def performanceForCDAAt(noOfTweets, fileName, **stream_settings):
clustering=HDStreaminClustering(**stream_settings)
ts = time.time()
clustering.cluster(TwitterIterators.iterateFromFile(fileName))
te = time.time()
documentClusters = [cluster.documentsInCluster.keys() for k, cluster in clustering.clusters.iteritems() if len(cluster.documentsInCluster.keys())>=stream_settings['cluster_filter_threshold']]
return Evaluation.getEvaluationMetrics(noOfTweets, documentClusters, te-ts)
def performanceForCDAITAt(noOfTweets, fileName, **stream_settings):
ts = time.time()
sstObject = SimilarStreamAggregation(dict(iterateTweetUsersAfterCombiningTweets(fileName, **stream_settings)), stream_settings['ssa_threshold'])
sstObject.estimate()
documentClusters = list(sstObject.iterateClusters())
te = time.time()
return Evaluation.getEvaluationMetrics(noOfTweets, documentClusters, te-ts)
def performanceForCDAITAt(noOfTweets, fileName, **stream_settings):
ts = time.time()
sstObject = SimilarStreamAggregation(
dict(
iterateTweetUsersAfterCombiningTweets(fileName,
**stream_settings)),
stream_settings['ssa_threshold'])
sstObject.estimate()
documentClusters = list(sstObject.iterateClusters())
te = time.time()
return Evaluation.getEvaluationMetrics(noOfTweets, documentClusters,
te - ts)
def performanceForCDAAt(noOfTweets, fileName, **stream_settings):
clustering = HDStreaminClustering(**stream_settings)
ts = time.time()
clustering.cluster(TwitterIterators.iterateFromFile(fileName))
te = time.time()
documentClusters = [
cluster.documentsInCluster.keys()
for k, cluster in clustering.clusters.iteritems()
if len(cluster.documentsInCluster.keys()) >=
stream_settings['cluster_filter_threshold']
]
return Evaluation.getEvaluationMetrics(noOfTweets, documentClusters,
te - ts)
