Skip to content
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
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: 51 additions & 0 deletions automl/beta/batch_predict.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
# Copyright 2020 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# [START automl_batch_predict_beta]
from google.cloud import automl_v1beta1 as automl


def batch_predict(
project_id="YOUR_PROJECT_ID",
model_id="YOUR_MODEL_ID",
input_uri="gs://YOUR_BUCKET_ID/path/to/your/input/csv_or_jsonl",
output_uri="gs://YOUR_BUCKET_ID/path/to/save/results/",
):
"""Batch predict"""
prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = prediction_client.model_path(
project_id, "us-central1", model_id
)

gcs_source = automl.types.GcsSource(input_uris=[input_uri])

input_config = automl.types.BatchPredictInputConfig(gcs_source=gcs_source)
gcs_destination = automl.types.GcsDestination(output_uri_prefix=output_uri)
output_config = automl.types.BatchPredictOutputConfig(
gcs_destination=gcs_destination
)

response = prediction_client.batch_predict(
model_full_id, input_config, output_config
)

print("Waiting for operation to complete...")
print(
"Batch Prediction results saved to Cloud Storage bucket. {}".format(
response.result()
)
)
# [END automl_batch_predict_beta]
47 changes: 47 additions & 0 deletions automl/beta/batch_predict_test.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
# Copyright 2020 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific ladnguage governing permissions and
# limitations under the License.

import datetime
import os

import batch_predict

PROJECT_ID = os.environ["AUTOML_PROJECT_ID"]
BUCKET_ID = "{}-lcm".format(PROJECT_ID)
MODEL_ID = "TEN0000000000000000000"
PREFIX = "TEST_EXPORT_OUTPUT_" + datetime.datetime.now().strftime(
"%Y%m%d%H%M%S"
)


def test_batch_predict(capsys):
# As batch prediction can take a long time. Try to batch predict on a model
# and confirm that the model was not found, but other elements of the
# request were valid.
try:
input_uri = "gs://{}/entity-extraction/input.jsonl".format(BUCKET_ID)
output_uri = "gs://{}/{}/".format(BUCKET_ID, PREFIX)
batch_predict.batch_predict(
PROJECT_ID, MODEL_ID, input_uri, output_uri
)
out, _ = capsys.readouterr()
assert (
"The model is either not found or not supported for prediction yet"
in out
)
except Exception as e:
assert (
"The model is either not found or not supported for prediction yet"
in e.message
)
29 changes: 29 additions & 0 deletions automl/beta/delete_dataset.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
# Copyright 2020 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# [START automl_delete_dataset_beta]
from google.cloud import automl_v1beta1 as automl


def delete_dataset(project_id="YOUR_PROJECT_ID", dataset_id="YOUR_DATASET_ID"):
"""Delete a dataset."""
client = automl.AutoMlClient()
# Get the full path of the dataset
dataset_full_id = client.dataset_path(
project_id, "us-central1", dataset_id
)
response = client.delete_dataset(dataset_full_id)

print("Dataset deleted. {}".format(response.result()))
# [END automl_delete_dataset_beta]
46 changes: 46 additions & 0 deletions automl/beta/delete_dataset_test.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
# Copyright 2020 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import os
import uuid

from google.cloud import automl_v1beta1 as automl
import pytest

import delete_dataset

PROJECT_ID = os.environ["AUTOML_PROJECT_ID"]
BUCKET_ID = "{}-lcm".format(PROJECT_ID)


@pytest.fixture(scope="function")
def dataset_id():
client = automl.AutoMlClient()
project_location = client.location_path(PROJECT_ID, "us-central1")
display_name = "test_{}".format(uuid.uuid4()).replace("-", "")[:32]
metadata = automl.types.TextExtractionDatasetMetadata()
dataset = automl.types.Dataset(
display_name=display_name, text_extraction_dataset_metadata=metadata
)
response = client.create_dataset(project_location, dataset)
dataset_id = response.name.split("/")[-1]

yield dataset_id


def test_delete_dataset(capsys, dataset_id):
# delete dataset
delete_dataset.delete_dataset(PROJECT_ID, dataset_id)
out, _ = capsys.readouterr()
assert "Dataset deleted." in out