1 # encoding: utf-8 2 # Copyright 2016 The TensorFlow Authors. All Rights Reserved. 3 # 4 # Licensed under the Apache License, Version 2.0 (the "License"); 5 # you may not use this file except in compliance with the License. 6 # You may obtain a copy of the License at 7 # 8 # http://www.apache.org/licenses/LICENSE-2.0 9 # 10 # Unless required by applicable law or agreed to in writing, software 11 # distributed under the License is distributed on an "AS IS" BASIS, 12 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 # See the License for the specific language governing permissions and 14 # limitations under the License. 15 # ============================================================================== 16 """Categorical vocabulary tests.""" 17 18 from __future__ import absolute_import 19 from __future__ import division 20 from __future__ import print_function 21 22 from tensorflow.contrib.learn.python.learn.preprocessing import categorical_vocabulary 23 from tensorflow.python.platform import test 24 25 26 class CategoricalVocabularyTest(test.TestCase): 27 """Categorical vocabulary tests.""" 28 29 def testIntVocabulary(self): 30 vocab = categorical_vocabulary.CategoricalVocabulary() 31 self.assertEqual(vocab.get(1), 1) 32 self.assertEqual(vocab.get(3), 2) 33 self.assertEqual(vocab.get(2), 3) 34 self.assertEqual(vocab.get(3), 2) 35 # This vocab doesn't handle nan specially. 36 self.assertEqual(vocab.get(float('nan')), 4) 37 self.assertEqual(len(vocab), 5) 38 39 def testWordVocabulary(self): 40 vocab = categorical_vocabulary.CategoricalVocabulary() 41 self.assertEqual(vocab.get('a'), 1) 42 self.assertEqual(vocab.get('b'), 2) 43 self.assertEqual(vocab.get('a'), 1) 44 self.assertEqual(vocab.get('b'), 2) 45 46 def testCountsTrim(self): 47 vocab = categorical_vocabulary.CategoricalVocabulary() 48 vocab.get('c') 49 vocab.add('c', 5) 50 vocab.get('a') 51 vocab.add('a', 10) 52 # not in vocab yet, skips. 53 vocab.add('b', 5) 54 vocab.add('d', 12) 55 vocab.trim(7, 11) 56 vocab.freeze() 57 self.assertEqual(vocab.get('b'), 0) 58 self.assertEqual(vocab.get('c'), 0) 59 self.assertEqual(len(vocab), 2) 60 self.assertEqual(vocab.get('a'), 1) 61 62 63 if __name__ == '__main__': 64 test.main() 65