def test_addDocument_existingKey(self):
newDocModifiedWithExistingSignature = Document(
3,
VectorGenerator.getRandomGaussianUnitVector(
dimension=self.dimension, mu=0, sigma=1))
newDocModifiedWithExistingSignature.signature = Signature(
self.doc1.signature.to01())
self.pm.addDocument(newDocModifiedWithExistingSignature)
self.assertEqual(
self.pm.signatureTrie[self.doc1.signature.permutate(
self.pm).to01()], set([1, 3]))
def test_getNearestDocument_usingANearbyKeyInTrie(self):
digitReplacement = {'0': '1', '1': '0'}
newDocWithANearbySignature = Document(
3,
VectorGenerator.getRandomGaussianUnitVector(
dimension=self.dimension, mu=0, sigma=1))
exactSignature = self.doc1.signature.to01()
newDocWithANearbySignature.signature = Signature(
exactSignature[:-1] + digitReplacement[exactSignature[-1]])
self.assertNotEquals(self.doc1.signature.to01(),
newDocWithANearbySignature.signature.to01())
self.assertEqual(
self.pm.getNearestDocuments(newDocWithANearbySignature), set([1])
) # This assertion can sometimes fail because of randomization. Run the tests again. It's OK!
def test_setSignatureUsingVectors(self):
phraseTextAndDimensionMap = TwoWayMap()
phraseTextAndDimensionMap.set(TwoWayMap.MAP_FORWARD, 'a', 1)
phraseTextAndDimensionMap.set(TwoWayMap.MAP_FORWARD, 'b', 2)
documentWithDimensionsInVector = Document(1, {'a': 1, 'b': 4})
documentWithDimensionsNotInVector = Document(1, {'a': 1, 'c': 4})
vectors = [
Vector({
1: 3 / 5.,
2: -4 / 5.
}),
Vector({
1: -5 / 13.,
2: 12 / 13.
})
]
documentWithDimensionsInVector.setSignatureUsingVectors(
vectors, phraseTextAndDimensionMap)
documentWithDimensionsNotInVector.setSignatureUsingVectors(
vectors, phraseTextAndDimensionMap)
self.assertEqual(Signature('01'),
documentWithDimensionsInVector.signature)
self.assertEqual(Signature('10'),
documentWithDimensionsNotInVector.signature)
def test_getNearestSignature_nearbyKey(self):
self.assertEquals(
SignatureTrie.getNearestSignatureKey(self.tr, Signature('1100')),
'1000')
def test_permutate(self):
sgnt = Signature('1001011')
self.assertTrue(sgnt.count() == sgnt.permutate(
SignaturePermutationWithTrie(7)).count())
def test_initialization(self):
sgnt = Signature('1001011')
self.assertEqual(sgnt.count(), 4)
sgnt = Signature()
self.assertEqual(sgnt.count(), 0)
def test_permutate(self):
sgnt = Signature('1001011')
self.assertTrue(sgnt.count()==sgnt.permutate(SignaturePermutationWithTrie(7)).count())
def test_initialization(self):
sgnt = Signature('1001011')
self.assertEqual(sgnt.count(), 4)
sgnt = Signature()
self.assertEqual(sgnt.count(), 0)
