def calculate_sparkml_scaler_output_shapes(operator):
check_input_and_output_numbers(operator, output_count_range=1)
check_input_and_output_types(
operator, good_input_types=[FloatTensorType, Int64TensorType])
input_shape = copy.deepcopy(operator.inputs[0].type.shape)
operator.outputs[0].type = FloatTensorType(input_shape)
def calculate_one_vs_rest_output_shapes(operator):
check_input_and_output_numbers(operator, input_count_range=1, output_count_range=1)
check_input_and_output_types(operator, good_input_types=[FloatTensorType, Int64TensorType])
if len(operator.inputs[0].type.shape) != 2:
raise RuntimeError('Input must be a [N, C]-tensor')
N = operator.inputs[0].type.shape[0]
operator.outputs[0].type = Int64TensorType(shape=[N])
def calculate_sparkml_naive_bayes_output_shapes(operator):
check_input_and_output_numbers(operator, output_count_range=2)
check_input_and_output_types(operator,
good_input_types=[FloatTensorType],
good_output_types=[FloatTensorType,FloatTensorType])
N = operator.inputs[0].type.shape[0]
C = operator.raw_operator.numClasses
operator.outputs[0].type = FloatTensorType([N, 1])
operator.outputs[1].type = FloatTensorType([N, C])
def calculate_bucketizer_output_shapes(operator):
check_input_and_output_numbers(operator,
input_count_range=1,
output_count_range=1)
check_input_and_output_types(operator,
good_input_types=[FloatTensorType],
good_output_types=[FloatTensorType])
input_type = copy.deepcopy(operator.inputs[0].type)
for output in operator.outputs:
output.type = input_type
def calculate_sparkml_polynomial_expansion_output_shapes(operator):
check_input_and_output_numbers(operator, output_count_range=1)
check_input_and_output_types(
operator, good_input_types=[FloatTensorType, Int64TensorType])
N = operator.inputs[0].type.shape[0]
C = get_combinations_count(operator.inputs[0].type.shape[1],
operator.raw_operator.getDegree())
operator.outputs[0].type = copy.deepcopy(operator.inputs[0].type)
operator.outputs[0].type.shape = [N, C]
def calculate_imputer_output_shapes(operator):
check_input_and_output_numbers(
operator, output_count_range=[1, len(operator.outputs)])
check_input_and_output_types(
operator,
good_input_types=[FloatTensorType, Int64TensorType],
good_output_types=[FloatTensorType, Int64TensorType])
input_type = copy.deepcopy(operator.inputs[0].type)
for output in operator.outputs:
output.type = input_type
def calculate_gbt_classifier_output_shapes(operator):
check_input_and_output_numbers(operator,
input_count_range=1,
output_count_range=[1, 2])
check_input_and_output_types(
operator, good_input_types=[FloatTensorType, Int64TensorType])
if len(operator.inputs[0].type.shape) != 2:
raise RuntimeError('Input must be a [N, C]-tensor')
N = operator.inputs[0].type.shape[0]
operator.outputs[0].type = Int64TensorType(shape=[N])
if isinstance(operator.raw_operator, GBTClassificationModel):
class_count = 2
operator.outputs[1].type = FloatTensorType([N, class_count])
def calculate_decision_tree_classifier_output_shapes(operator):
check_input_and_output_numbers(operator,
input_count_range=1,
output_count_range=[1, 2])
check_input_and_output_types(
operator, good_input_types=[FloatTensorType, Int64TensorType])
if len(operator.inputs[0].type.shape) != 2:
raise RuntimeError('Input must be a [N, C]-tensor')
N = operator.inputs[0].type.shape[0]
class_count = operator.raw_operator.numClasses
operator.outputs[0].type = Int64TensorType(shape=[N])
operator.outputs[1].type = FloatTensorType([N, class_count])
def calculate_sparkml_tokenizer_output_shapes(operator):
check_input_and_output_numbers(operator, output_count_range=1)
check_input_and_output_types(operator,
good_input_types=[StringTensorType])
operator.outputs[0].type = StringTensorType()
def calculate_sparkml_pca_output_shapes(operator):
check_input_and_output_numbers(operator, output_count_range=1)
check_input_and_output_types(operator, good_input_types=[FloatTensorType])
N = operator.inputs[0].type.shape[0]
operator.outputs[0].type = FloatTensorType([N, operator.raw_operator.getOrDefault('k')])
def calculate_element_wise_product_output_shapes(operator):
check_input_and_output_numbers(operator, output_count_range=1)
check_input_and_output_types(operator, good_input_types=[FloatTensorType])
N = operator.inputs[0].type.shape[0]
operator.outputs[0].type = FloatTensorType(
[N, operator.inputs[0].type.shape[1]])
def calculate_decision_tree_regressor_output_shapes(operator):
check_input_and_output_numbers(operator,
input_count_range=1,
output_count_range=1)
N = operator.inputs[0].type.shape[0]
operator.outputs[0].type = FloatTensorType(shape=[N, 1])
def calculate_sparkml_stop_words_remover_output_shapes(operator):
check_input_and_output_numbers(operator, output_count_range=1)
check_input_and_output_types(operator, good_input_types=[StringTensorType])
input_shape = copy.deepcopy(operator.inputs[0].type.shape)
operator.outputs[0].type = StringTensorType(input_shape)
