You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@beam.apache.org by GitBox <gi...@apache.org> on 2022/07/15 13:07:16 UTC
[GitHub] [beam] yeandy commented on a diff in pull request #22285: Run Inference snippets 2
yeandy commented on code in PR #22285:
URL: https://github.com/apache/beam/pull/22285#discussion_r922140914
##########
sdks/python/apache_beam/examples/snippets/transforms/elementwise/runinference_test.py:
##########
@@ -0,0 +1,125 @@
+# coding=utf-8
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You 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.
+#
+
+# pytype: skip-file
+
+import re
+import unittest
+from io import StringIO
+
+import mock
+import pytest
+
+from apache_beam.examples.snippets.util import assert_matches_stdout
+from apache_beam.testing.test_pipeline import TestPipeline
+
+# pylint: disable=wrong-import-order, wrong-import-position, ungrouped-imports, unused-import
+try:
+ import torch
+ from . import runinference
+except ImportError:
+ raise unittest.SkipTest('PyTorch dependencies are not installed')
+
+# pylint: disable=wrong-import-order, wrong-import-position, ungrouped-imports, unused-import
+try:
+ from apache_beam.io.gcp.gcsfilesystem import GCSFileSystem
+except ImportError:
+ raise unittest.SkipTest('GCP dependencies are not installed')
+
+
+def check_torch_keyed_model_handler():
+ expected = '''[START torch_keyed_model_handler]
+('first_question', PredictionResult(example=tensor([105.]), inference=tensor([523.6982], grad_fn=<UnbindBackward>)))
+('second_question', PredictionResult(example=tensor([108.]), inference=tensor([538.5867], grad_fn=<UnbindBackward>)))
+('third_question', PredictionResult(example=tensor([1000.]), inference=tensor([4965.4019], grad_fn=<UnbindBackward>)))
+('fourth_question', PredictionResult(example=tensor([1013.]), inference=tensor([5029.9180], grad_fn=<UnbindBackward>)))
+[END torch_keyed_model_handler] '''.splitlines()[1:-1]
+ return expected
+
+
+def check_sklearn_keyed_model_handler(actual):
+ expected = '''[START sklearn_keyed_model_handler]
+('first_question', PredictionResult(example=[105.0], inference=array([525.])))
+('second_question', PredictionResult(example=[108.0], inference=array([540.])))
+('third_question', PredictionResult(example=[1000.0], inference=array([5000.])))
+('fourth_question', PredictionResult(example=[1013.0], inference=array([5065.])))
+[END sklearn_keyed_model_handler] '''.splitlines()[1:-1]
+ assert_matches_stdout(actual, expected)
+
+
+def check_torch_unkeyed_model_handler():
+ expected = '''[START torch_unkeyed_model_handler]
+PredictionResult(example=tensor([10.]), inference=tensor([52.2325], grad_fn=<UnbindBackward>))
+PredictionResult(example=tensor([40.]), inference=tensor([201.1165], grad_fn=<UnbindBackward>))
+PredictionResult(example=tensor([60.]), inference=tensor([300.3724], grad_fn=<UnbindBackward>))
+PredictionResult(example=tensor([90.]), inference=tensor([449.2563], grad_fn=<UnbindBackward>))
+[END torch_unkeyed_model_handler] '''.splitlines()[1:-1]
+ return expected
+
+
+def check_sklearn_unkeyed_model_handler(actual):
+ expected = '''[START sklearn_unkeyed_model_handler]
+PredictionResult(example=array([20.], dtype=float32), inference=array([100.], dtype=float32))
+PredictionResult(example=array([40.], dtype=float32), inference=array([200.], dtype=float32))
+PredictionResult(example=array([60.], dtype=float32), inference=array([300.], dtype=float32))
+PredictionResult(example=array([90.], dtype=float32), inference=array([450.], dtype=float32))
+[END sklearn_unkeyed_model_handler] '''.splitlines()[1:-1]
+ assert_matches_stdout(actual, expected)
+
+
+@mock.patch('apache_beam.Pipeline', TestPipeline)
+@mock.patch(
+ 'apache_beam.examples.snippets.transforms.elementwise.runinference.print',
+ str)
+class RunInferenceTest(unittest.TestCase):
+ def test_sklearn_unkeyed_model_handler(self):
+ runinference.sklearn_unkeyed_model_handler(
+ check_sklearn_unkeyed_model_handler)
+
+ def test_sklearn_keyed_model_handler(self):
+ runinference.sklearn_keyed_model_handler(check_sklearn_keyed_model_handler)
+
+
+@mock.patch('apache_beam.Pipeline', TestPipeline)
+@mock.patch('sys.stdout', new_callable=StringIO)
+class RunInferenceStdoutTest(unittest.TestCase):
+ @pytest.mark.uses_pytorch
+ def test_check_torch_keyed_model_handler(self, mock_stdout):
+ runinference.torch_keyed_model_handler()
+ predicted = mock_stdout.getvalue().splitlines()
+ expected = check_torch_keyed_model_handler()
+ actual_stdout = [line.split(':')[0] for line in predicted]
+ replace_fn = lambda x: re.sub(r"<UnbindBackward\d*>", "<UnbindBackward>", x)
+ actual_stdout = [replace_fn(x) for x in actual_stdout]
+ expected_stdout = [line.split(':')[0] for line in expected]
+ self.assertEqual(actual_stdout, expected_stdout)
+
+ @pytest.mark.uses_pytorch
+ def test_check_torch_unkeyed_model_handler(self, mock_stdout):
+ runinference.torch_unkeyed_model_handler()
+ predicted = mock_stdout.getvalue().splitlines()
+ expected = check_torch_unkeyed_model_handler()
+ actual_stdout = [line.split(':')[0] for line in predicted]
+ replace_fn = lambda x: re.sub(r"<UnbindBackward\d*>", "<UnbindBackward>", x)
+ actual_stdout = [replace_fn(x) for x in actual_stdout]
+ expected_stdout = [line.split(':')[0] for line in expected]
+ self.assertEqual(actual_stdout, expected_stdout)
Review Comment:
looks like mostly the same logic to parse and match the stdout. Can we refactor into a helper?
