Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix(automl): fix TablesClient.predict for array and struct #9991

Merged
merged 2 commits into from
Jan 28, 2020
Merged

fix(automl): fix TablesClient.predict for array and struct #9991

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
66302e5
fix(automl): fix TablesClient.predict for list and struct
Dec 17, 2019
20209f6
Address comment: remove protobuf dependency requirement.
Jan 27, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
51 changes: 36 additions & 15 deletions automl/google/cloud/automl_v1beta1/tables/tables_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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__)
Expand Down Expand Up @@ -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(null_value=struct_pb2.NullValue.NULL_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))

Expand Down Expand Up @@ -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,
Expand Down
1 change: 1 addition & 0 deletions automl/setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
dependencies = [
"google-api-core[grpc] >= 1.14.0, < 2.0.0dev",
'enum34; python_version < "3.4"',
"protobuf >= 3.4.0",
helinwang marked this conversation as resolved.
Show resolved Hide resolved
]
extras = {
"pandas": ["pandas>=0.17.1"],
Expand Down
96 changes: 63 additions & 33 deletions automl/tests/unit/gapic/v1beta1/test_tables_client_v1beta1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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"
Expand Down Expand Up @@ -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)
Expand All @@ -1131,11 +1133,15 @@ 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")
client.prediction_client.predict.assert_called_with(
"my_model",
{"row": {"values": [{"string_value": "1"}, {"string_value": "2"}]}},
None,
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", payload, None)

def test_predict_from_dict_with_feature_importance(self):
data_type = mock.Mock(type_code=data_types_pb2.CATEGORY)
Expand All @@ -1150,10 +1156,16 @@ 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):
Expand All @@ -1167,18 +1179,32 @@ 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")
client.prediction_client.predict.assert_called_with(
"my_model",
{"row": {"values": [{"string_value": "1"}, {"null_value": 0}]}},
None,
payload = data_items_pb2.ExamplePayload(
row=data_items_pb2.Row(
values=[
struct_pb2.Value(string_value="1"),
struct_pb2.Value(null_value=struct_pb2.NullValue.NULL_VALUE),
]
)
)
client.prediction_client.predict.assert_called_with("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(
Expand Down Expand Up @@ -1211,29 +1237,33 @@ 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",
)
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,
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(null_value=struct_pb2.NullValue.NULL_VALUE),
]
)
)
client.prediction_client.predict.assert_called_with("my_model", payload, None)

def test_predict_from_array_missing(self):
data_type = mock.Mock(type_code=data_types_pb2.CATEGORY)
Expand Down