def setUp(self):
self.m1 = Message(1, 'sdf',
'A project to cluster high-dimensional streams.',
test_time - timedelta(seconds=60))
self.m1.vector = Vector({1: 1., 2: 3.})
self.stream = Stream(1, self.m1)
self.cluster = StreamCluster(self.stream)
self.crowd = Crowd(self.cluster, test_time)
def test_crowdSize(self):
self.assertEqual(1, self.crowd.crowdSize)
self.cluster.addDocument(Stream(2, self.m1))
self.cluster.addDocument(Stream(3, self.m1))
self.assertEqual(3, self.crowd.crowdSize)
cluster = StreamCluster(Stream(3, self.m1))
self.crowd.append(cluster, test_time + timedelta(days=2))
self.assertNotEqual(4, self.crowd.crowdSize)
self.assertEqual(3, self.crowd.crowdSize)
def setUp(self):
self.m1 = Message(1, 'sdf',
'A project to cluster high-dimensional streams.',
test_time - timedelta(seconds=60))
self.m1.vector = Vector({1: 2, 2: 4})
self.stream1 = Stream(1, self.m1)
self.m2 = Message(2, 'sdf',
'A project to cluster high-dimensional streams.',
test_time)
self.m2.vector = Vector({2: 4})
self.stream2 = Stream(2, self.m2)
self.m3 = Message(3, 'sdf',
'A project to cluster high-dimensional streams.',
test_time + timedelta(seconds=60))
self.m3.vector = Vector({2: 4})
self.stream3 = Stream(3, self.m3)
self.cluster1 = StreamCluster(self.stream1)
self.cluster2 = StreamCluster(self.stream2)
self.cluster3 = StreamCluster(self.stream3)
def getClusterFromMapFormat(clusterMap):
dummyMessage = Message(1, '', '', datetime.now())
dummyMessage.vector = Vector({})
dummyStream = Stream(1, dummyMessage)
cluster = StreamCluster(dummyStream)
cluster.clusterId = clusterMap['clusterId']
cluster.lastStreamAddedTime = getDateTimeObjectFromTweetTimestamp(
clusterMap['lastStreamAddedTime'])
cluster.mergedClustersList = clusterMap['mergedClustersList']
cluster.documentsInCluster = clusterMap['streams']
for k, v in clusterMap['dimensions'].iteritems():
cluster[k] = v
return cluster
def getClusterAndUpdateExistingClusters(self, stream):
predictedCluster = self.getClusterForDocument(stream)
if predictedCluster != None:
self.clusters[predictedCluster].addDocument(
stream, **self.stream_settings)
else:
newCluster = StreamCluster(stream)
newCluster.setSignatureUsingVectorPermutations(
self.unitVector, self.vectorPermutations,
self.phraseTextAndDimensionMap)
for permutation in self.signaturePermutations:
permutation.addDocument(newCluster)
self.clusters[newCluster.clusterId] = newCluster
def getClusterAndUpdateExistingClusters(self, stream):
predictedCluster = self.getClusterForDocument(stream)
'''
Do not remove this comment. Might need this if StreamCluster is used again in future.
if predictedCluster!=None: self.clusters[predictedCluster].addStream(stream, **self.stream_settings)
'''
if predictedCluster != None:
self.clusters[predictedCluster].addDocument(
stream, **self.stream_settings)
else:
newCluster = StreamCluster(stream)
newCluster.setSignatureUsingVectorPermutations(
self.unitVector, self.vectorPermutations,
self.phraseTextAndDimensionMap)
for permutation in self.signaturePermutations:
permutation.addDocument(newCluster)
self.clusters[newCluster.clusterId] = newCluster
