def getEvaluationMetrics(self, documentClusters, timeDifference):
iterationData = {'no_of_documents':self.length, 'no_of_clusters': len(documentClusters), 'iteration_time': timeDifference, 'clusters': documentClusters}
clustersForEvaluation = [self._getExpertClasses(cluster) for cluster in documentClusters]
iterationData['nmi'] = EvaluationMetrics.getValueForClusters(clustersForEvaluation, EvaluationMetrics.nmi)
iterationData['purity'] = EvaluationMetrics.getValueForClusters(clustersForEvaluation, EvaluationMetrics.purity)
iterationData['f1'] = EvaluationMetrics.getValueForClusters(clustersForEvaluation, EvaluationMetrics.f1)
return iterationData
def getEvaluationMetrics(self, documentClusters, timeDifference, iteration_parameters):
iterationData = {'iteration_parameters': iteration_parameters, 'no_of_clusters': len(documentClusters), 'iteration_time': timeDifference, 'clusters': documentClusters}
clustersForEvaluation = [self._getExpertClasses(cluster) for cluster in documentClusters]
iterationData['nmi'] = EvaluationMetrics.getValueForClusters(clustersForEvaluation, EvaluationMetrics.nmi)
iterationData['purity'] = EvaluationMetrics.getValueForClusters(clustersForEvaluation, EvaluationMetrics.purity)
iterationData['f1'] = EvaluationMetrics.getValueForClusters(clustersForEvaluation, EvaluationMetrics.f1)
return iterationData
def getEvaluationMetrics(self, documentClusters, timeDifference, iteration_parameters):
iterationData = {
"iteration_parameters": iteration_parameters,
"no_of_clusters": len(documentClusters),
"iteration_time": timeDifference,
"clusters": documentClusters,
}
clustersForEvaluation = [self._getExpertClasses(cluster) for cluster in documentClusters]
iterationData["nmi"] = EvaluationMetrics.getValueForClusters(clustersForEvaluation, EvaluationMetrics.nmi)
iterationData["purity"] = EvaluationMetrics.getValueForClusters(clustersForEvaluation, EvaluationMetrics.purity)
iterationData["f1"] = EvaluationMetrics.getValueForClusters(clustersForEvaluation, EvaluationMetrics.f1)
return iterationData
def getEvaluationMetrics(noOfTweets, documentClusters, timeDifference):
iterationData = {
'no_of_tweets': noOfTweets,
'no_of_clusters': len(documentClusters),
'iteration_time': timeDifference,
'clusters': documentClusters
}
clustersForEvaluation = [
Evaluation.getExpertClasses(cluster)
for cluster in documentClusters
]
iterationData['nmi'] = EvaluationMetrics.getValueForClusters(
clustersForEvaluation, EvaluationMetrics.nmi)
iterationData['purity'] = EvaluationMetrics.getValueForClusters(
clustersForEvaluation, EvaluationMetrics.purity)
iterationData['f1'] = EvaluationMetrics.getValueForClusters(
clustersForEvaluation, EvaluationMetrics.f1)
return iterationData
def getCrowdQuality(self, evaluationMetric, expertsToClassMap):
def getExpertClasses(cluster):
return [
expertsToClassMap[user.lower()]
for user in cluster.documentsInCluster
if user.lower() in expertsToClassMap
]
return EvaluationMetrics.getValueForClusters(
[getExpertClasses(cluster) for cluster in self.clusters.itervalues()], evaluationMetric
)
def getCrowdQuality(self, evaluationMetric, expertsToClassMap):
def getExpertClasses(cluster):
return [
expertsToClassMap[user.lower()]
for user in cluster.documentsInCluster
if user.lower() in expertsToClassMap
]
return EvaluationMetrics.getValueForClusters([
getExpertClasses(cluster)
for cluster in self.clusters.itervalues()
], evaluationMetric)
def streamingLSHClusteringDemo():
clustering_settings = {'dimensions': 53,
'signature_length': 13,
'number_of_permutations': 5,
'threshold_for_document_to_be_in_cluster': 0.2}
clustering=StreamingLSHClustering(**clustering_settings)
docId = 0
docsToOriginalClusterMap = {}
for line in FileIO.iterateLinesFromFile('../data/streaming.dat'):
document = createDocumentFromLine(docId, line)
docsToOriginalClusterMap[docId] = document.clusterId
docId+=1
clustering.getClusterAndUpdateExistingClusters(document)
clusterLabels = []
for k, cluster in clustering.clusters.iteritems(): clusterLabels.append([docsToOriginalClusterMap[doc.docId] for doc in cluster.iterateDocumentsInCluster()])
return EvaluationMetrics.getValueForClusters(clusterLabels, EvaluationMetrics.purity)
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)
