def test_addDocument_newKey(self):
doc1 = Document(
1,
VectorGenerator.getRandomGaussianUnitVector(
dimension=self.dimension, mu=0, sigma=1))
doc1.setSignatureUsingVectors(self.unitRandomVectors,
self.phraseTextAndDimensionMap)
pm = SignaturePermutationWithTrie(signatureLength=self.signatureLength)
pm.addDocument(doc1)
self.assertEqual(pm.signatureTrie[doc1.signature.permutate(pm).to01()],
set([1]))
class SignaturePermutationTests(unittest.TestCase):
def setUp(self):
self.dimension, self.signatureLength = 50, 23
self.phraseTextAndDimensionMap = TwoWayMap()
for i in range(self.dimension): self.phraseTextAndDimensionMap.set(TwoWayMap.MAP_FORWARD, i,i)
self.unitRandomVectors = [VectorGenerator.getRandomGaussianUnitVector(dimension=self.dimension, mu=0, sigma=1) for i in range(self.signatureLength)]
self.doc1=Document(1, VectorGenerator.getRandomGaussianUnitVector(dimension=self.dimension, mu=0, sigma=1))
self.doc2=Document(2, VectorGenerator.getRandomGaussianUnitVector(dimension=self.dimension, mu=0, sigma=1))
self.doc1.setSignatureUsingVectors(self.unitRandomVectors, self.phraseTextAndDimensionMap); self.doc2.setSignatureUsingVectors(self.unitRandomVectors, self.phraseTextAndDimensionMap)
self.pm = SignaturePermutationWithTrie(signatureLength=self.signatureLength)
self.pm.addDocument(self.doc1)
self.pm.addDocument(self.doc2)
def test_addDocument_newKey(self):
doc1=Document(1, VectorGenerator.getRandomGaussianUnitVector(dimension=self.dimension, mu=0, sigma=1))
doc1.setSignatureUsingVectors(self.unitRandomVectors, self.phraseTextAndDimensionMap)
pm = SignaturePermutationWithTrie(signatureLength=self.signatureLength)
pm.addDocument(doc1)
self.assertEqual(pm.signatureTrie[doc1.signature.permutate(pm).to01()], set([1]))
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_usingAKeyAlreadyInTrie(self): self.assertEqual(self.pm.getNearestDocuments(self.doc1), set([1]))
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_getNearestDocument_emptyTrie(self):
permutationWithEmptyTrie = SignaturePermutationWithTrie(signatureLength=self.signatureLength)
self.assertEqual(permutationWithEmptyTrie.getNearestDocuments(self.doc1), set())
def test_removeDocument_documents(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]))
self.pm.removeDocument(newDocModifiedWithExistingSignature)
self.assertEqual(self.pm.signatureTrie[self.doc1.signature.permutate(self.pm).to01()], set([1]))
self.pm.removeDocument(self.doc1)
self.assertEqual(None, self.pm.signatureTrie.get(self.doc1.signature.permutate(self.pm).to01()))
def test_resetSignatureTrie(self):
self.assertTrue(len(self.pm.signatureTrie)>0)
self.pm.resetSignatureDataStructure()
self.assertTrue(len(self.pm.signatureTrie)==0)
class SignaturePermutationTests(unittest.TestCase):
def setUp(self):
self.dimension, self.signatureLength = 50, 23
self.phraseTextAndDimensionMap = TwoWayMap()
for i in range(self.dimension):
self.phraseTextAndDimensionMap.set(TwoWayMap.MAP_FORWARD, i, i)
self.unitRandomVectors = [
VectorGenerator.getRandomGaussianUnitVector(
dimension=self.dimension, mu=0, sigma=1)
for i in range(self.signatureLength)
]
self.doc1 = Document(
1,
VectorGenerator.getRandomGaussianUnitVector(
dimension=self.dimension, mu=0, sigma=1))
self.doc2 = Document(
2,
VectorGenerator.getRandomGaussianUnitVector(
dimension=self.dimension, mu=0, sigma=1))
self.doc1.setSignatureUsingVectors(self.unitRandomVectors,
self.phraseTextAndDimensionMap)
self.doc2.setSignatureUsingVectors(self.unitRandomVectors,
self.phraseTextAndDimensionMap)
self.pm = SignaturePermutationWithTrie(
signatureLength=self.signatureLength)
self.pm.addDocument(self.doc1)
self.pm.addDocument(self.doc2)
def test_addDocument_newKey(self):
doc1 = Document(
1,
VectorGenerator.getRandomGaussianUnitVector(
dimension=self.dimension, mu=0, sigma=1))
doc1.setSignatureUsingVectors(self.unitRandomVectors,
self.phraseTextAndDimensionMap)
pm = SignaturePermutationWithTrie(signatureLength=self.signatureLength)
pm.addDocument(doc1)
self.assertEqual(pm.signatureTrie[doc1.signature.permutate(pm).to01()],
set([1]))
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_usingAKeyAlreadyInTrie(self):
self.assertEqual(self.pm.getNearestDocuments(self.doc1), set([1]))
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_getNearestDocument_emptyTrie(self):
permutationWithEmptyTrie = SignaturePermutationWithTrie(
signatureLength=self.signatureLength)
self.assertEqual(
permutationWithEmptyTrie.getNearestDocuments(self.doc1), set())
def test_removeDocument_documents(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]))
self.pm.removeDocument(newDocModifiedWithExistingSignature)
self.assertEqual(
self.pm.signatureTrie[self.doc1.signature.permutate(
self.pm).to01()], set([1]))
self.pm.removeDocument(self.doc1)
self.assertEqual(
None,
self.pm.signatureTrie.get(
self.doc1.signature.permutate(self.pm).to01()))
def test_resetSignatureTrie(self):
self.assertTrue(len(self.pm.signatureTrie) > 0)
self.pm.resetSignatureDataStructure()
self.assertTrue(len(self.pm.signatureTrie) == 0)
def test_addDocument_newKey(self):
doc1=Document(1, VectorGenerator.getRandomGaussianUnitVector(dimension=self.dimension, mu=0, sigma=1))
doc1.setSignatureUsingVectors(self.unitRandomVectors, self.phraseTextAndDimensionMap)
pm = SignaturePermutationWithTrie(signatureLength=self.signatureLength)
pm.addDocument(doc1)
self.assertEqual(pm.signatureTrie[doc1.signature.permutate(pm).to01()], set([1]))