Esempio n. 1
0
 def test_cbf_jaccard_invalid_msg(self):
     """ check invalid type in a jaccard index message """
     msg = "The parameter second must be of type CountingBloomFilter"
     blm = CountingBloomFilter(est_elements=10, false_positive_rate=0.05)
     blm.add("this is another test")
     try:
         blm.jaccard_index(15)
     except TypeError as ex:
         self.assertEqual(str(ex), msg)
     else:
         self.assertEqual(True, False)
Esempio n. 2
0
 def test_cbf_jaccard_invalid_msg(self):
     ''' check invalid type in a jaccard index message '''
     msg = ('The parameter second must be of type CountingBloomFilter')
     blm = CountingBloomFilter(est_elements=10, false_positive_rate=0.05)
     blm.add('this is another test')
     try:
         blm.jaccard_index(15)
     except TypeError as ex:
         self.assertEqual(str(ex), msg)
     else:
         self.assertEqual(True, False)
Esempio n. 3
0
 def test_cbf_jaccard_different(self):
     """ test jaccard of two completly different counting bloom filters """
     blm1 = CountingBloomFilter(est_elements=10, false_positive_rate=0.05)
     blm1.add("this is a test", 10)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.05)
     blm2.add("this is also a test", 10)
     self.assertEqual(blm1.jaccard_index(blm2), 0.0)
Esempio n. 4
0
 def test_cbf_jaccard_ident_2(self):
     """ test jaccard of two mostly identical counting bloom filters """
     blm1 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm1.add("this is a test", 10)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm2.add("this is a test", 15)
     self.assertEqual(blm1.jaccard_index(blm2), 1.0)
Esempio n. 5
0
 def test_cbf_jaccard_different(self):
     ''' test jaccard of two completly different counting bloom filters '''
     blm1 = CountingBloomFilter(est_elements=10, false_positive_rate=0.05)
     blm1.add('this is a test', 10)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.05)
     blm2.add('this is also a test', 10)
     self.assertEqual(blm1.jaccard_index(blm2), 0.0)
Esempio n. 6
0
 def test_cbf_jaccard_ident_2(self):
     ''' test jaccard of two mostly identical counting bloom filters '''
     blm1 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm1.add('this is a test', 10)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm2.add('this is a test', 15)
     self.assertEqual(blm1.jaccard_index(blm2), 1.0)
Esempio n. 7
0
 def test_cbf_jaccard_ident(self):
     ''' test jaccard of two identical counting bloom filters '''
     blm1 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm1.add('this is a test', 10)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm2.add('this is a test', 10)
     self.assertEqual(blm1.jaccard_index(blm2), 1.0)
Esempio n. 8
0
 def test_cbf_jaccard_similar_2(self):
     """ test jaccard of two similar counting bloom filters - again """
     blm1 = CountingBloomFilter(est_elements=100, false_positive_rate=0.01)
     blm1.add("this is a test", 10)
     blm1.add("this is a different test", 10)
     blm2 = CountingBloomFilter(est_elements=100, false_positive_rate=0.01)
     blm2.add("this is a test", 10)
     res = blm1.jaccard_index(blm2)
     self.assertEqual(res, 0.50)
Esempio n. 9
0
 def test_cbf_jaccard_similar_2(self):
     ''' test jaccard of two similar counting bloom filters - again '''
     blm1 = CountingBloomFilter(est_elements=100, false_positive_rate=0.01)
     blm1.add('this is a test', 10)
     blm1.add('this is a different test', 10)
     blm2 = CountingBloomFilter(est_elements=100, false_positive_rate=0.01)
     blm2.add('this is a test', 10)
     res = blm1.jaccard_index(blm2)
     self.assertEqual(res, 0.50)
Esempio n. 10
0
 def test_cbf_jaccard_similar(self):
     ''' test jaccard of two similar counting bloom filters '''
     blm1 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm1.add('this is a test', 10)
     blm1.add('this is a different test', 10)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm2.add('this is a test', 10)
     blm2.add('this is also a test', 10)
     res = blm1.jaccard_index(blm2)
     self.assertGreater(res, 0.33)
     self.assertLess(res, 0.50)
Esempio n. 11
0
 def test_cbf_jaccard_invalid(self):
     """ use an invalid type in a jaccard index """
     blm = CountingBloomFilter(est_elements=10, false_positive_rate=0.05)
     blm.add("this is a test")
     self.assertRaises(TypeError, lambda: blm.jaccard_index(1))
Esempio n. 12
0
 def test_cbf_jaccard_different_2(self):
     """ test jaccard of an mismath of counting bloom filters """
     blm1 = CountingBloomFilter(est_elements=101, false_positive_rate=0.01)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     self.assertEqual(blm1.jaccard_index(blm2), None)
Esempio n. 13
0
 def test_cbf_jaccard_empty_both(self):
     """ test jaccard of an empty counting bloom filters """
     blm1 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     self.assertEqual(blm1.jaccard_index(blm2), 1.0)
Esempio n. 14
0
 def test_cbf_jaccard_invalid(self):
     ''' use an invalid type in a jaccard index '''
     blm = CountingBloomFilter(est_elements=10, false_positive_rate=0.05)
     blm.add('this is a test')
     self.assertRaises(TypeError, lambda: blm.jaccard_index(1))
Esempio n. 15
0
 def test_cbf_jaccard_different_2(self):
     ''' test jaccard of an mismath of counting bloom filters '''
     blm1 = CountingBloomFilter(est_elements=101, false_positive_rate=0.01)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     self.assertEqual(blm1.jaccard_index(blm2), None)
Esempio n. 16
0
 def test_cbf_jaccard_empty_both(self):
     ''' test jaccard of an empty counting bloom filters '''
     blm1 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     blm2 = CountingBloomFilter(est_elements=10, false_positive_rate=0.01)
     self.assertEqual(blm1.jaccard_index(blm2), 1.0)