TheNeuralBit commented on code in PR #17253: URL: https://github.com/apache/beam/pull/17253#discussion_r842237613
########## sdks/python/apache_beam/typehints/batch_test.py: ########## @@ -0,0 +1,111 @@ +# +# 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. +# + +"""Unit tests for the batched type-hint objects.""" + +import unittest + +import numpy as np +import pandas as pd +from parameterized import parameterized +from parameterized import parameterized_class + +from apache_beam.typehints import row_type +from apache_beam.typehints.batch import BatchConverter +from apache_beam.typehints.batch import N +from apache_beam.typehints.batch import NumpyArray +from apache_beam.typehints.typehints import check_constraint +from apache_beam.typehints.typehints import validate_composite_type_param + + +@parameterized_class( + [{ + 'batch_typehint': np.ndarray, + 'element_typehint': np.int32, + 'batch': np.array(range(100), np.int32) + }, + { + 'batch_typehint': NumpyArray[np.int64, (N, 10)], + 'element_typehint': NumpyArray[np.int64, (10, )], + 'batch': np.array([list(range(i, i + 10)) for i in range(100)], + np.int64), + }, + { + 'batch_typehint': pd.DataFrame, + 'element_typehint': row_type.RowTypeConstraint([ + ('f_str', str), ('f_int64', np.int64), ('f_int32', np.int32) + ]), + 'batch': pd.DataFrame({ + 'f_str': pd.Series(map(str, range(100)), dtype=pd.StringDtype()), + 'f_int64': pd.Series(range(100), dtype=np.int64), + 'f_int32': pd.Series(range(100), dtype=np.int32) + }), + }]) +class BatchTest(unittest.TestCase): + def setUp(self): + self.utils = BatchConverter.from_typehints( + element_type=self.element_typehint, batch_type=self.batch_typehint) + + def equality_check(self, left, right): + if isinstance(left, np.ndarray) and isinstance(right, np.ndarray): + return np.array_equal(left, right) + elif isinstance(left, pd.DataFrame) and isinstance(right, pd.DataFrame): + return left.equals(right) Review Comment: TODO: verify DataFrame without index -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
