def iterateExpertClusters(startingDay=datetime(2011,3,19), endingDay=datetime(2011,3, 30)):
# def iterateExpertClusters(startingDay=datetime(2011,3,19), endingDay=datetime(2011,4,7)):
while startingDay<=endingDay:
for line in FileIO.iterateJsonFromFile(experts_twitter_stream_settings.lsh_clusters_folder+FileIO.getFileByDay(startingDay)):
currentTime = getDateTimeObjectFromTweetTimestamp(line['time_stamp'])
for clusterMap in line['clusters']: yield (currentTime, TwitterCrowdsSpecificMethods.getClusterFromMapFormat(clusterMap))
startingDay+=timedelta(days=1)
def test_getClusterFromMapFormat(self):
mapReresentation = {'clusterId': 1, 'mergedClustersList': [self.cluster1.clusterId], 'lastStreamAddedTime': getStringRepresentationForTweetTimestamp(test_time), 'streams': [self.doc1.docId], 'dimensions': {'#tcot':2, 'dsf':2}}
cluster = TwitterCrowdsSpecificMethods.getClusterFromMapFormat(mapReresentation)
self.assertEqual(1, cluster.clusterId)
self.assertEqual([self.cluster1.clusterId], cluster.mergedClustersList)
self.assertEqual([self.doc1.docId], cluster.documentsInCluster)
self.assertEqual({'#tcot':2, 'dsf':2}, cluster)
self.assertEqual(getStringRepresentationForTweetTimestamp(test_time), getStringRepresentationForTweetTimestamp(cluster.lastStreamAddedTime))
def dataIterator(self):
for currentTime, clusterMaps in sorted(self.clusterMaps.iteritems()):
for clusterMap in clusterMaps:
yield (currentTime,
TwitterCrowdsSpecificMethods.getClusterFromMapFormat(
clusterMap))
def dataIterator(self):
for currentTime, clusterMaps in sorted(self.clusterMaps.iteritems()):
for clusterMap in clusterMaps: yield (currentTime, TwitterCrowdsSpecificMethods.getClusterFromMapFormat(clusterMap))
