def test_infer(self, mock_call_servo):
self.plugin.examples = [
self.get_fake_example(0),
self.get_fake_example(1),
self.get_fake_example(2),
]
self.plugin.updated_example_indices = set([0, 2])
inference_result_proto = regression_pb2.RegressionResponse()
regression = inference_result_proto.result.regressions.add()
regression.value = 0.45
regression = inference_result_proto.result.regressions.add()
regression.value = 0.55
mock_call_servo.return_value = inference_result_proto
response = self.server.get(
"/data/plugin/whatif/infer?" +
urllib_parse.urlencode({
"inference_address": "addr",
"model_name": "name",
"model_type": "regression",
"model_version": ",",
"model_signature": ",",
}))
self.assertEqual(200, response.status_code)
self.assertEqual(0, len(self.plugin.updated_example_indices))
inferences = json.loads(
json.loads(response.get_data().decode("utf-8"))["inferences"])
self.assertTrue(0 in inferences["indices"])
self.assertFalse(1 in inferences["indices"])
self.assertTrue(2 in inferences["indices"])
def test_make_json_formatted_for_single_chart_regression(self):
"""Test making a regression chart with a single point on it."""
inference_result_proto = regression_pb2.RegressionResponse()
regression = inference_result_proto.result.regressions.add()
regression.value = 0.45
regression = inference_result_proto.result.regressions.add()
regression.value = 0.55
original_feature = inference_utils.OriginalFeatureList(
'feature_name', [2.], 'float_list')
mutant_feature = inference_utils.MutantFeatureValue(original_feature,
index=0,
mutant_value=20)
mutant_feature_2 = inference_utils.MutantFeatureValue(original_feature,
index=0,
mutant_value=10)
jsonable = inference_utils.make_json_formatted_for_single_chart(
[mutant_feature, mutant_feature_2], inference_result_proto, 0)
self.assertEqual(['value'], list(jsonable.keys()))
self.assertEqual(2, len(jsonable['value']))
self.assertEqual(10, jsonable['value'][0]['step'])
self.assertAlmostEqual(0.55, jsonable['value'][0]['scalar'])
self.assertEqual(20, jsonable['value'][1]['step'])
self.assertAlmostEqual(0.45, jsonable['value'][1]['scalar'])
def test_infer(self, mock_call_servo):
self.plugin.examples = [
self.get_fake_example(0),
self.get_fake_example(1),
self.get_fake_example(2)
]
self.plugin.updated_example_indices = set([0, 2])
inference_result_proto = regression_pb2.RegressionResponse()
regression = inference_result_proto.result.regressions.add()
regression.value = 0.45
regression = inference_result_proto.result.regressions.add()
regression.value = 0.55
mock_call_servo.return_value = inference_result_proto
response = self.server.get(
'/data/plugin/whatif/infer?' +
urllib_parse.urlencode({
'inference_address': 'addr',
'model_name': 'name',
'model_type': 'regression',
'model_version': ',',
'model_signature': ',',
}))
self.assertEqual(200, response.status_code)
self.assertEqual(0, len(self.plugin.updated_example_indices))
inferences = json.loads(
json.loads(response.get_data().decode('utf-8'))['inferences'])
self.assertTrue(0 in inferences['indices'])
self.assertFalse(1 in inferences['indices'])
self.assertTrue(2 in inferences['indices'])
def convert_prediction_values(values, serving_bundle, model_spec=None):
"""Converts tensor values into ClassificationResponse or
RegressionResponse.
Args:
values: For classification, a 2D list of numbers. The first dimension is for
each example being predicted. The second dimension are the probabilities
for each class ID in the prediction. For regression, a 1D list of numbers,
with a regression score for each example being predicted.
serving_bundle: A `ServingBundle` object that contains the information about
the serving request that the response was generated by.
model_spec: Optional model spec to put into the response.
Returns:
A ClassificationResponse or RegressionResponse.
"""
if serving_bundle.model_type == "classification":
response = classification_pb2.ClassificationResponse()
for example_index in range(len(values)):
classification = response.result.classifications.add()
for class_index in range(len(values[example_index])):
class_score = classification.classes.add()
class_score.score = values[example_index][class_index]
class_score.label = str(class_index)
else:
response = regression_pb2.RegressionResponse()
for example_index in range(len(values)):
regression = response.result.regressions.add()
regression.value = values[example_index]
if model_spec:
response.model_spec.CopyFrom(model_spec)
return response
def convert_predict_response(pred, serving_bundle):
"""Converts a PredictResponse to ClassificationResponse or RegressionResponse.
Args:
pred: PredictResponse to convert.
serving_bundle: A `ServingBundle` object that contains the information about
the serving request that the response was generated by.
Returns:
A ClassificationResponse or RegressionResponse.
"""
output = pred.outputs[serving_bundle.predict_output_tensor]
raw_output = output.float_val
output_index = 0
if serving_bundle.model_type == 'classification':
response = classification_pb2.ClassificationResponse()
response.model_spec.CopyFrom(pred.model_spec)
for _ in range(output.tensor_shape.dim[0].size):
classification = response.result.classifications.add()
for class_index in range(output.tensor_shape.dim[1].size):
class_score = classification.classes.add()
class_score.score = raw_output[output_index]
output_index += 1
class_score.label = str(class_index)
else:
response = regression_pb2.RegressionResponse()
response.model_spec.CopyFrom(pred.model_spec)
for _ in range(output.tensor_shape.dim[0].size):
regression = response.result.regressions.add()
regression.value = raw_output[output_index]
output_index += 1
return response
def test_wrap_inference_results_regression(self):
"""Test wrapping a regression result."""
inference_result_proto = regression_pb2.RegressionResponse()
regression = inference_result_proto.result.regressions.add()
regression.value = 0.45
regression = inference_result_proto.result.regressions.add()
regression.value = 0.55
wrapped = inference_utils.wrap_inference_results(inference_result_proto)
self.assertEqual(2, len(wrapped.regression_result.regressions))
