From f58f6b169c8e3e80341857669ee16544909d0d18 Mon Sep 17 00:00:00 2001 From: Helin Wang Date: Tue, 17 Dec 2019 15:31:29 -0800 Subject: [PATCH] fix(automl): fix TablesClient.predict for list and struct The Predict request payload is proto. Previously Python dict is automatically converted to proto. However, the conversion failed for google.protobuf.ListValue and google.protobuf.Struct. Changing the structure of the Python dict might fix the problem. However, this PR fixes the problem by generating the proto message directly. So there is no auto conversion step. FIXES #9887 --- .../automl_v1beta1/tables/tables_client.py | 51 +++++++--- automl/setup.py | 1 + .../v1beta1/test_tables_client_v1beta1.py | 93 +++++++++++++------ 3 files changed, 100 insertions(+), 45 deletions(-) diff --git a/automl/google/cloud/automl_v1beta1/tables/tables_client.py b/automl/google/cloud/automl_v1beta1/tables/tables_client.py index 668e1e55cbe5a..cea97ef797ae4 100644 --- a/automl/google/cloud/automl_v1beta1/tables/tables_client.py +++ b/automl/google/cloud/automl_v1beta1/tables/tables_client.py @@ -22,8 +22,10 @@ from google.api_core.gapic_v1 import client_info from google.api_core import exceptions from google.cloud.automl_v1beta1 import gapic -from google.cloud.automl_v1beta1.proto import data_types_pb2 +from google.cloud.automl_v1beta1.proto import data_types_pb2, data_items_pb2 from google.cloud.automl_v1beta1.tables import gcs_client +from google.protobuf import struct_pb2 + _GAPIC_LIBRARY_VERSION = pkg_resources.get_distribution("google-cloud-automl").version _LOGGER = logging.getLogger(__name__) @@ -390,21 +392,39 @@ def __column_spec_name_from_args( return column_spec_name - def __type_code_to_value_type(self, type_code, value): + def __data_type_to_proto_value(self, data_type, value): + type_code = data_type.type_code if value is None: - return {"null_value": 0} + return struct_pb2.Value() elif type_code == data_types_pb2.FLOAT64: - return {"number_value": value} - elif type_code == data_types_pb2.TIMESTAMP: - return {"string_value": value} - elif type_code == data_types_pb2.STRING: - return {"string_value": value} + return struct_pb2.Value(number_value=value) + elif ( + type_code == data_types_pb2.TIMESTAMP + or type_code == data_types_pb2.STRING + or type_code == data_types_pb2.CATEGORY + ): + return struct_pb2.Value(string_value=value) elif type_code == data_types_pb2.ARRAY: - return {"list_value": value} + if isinstance(value, struct_pb2.ListValue): + # in case the user passed in a ListValue. + return struct_pb2.Value(list_value=value) + array = [] + for item in value: + array.append( + self.__data_type_to_proto_value(data_type.list_element_type, item) + ) + return struct_pb2.Value(list_value=struct_pb2.ListValue(values=array)) elif type_code == data_types_pb2.STRUCT: - return {"struct_value": value} - elif type_code == data_types_pb2.CATEGORY: - return {"string_value": value} + if isinstance(value, struct_pb2.Struct): + # in case the user passed in a Struct. + return struct_pb2.Value(struct_value=value) + struct_value = struct_pb2.Struct() + for k, v in value.items(): + field_value = self.__data_type_to_proto_value( + data_type.struct_type.fields[k], v + ) + struct_value.fields[k].CopyFrom(field_value) + return struct_pb2.Value(struct_value=struct_value) else: raise ValueError("Unknown type_code: {}".format(type_code)) @@ -2682,16 +2702,17 @@ def predict( values = [] for i, c in zip(inputs, column_specs): - value_type = self.__type_code_to_value_type(c.data_type.type_code, i) + value_type = self.__data_type_to_proto_value(c.data_type, i) values.append(value_type) - request = {"row": {"values": values}} + row = data_items_pb2.Row(values=values) + payload = data_items_pb2.ExamplePayload(row=row) params = None if feature_importance: params = {"feature_importance": "true"} - return self.prediction_client.predict(model.name, request, params, **kwargs) + return self.prediction_client.predict(model.name, payload, params, **kwargs) def batch_predict( self, diff --git a/automl/setup.py b/automl/setup.py index 208d1e2211587..da79c0d046915 100644 --- a/automl/setup.py +++ b/automl/setup.py @@ -24,6 +24,7 @@ dependencies = [ "google-api-core[grpc] >= 1.14.0, < 2.0.0dev", 'enum34; python_version < "3.4"', + "protobuf >= 3.4.0", ] extras = { "pandas": ["pandas>=0.17.1"], diff --git a/automl/tests/unit/gapic/v1beta1/test_tables_client_v1beta1.py b/automl/tests/unit/gapic/v1beta1/test_tables_client_v1beta1.py index 3f2b6d3de2bde..12e1adcb0c7c4 100644 --- a/automl/tests/unit/gapic/v1beta1/test_tables_client_v1beta1.py +++ b/automl/tests/unit/gapic/v1beta1/test_tables_client_v1beta1.py @@ -23,7 +23,8 @@ from google.api_core import exceptions from google.auth.credentials import AnonymousCredentials from google.cloud import automl_v1beta1 -from google.cloud.automl_v1beta1.proto