator, expected_accumulator_output)
self.validate_accumulator_computation(combiner, data,
expected_accumulator)
self.validate_accumulator_extract(combiner, data,
expected_extract_output)
def test_combiner_api_compatibility_int_mode(self):
data = np.array([[1, 2, 3, 4], [1, 2, 3, 0]])
combiner = categorical_encoding._CategoricalEncodingCombiner(
compute_idf=False)
expected_accumulator_output = {
"max_element": np.array(4),
"num_documents": np.array(2),
}
expected_extract_output = {
"num_elements": np.array(5),
}
expected_accumulator = combiner._create_accumulator()
expected_accumulator = self.update_accumulator(
expected_accumulator, expected_accumulator_output)
self.validate_accumulator_serialize_and_deserialize(
combiner, data, expected_accumulator)
self.validate_accumulator_uniqueness(combiner, data)
self.validate_accumulator_extract(combiner, data,
expected_extract_output)