def execute_inspections(op_id, caller_filename, lineno,
optional_code_reference, optional_source_code):
""" Execute inspections, add DAG node """
function_info = FunctionInfo('statsmodel.api', 'add_constant')
input_info = get_input_info(args[0], caller_filename, lineno,
function_info, optional_code_reference,
optional_source_code)
operator_context = OperatorContext(OperatorType.PROJECTION_MODIFY,
function_info)
input_infos = SklearnBackend.before_call(
operator_context, [input_info.annotated_dfobject])
result = original(input_infos[0].result_data, *args[1:], **kwargs)
backend_result = SklearnBackend.after_call(operator_context,
input_infos, result)
new_return_value = backend_result.annotated_dfobject.result_data
dag_node = DagNode(
op_id, BasicCodeLocation(caller_filename,
lineno), operator_context,
DagNodeDetails("Adds const column", ["array"]),
get_optional_code_info_or_none(optional_code_reference,
optional_source_code))
add_dag_node(dag_node, [input_info.dag_node], backend_result)
return new_return_value
def patched_fit_transform(self, *args, **kwargs):
""" Patch for ('example_pipelines.healthcare.healthcare_utils.MyW2VTransformer', 'fit_transform') """
# pylint: disable=no-method-argument
self.mlinspect_fit_transform_active = True # pylint: disable=attribute-defined-outside-init
original = gorilla.get_original_attribute(
healthcare_utils.MyW2VTransformer, 'fit_transform')
function_info = FunctionInfo(
'example_pipelines.healthcare.healthcare_utils',
'MyW2VTransformer')
input_info = get_input_info(args[0], self.mlinspect_caller_filename,
self.mlinspect_lineno, function_info,
self.mlinspect_optional_code_reference,
self.mlinspect_optional_source_code)
operator_context = OperatorContext(OperatorType.TRANSFORMER,
function_info)
input_infos = SklearnBackend.before_call(
operator_context, [input_info.annotated_dfobject])
result = original(self, input_infos[0].result_data, *args[1:],
**kwargs)
backend_result = SklearnBackend.after_call(operator_context,
input_infos, result)
new_return_value = backend_result.annotated_dfobject.result_data
assert isinstance(new_return_value, MlinspectNdarray)
dag_node = DagNode(
singleton.get_next_op_id(),
BasicCodeLocation(self.mlinspect_caller_filename,
self.mlinspect_lineno), operator_context,
DagNodeDetails("Word2Vec: fit_transform", ['array']),
get_optional_code_info_or_none(
self.mlinspect_optional_code_reference,
self.mlinspect_optional_source_code))
add_dag_node(dag_node, [input_info.dag_node], backend_result)
self.mlinspect_fit_transform_active = False # pylint: disable=attribute-defined-outside-init
return new_return_value
def add_test_label_node(test_label_arg, caller_filename, function_info, lineno,
optional_code_reference, optional_source_code):
"""Add a Test Label DAG Node for a estimator.score call"""
# pylint: disable=too-many-arguments
operator_context = OperatorContext(OperatorType.TEST_LABELS, function_info)
input_info_test_labels = get_input_info(test_label_arg, caller_filename,
lineno, function_info,
optional_code_reference,
optional_source_code)
test_label_op_id = _pipeline_executor.singleton.get_next_op_id()
test_labels_dag_node = DagNode(
test_label_op_id, BasicCodeLocation(caller_filename,
lineno), operator_context,
DagNodeDetails(None, get_column_names(test_label_arg)),
get_optional_code_info_or_none(optional_code_reference,
optional_source_code))
input_infos = SklearnBackend.before_call(
operator_context, [input_info_test_labels.annotated_dfobject])
label_backend_result = SklearnBackend.after_call(operator_context,
input_infos,
test_label_arg)
add_dag_node(test_labels_dag_node, [input_info_test_labels.dag_node],
label_backend_result)
test_labels_result = label_backend_result.annotated_dfobject.result_data
return label_backend_result, test_labels_dag_node, test_labels_result
def add_train_data_node(estimator, train_data_arg, function_info):
"""Add a Train Label DAG Node for a estimator.fit call"""
input_info_train_data = get_input_info(
train_data_arg, estimator.mlinspect_caller_filename,
estimator.mlinspect_lineno, function_info,
estimator.mlinspect_optional_code_reference,
estimator.mlinspect_optional_source_code)
train_data_op_id = _pipeline_executor.singleton.get_next_op_id()
operator_context = OperatorContext(OperatorType.TRAIN_DATA, function_info)
train_data_dag_node = DagNode(
train_data_op_id,
BasicCodeLocation(estimator.mlinspect_caller_filename,
estimator.mlinspect_lineno), operator_context,
DagNodeDetails(None, ["array"]),
get_optional_code_info_or_none(
estimator.mlinspect_optional_code_reference,
estimator.mlinspect_optional_source_code))
input_infos = SklearnBackend.before_call(
operator_context, [input_info_train_data.annotated_dfobject])
data_backend_result = SklearnBackend.after_call(operator_context,
input_infos,
train_data_arg)
add_dag_node(train_data_dag_node, [input_info_train_data.dag_node],
data_backend_result)
train_data_result = data_backend_result.annotated_dfobject.result_data
return data_backend_result, train_data_dag_node, train_data_result
def execute_inspections(op_id, caller_filename, lineno,
optional_code_reference, optional_source_code):
""" Execute inspections, add DAG node """
function_info = FunctionInfo('numpy.random', 'random')
operator_context = OperatorContext(OperatorType.DATA_SOURCE,
function_info)
input_infos = SklearnBackend.before_call(operator_context, [])
result = original(*args, **kwargs)
backend_result = SklearnBackend.after_call(operator_context,
input_infos, result)
dag_node = DagNode(
op_id, BasicCodeLocation(caller_filename, lineno),
operator_context, DagNodeDetails("random", ['array']),
get_optional_code_info_or_none(optional_code_reference,
optional_source_code))
add_dag_node(dag_node, [], backend_result)
new_return_value = backend_result.annotated_dfobject.result_data
return new_return_value
def patched_fit(self, *args, **kwargs):
""" Patch for ('statsmodel.api.OLS', 'fit') """
# pylint: disable=no-method-argument, too-many-locals
original = gorilla.get_original_attribute(api.OLS, 'fit')
function_info = FunctionInfo('statsmodel.api.OLS', 'fit')
# Train data
# pylint: disable=no-member
data_backend_result, train_data_node, train_data_result = add_train_data_node(
self, self.data.exog, function_info)
self.data.exog = train_data_result
# pylint: disable=no-member
label_backend_result, train_labels_node, train_labels_result = add_train_label_node(
self, self.data.endog, function_info)
self.data.endog = train_labels_result
# Estimator
operator_context = OperatorContext(OperatorType.ESTIMATOR,
function_info)
input_dfs = [
data_backend_result.annotated_dfobject,
label_backend_result.annotated_dfobject
]
input_infos = SklearnBackend.before_call(operator_context, input_dfs)
result = original(self, *args, **kwargs)
estimator_backend_result = SklearnBackend.after_call(
operator_context, input_infos, None)
dag_node = DagNode(
singleton.get_next_op_id(),
BasicCodeLocation(self.mlinspect_caller_filename,
self.mlinspect_lineno), operator_context,
DagNodeDetails("Decision Tree", []),
get_optional_code_info_or_none(
self.mlinspect_optional_code_reference,
self.mlinspect_optional_source_code))
add_dag_node(dag_node, [train_data_node, train_labels_node],
estimator_backend_result)
return result