import data_types_pb2 +from google.cloud.automl_v1beta1.proto import data_types_pb2, data_items_pb2 +from google.protobuf import struct_pb2 PROJECT = "project" REGION = "region" @@ -1116,9 +1117,10 @@ def test_predict_from_array(self): model.configure_mock(tables_model_metadata=model_metadata, name="my_model") client = self.tables_client({"get_model.return_value": model}, {}) client.predict(["1"], model_name="my_model") - client.prediction_client.predict.assert_called_with( - "my_model", {"row": {"values": [{"string_value": "1"}]}}, None + payload = data_items_pb2.ExamplePayload( + row=data_items_pb2.Row(values=[struct_pb2.Value(string_value="1")]) ) + client.prediction_client.predict.assert_called_with("my_model", payload, None) def test_predict_from_dict(self): data_type = mock.Mock(type_code=data_types_pb2.CATEGORY) @@ -1131,10 +1133,16 @@ def test_predict_from_dict(self): model.configure_mock(tables_model_metadata=model_metadata, name="my_model") client = self.tables_client({"get_model.return_value": model}, {}) client.predict({"a": "1", "b": "2"}, model_name="my_model") + payload = data_items_pb2.ExamplePayload( + row=data_items_pb2.Row( + values=[ + struct_pb2.Value(string_value="1"), + struct_pb2.Value(string_value="2"), + ] + ) + ) client.prediction_client.predict.assert_called_with( - "my_model", - {"row": {"values": [{"string_value": "1"}, {"string_value": "2"}]}}, - None, + "my_model", payload, None, ) def test_predict_from_dict_with_feature_importance(self): @@ -1150,10 +1158,16 @@ def test_predict_from_dict_with_feature_importance(self): client.predict( {"a": "1", "b": "2"}, model_name="my_model", feature_importance=True ) + payload = data_items_pb2.ExamplePayload( + row=data_items_pb2.Row( + values=[ + struct_pb2.Value(string_value="1"), + struct_pb2.Value(string_value="2"), + ] + ) + ) client.prediction_client.predict.assert_called_with( - "my_model", - {"row": {"values": [{"string_value": "1"}, {"string_value": "2"}]}}, - {"feature_importance": "true"}, + "my_model", payload, {"feature_importance": "true"}, ) def test_predict_from_dict_missing(self): @@ -1167,18 +1181,31 @@ def test_predict_from_dict_missing(self): model.configure_mock(tables_model_metadata=model_metadata, name="my_model") client = self.tables_client({"get_model.return_value": model}, {}) client.predict({"a": "1"}, model_name="my_model") + payload = data_items_pb2.ExamplePayload( + row=data_items_pb2.Row( + values=[struct_pb2.Value(string_value="1"), struct_pb2.Value()] + ) + ) client.prediction_client.predict.assert_called_with( - "my_model", - {"row": {"values": [{"string_value": "1"}, {"null_value": 0}]}}, - None, + "my_model", payload, None, ) def test_predict_all_types(self): float_type = mock.Mock(type_code=data_types_pb2.FLOAT64) timestamp_type = mock.Mock(type_code=data_types_pb2.TIMESTAMP) string_type = mock.Mock(type_code=data_types_pb2.STRING) - array_type = mock.Mock(type_code=data_types_pb2.ARRAY) - struct_type = mock.Mock(type_code=data_types_pb2.STRUCT) + array_type = mock.Mock( + type_code=data_types_pb2.ARRAY, + list_element_type=mock.Mock(type_code=data_types_pb2.FLOAT64), + ) + struct = data_types_pb2.StructType() + struct.fields["a"].CopyFrom( + data_types_pb2.DataType(type_code=data_types_pb2.CATEGORY) + ) + struct.fields["b"].CopyFrom( + data_types_pb2.DataType(type_code=data_types_pb2.CATEGORY) + ) + struct_type = mock.Mock(type_code=data_types_pb2.STRUCT, struct_type=struct) category_type = mock.Mock(type_code=data_types_pb2.CATEGORY) column_spec_float = mock.Mock(display_name="float", data_type=float_type) column_spec_timestamp = mock.Mock( @@ -1211,28 +1238,34 @@ def test_predict_all_types(self): "timestamp": "EST", "string": "text", "array": [1], - "struct": {"a": "b"}, + "struct": {"a": "label_a", "b": "label_b"}, "category": "a", "null": None, }, model_name="my_model", ) + struct = struct_pb2.Struct() + struct.fields["a"].CopyFrom(struct_pb2.Value(string_value="label_a")) + struct.fields["b"].CopyFrom(struct_pb2.Value(string_value="label_b")) + payload = data_items_pb2.ExamplePayload( + row=data_items_pb2.Row( + values=[ + struct_pb2.Value(number_value=1.0), + struct_pb2.Value(string_value="EST"), + struct_pb2.Value(string_value="text"), + struct_pb2.Value( + list_value=struct_pb2.ListValue( + values=[struct_pb2.Value(number_value=1.0)] + ) + ), + struct_pb2.Value(struct_value=struct), + struct_pb2.Value(string_value="a"), + struct_pb2.Value(), + ] + ) + ) client.prediction_client.predict.assert_called_with( - "my_model", - { - "row": { - "values": [ - {"number_value": 1.0}, - {"string_value": "EST"}, - {"string_value": "text"}, - {"list_value": [1]}, - {"struct_value": {"a": "b"}}, - {"string_value": "a"}, - {"null_value": 0}, - ] - } - }, - None, + "my_model", payload, None, ) def test_predict_from_array_missing(self):