##########
sdks/python/apache_beam/examples/snippets/transforms/elementwise/runinference_test.py:
##########
@@ -0,0 +1,125 @@
+# coding=utf-8
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You 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.
+#
+
+# pytype: skip-file
+
+import re
+import unittest
+from io import StringIO
+
+import mock
+import pytest
+
+from apache_beam.examples.snippets.util import assert_matches_stdout
+from apache_beam.testing.test_pipeline import TestPipeline
+
+# pylint: disable=wrong-import-order, wrong-import-position, ungrouped-imports, unused-import
+try:
+ import torch
+ from . import runinference
+except ImportError:
+ raise unittest.SkipTest('PyTorch dependencies are not installed')
+
+# pylint: disable=wrong-import-order, wrong-import-position, ungrouped-imports, unused-import
+try:
+ from apache_beam.io.gcp.gcsfilesystem import GCSFileSystem
+except ImportError:
+ raise unittest.SkipTest('GCP dependencies are not installed')
+
+
+def check_torch_keyed_model_handler():
+ expected = '''[START torch_keyed_model_handler]
+('first_question', PredictionResult(example=tensor([105.]), inference=tensor([523.6982], grad_fn=<UnbindBackward>)))
+('second_question', PredictionResult(example=tensor([108.]), inference=tensor([538.5867], grad_fn=<UnbindBackward>)))
+('third_question', PredictionResult(example=tensor([1000.]), inference=tensor([4965.4019], grad_fn=<UnbindBackward>)))
+('fourth_question', PredictionResult(example=tensor([1013.]), inference=tensor([5029.9180], grad_fn=<UnbindBackward>)))
+[END torch_keyed_model_handler] '''.splitlines()[1:-1]
+ return expected
+
+
+def check_sklearn_keyed_model_handler(actual):
+ expected = '''[START sklearn_keyed_model_handler]
+('first_question', PredictionResult(example=[105.0], inference=array([525.])))
+('second_question', PredictionResult(example=[108.0], inference=array([540.])))
+('third_question', PredictionResult(example=[1000.0], inference=array([5000.])))
+('fourth_question', PredictionResult(example=[1013.0], inference=array([5065.])))
+[END sklearn_keyed_model_handler] '''.splitlines()[1:-1]
+ assert_matches_stdout(actual, expected)
+
+
+def check_torch_unkeyed_model_handler():
+ expected = '''[START torch_unkeyed_model_handler]
+PredictionResult(example=tensor([10.]), inference=tensor([52.2325], grad_fn=<UnbindBackward>))
+PredictionResult(example=tensor([40.]), inference=tensor([201.1165], grad_fn=<UnbindBackward>))
+PredictionResult(example=tensor([60.]), inference=tensor([300.3724], grad_fn=<UnbindBackward>))
+PredictionResult(example=tensor([90.]), inference=tensor([449.2563], grad_fn=<UnbindBackward>))
+[END torch_unkeyed_model_handler] '''.splitlines()[1:-1]
+ return expected
+
+
+def check_sklearn_unkeyed_model_handler(actual):
+ expected = '''[START sklearn_unkeyed_model_handler]
+PredictionResult(example=array([20.], dtype=float32), inference=array([100.], dtype=float32))
+PredictionResult(example=array([40.], dtype=float32), inference=array([200.], dtype=float32))
+PredictionResult(example=array([60.], dtype=float32), inference=array([300.], dtype=float32))
+PredictionResult(example=array([90.], dtype=float32), inference=array([450.], dtype=float32))
+[END sklearn_unkeyed_model_handler] '''.splitlines()[1:-1]
+ assert_matches_stdout(actual, expected)
+
+
+@mock.patch('apache_beam.Pipeline', TestPipeline)
+@mock.patch(
+ 'apache_beam.examples.snippets.transforms.elementwise.runinference.print',
+ str)
+class RunInferenceTest(unittest.TestCase):
+ def test_sklearn_unkeyed_model_handler(self):
+ runinference.sklearn_unkeyed_model_handler(
+ check_sklearn_unkeyed_model_handler)
+
+ def test_sklearn_keyed_model_handler(self):
+ runinference.sklearn_keyed_model_handler(check_sklearn_keyed_model_handler)
+
+
+@mock.patch('apache_beam.Pipeline', TestPipeline)
+@mock.patch('sys.stdout', new_callable=StringIO)
+class RunInferenceStdoutTest(unittest.TestCase):
Review Comment:
Technically the sklearn tests also print to stdout, right? Maybe rename to `RunInferencePytorchTest`, and the other to `RunInferenceSklearnTest`?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscribe@beam.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org