class RandomGaussianUnitVectorTests(unittest.TestCase):
def setUp(self):
self.vector = RandomGaussianUnitVector(dimensions=5, mu=0, sigma=1)
self.permutation = VectorPermutation(dimensions=5)
def test_initialization(self): self.assertEquals('%0.0f'%self.vector.mod(),'1')
def test_getPermutedDimensionValue(self): self.assertEqual(self.vector[self.permutation.applyFunction(10)], self.vector.getPermutedDimensionValue(self.permutation, 10))
def test_getPermutedVector(self):
permutedVector = self.vector.getPermutedVector(self.permutation)
self.assertEqual(RandomGaussianUnitVector, type(permutedVector))
self.assertNotEqual(self.vector, permutedVector)
self.assertEqual('1', '%0.0f'%permutedVector.mod())
def test_isPermutationSameAsVector(self):
self.permutation.a=1
self.permutation.b=0
self.assertTrue(self.vector.isPermutationSameAsVector(self.permutation))
def __init__(self, **settings):
self.settings = settings
self.nearestNeighborThreshold = settings['nearest_neighbor_threshold']
self.unitVector = RandomGaussianUnitVector(
dimensions=settings['dimensions'], mu=0, sigma=1)
self.vectorPermutations = VectorPermutation.getPermutations(
settings['signature_length'], settings['dimensions'],
self.unitVector)
# self.signaturePermutations = [SignaturePermutationWithTrie(settings['signature_length']) for i in range(settings['number_of_permutations'])]
signatureType = settings.get('signature_type', 'signature_type_trie')
if signatureType == 'signature_type_trie':
self.signaturePermutations = [
SignaturePermutationWithTrie(settings['signature_length'])
for i in range(settings['number_of_permutations'])
]
else:
self.signaturePermutations = [
SignaturePermutationWithSortedList(
settings['signature_length'])
for i in range(settings['number_of_permutations'])
]
self.phraseTextAndDimensionMap = TwoWayMap()
self.documentIdToDocumentMap = {}
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)
class RandomGaussianUnitVectorTests(unittest.TestCase):
def setUp(self):
self.vector = RandomGaussianUnitVector(dimensions=5, mu=0, sigma=1)
self.permutation = VectorPermutation(dimensions=5)
def test_initialization(self):
self.assertEquals('%0.0f' % self.vector.mod(), '1')
def test_getPermutedDimensionValue(self):
self.assertEqual(
self.vector[self.permutation.applyFunction(10)],
self.vector.getPermutedDimensionValue(self.permutation, 10))
def test_getPermutedVector(self):
permutedVector = self.vector.getPermutedVector(self.permutation)
self.assertEqual(RandomGaussianUnitVector, type(permutedVector))
self.assertNotEqual(self.vector, permutedVector)
self.assertEqual('1', '%0.0f' % permutedVector.mod())
def test_isPermutationSameAsVector(self):
self.permutation.a = 1
self.permutation.b = 0
self.assertTrue(self.vector.isPermutationSameAsVector(
self.permutation))
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 __init__(self, **clustering_settings):
self.thresholdForDocumentToBeInACluster = clustering_settings[
'threshold_for_document_to_be_in_cluster']
self.unitVector = RandomGaussianUnitVector(
dimensions=clustering_settings['dimensions'], mu=0, sigma=1)
self.vectorPermutations = VectorPermutation.getPermutations(
clustering_settings['signature_length'],
clustering_settings['dimensions'], self.unitVector)
signatureType = clustering_settings.get('signature_type',
'signature_type_trie')
if signatureType == 'signature_type_trie':
self.signaturePermutations = [
SignaturePermutationWithTrie(
clustering_settings['signature_length'])
for i in range(clustering_settings['number_of_permutations'])
]
else:
self.signaturePermutations = [
SignaturePermutationWithSortedList(
clustering_settings['signature_length'])
for i in range(clustering_settings['number_of_permutations'])
]
self.phraseTextAndDimensionMap, self.clusters = TwoWayMap(), {}
self.clustering_settings = clustering_settings
def setUp(self):
self.vector = RandomGaussianUnitVector(dimensions=5, mu=0, sigma=1)
self.permutation = VectorPermutation(dimensions=5)
def setUp(self):
self.vector = RandomGaussianUnitVector(dimensions=5, mu=0, sigma=1)
self.permutation = VectorPermutation(dimensions=5)
def offlineLSHClusteringDemo():
wordToDimensionMap = {}
def createDocumentFromLine(docId, line):
vector = Vector()
words = line.split()
for word in words[1:]:
if word not in wordToDimensionMap:
wordToDimensionMap[word] = len(wordToDimensionMap)
wordDimension = wordToDimensionMap[word]
if wordDimension not in vector: vector[wordDimension] = 1
else: vector[wordDimension] += 1
return Document(docId, vector, clusterId=words[0])
dimensions = 53
signatureLength = 13
numberOfPermutations = 5
unitVector = RandomGaussianUnitVector(dimensions=dimensions, mu=0, sigma=1)
vectorPermutations = VectorPermutation.getPermutations(
signatureLength, dimensions, unitVector)
signaturePermutations = [
SignaturePermutationWithTrie(signatureLength)
for i in range(numberOfPermutations)
]
permutatedUnitVectors = [
unitVector.getPermutedVector(r) for r in vectorPermutations
]
# Build LSH Model.
# Read training documents.
traningDocumentsMap = {}
for docId, l in enumerate(
FileIO.iterateLinesFromFile('../data/train_offline.dat')):
traningDocumentsMap[docId] = createDocumentFromLine(docId, l)
# Construct cluster vectors.
clusterToDocumentsMap = defaultdict(list)
for document in traningDocumentsMap.values():
clusterToDocumentsMap[document.clusterId].append(document)
clusterMap = {}
for k, v in clusterToDocumentsMap.iteritems():
clusterMap[k] = Document(docId=k,
vector=Vector.getMeanVector(v),
clusterId=k)
# Create signatures and signaturePermutations for all the clusters.
map(
lambda document: document.setSignatureUsingVectors(
permutatedUnitVectors), clusterMap.values())
for permutation in signaturePermutations:
for document in clusterMap.values():
permutation.addDocument(document)
# Testing the model.
# Read testing documents.
testDocumentsMap = {}
for docId, l in enumerate(
FileIO.iterateLinesFromFile('../data/test_offline.dat')):
testDocumentsMap[docId] = createDocumentFromLine(docId, l)
# Create signatures for test documents
map(
lambda document: document.setSignatureUsingVectors(
permutatedUnitVectors), testDocumentsMap.values())
predicted, labels = [], []
for t in testDocumentsMap.values():
possibleNearestClusters = reduce(
lambda x, y: x.union(y),
(permutation.getNearestDocuments(t)
for permutation in signaturePermutations), set())
predictedClass = max(
((clusterId, clusterMap[clusterId].cosineSimilarity(t))
for clusterId in possibleNearestClusters),
key=itemgetter(1))
predicted.append(predictedClass[0])
labels.append(t.clusterId)
return EvaluationMetrics.purity(predicted, labels)
