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 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_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 __init__(self, vector=None, dimensions=None, mu=None, sigma=None):
if vector == None:
vector = VectorGenerator.getRandomGaussianUnitVector(
dimensions, mu, sigma)
super(RandomGaussianUnitVector,
self).__init__(vector.getNormalizedVector())
else:
super(RandomGaussianUnitVector, self).__init__(vector)
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_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_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_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_setSignatureUsingVectorPermutations(self):
dimensions, signatureLength = 53, 13
phraseTextAndDimensionMap = TwoWayMap()
for i in range(dimensions): phraseTextAndDimensionMap.set(TwoWayMap.MAP_FORWARD, i,i)
phraseTextAndDimensionMapWithMissingDimensions = TwoWayMap()
for i in range(dimensions-50): phraseTextAndDimensionMapWithMissingDimensions.set(TwoWayMap.MAP_FORWARD, i,i)
unitVector = RandomGaussianUnitVector(dimensions=dimensions, mu=0, sigma=1)
vectorPermutations = VectorPermutation.getPermutations(signatureLength, dimensions, unitVector)
permutatedUnitVectors = [unitVector.getPermutedVector(r) for r in vectorPermutations]
documentVector = VectorGenerator.getRandomGaussianUnitVector(dimension=dimensions, mu=0, sigma=1)
documentWithSignatureByVectors=Document(1, documentVector)
documentWithSignatureByVectorPermutations=Document(2, documentVector)
documentWithSignatureByVectors.setSignatureUsingVectors(permutatedUnitVectors, phraseTextAndDimensionMap)
documentWithSignatureByVectorPermutations.setSignatureUsingVectorPermutations(unitVector, vectorPermutations, phraseTextAndDimensionMap)
self.assertEqual(documentWithSignatureByVectors.signature, documentWithSignatureByVectorPermutations.signature)
documentWithSignatureByVectors.setSignatureUsingVectors(permutatedUnitVectors, phraseTextAndDimensionMapWithMissingDimensions)
documentWithSignatureByVectorPermutations.setSignatureUsingVectorPermutations(unitVector, vectorPermutations, phraseTextAndDimensionMapWithMissingDimensions)
self.assertEqual(documentWithSignatureByVectors.signature, documentWithSignatureByVectorPermutations.signature)
def test_setSignatureUsingVectorPermutations(self):
dimensions, signatureLength = 53, 13
phraseTextAndDimensionMap = TwoWayMap()
for i in range(dimensions):
phraseTextAndDimensionMap.set(TwoWayMap.MAP_FORWARD, i, i)
phraseTextAndDimensionMapWithMissingDimensions = TwoWayMap()
for i in range(dimensions - 50):
phraseTextAndDimensionMapWithMissingDimensions.set(
TwoWayMap.MAP_FORWARD, i, i)
unitVector = RandomGaussianUnitVector(dimensions=dimensions,
mu=0,
sigma=1)
vectorPermutations = VectorPermutation.getPermutations(
signatureLength, dimensions, unitVector)
permutatedUnitVectors = [
unitVector.getPermutedVector(r) for r in vectorPermutations
]
documentVector = VectorGenerator.getRandomGaussianUnitVector(
dimension=dimensions, mu=0, sigma=1)
documentWithSignatureByVectors = Document(1, documentVector)
documentWithSignatureByVectorPermutations = Document(2, documentVector)
documentWithSignatureByVectors.setSignatureUsingVectors(
permutatedUnitVectors, phraseTextAndDimensionMap)
documentWithSignatureByVectorPermutations.setSignatureUsingVectorPermutations(
unitVector, vectorPermutations, phraseTextAndDimensionMap)
self.assertEqual(documentWithSignatureByVectors.signature,
documentWithSignatureByVectorPermutations.signature)
documentWithSignatureByVectors.setSignatureUsingVectors(
permutatedUnitVectors,
phraseTextAndDimensionMapWithMissingDimensions)
documentWithSignatureByVectorPermutations.setSignatureUsingVectorPermutations(
unitVector, vectorPermutations,
phraseTextAndDimensionMapWithMissingDimensions)
self.assertEqual(documentWithSignatureByVectors.signature,
documentWithSignatureByVectorPermutations.signature)
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 __init__(self, vector=None, dimensions=None, mu=None, sigma=None):
if vector==None:
vector = VectorGenerator.getRandomGaussianUnitVector(dimensions, mu, sigma)
super(RandomGaussianUnitVector, self).__init__(vector.getNormalizedVector())
else: super(RandomGaussianUnitVector, self).__init__(vector)