def main():
outputFile = open(cleanedPath, "w")
with open(tweetPath, "r") as tweetLines:
for line in tweetLines:
possibleTweet = parseJson(line)
if isATweet(possibleTweet):
outputFile.write("%s\n" % getTextAndTimestamp(possibleTweet))
outputFile.write("%s tweets contained unicode." % getTextAndTimestamp.tweetsWithUnicode)
def main():
outputFile = open(feature2FilePath, "w")
with open(tweetPath, "r") as tweetLines:
for line in tweetLines:
possibleTweet = parseJson(line)
#check if is tweet. Assume valid tweets cotains 'created_at' and 'entities.hashtags' according to https://dev.twitter.com/overview/api/tweets field guide
if (('created_at' in possibleTweet) and ('entities' in possibleTweet) and ('hashtags' in possibleTweet['entities'])):
graph = updateGrapWith(possibleTweet)
avgDegree = float(0)
if graph:
#remove multiple adjacencies use to track mutiple tweets
trueGraph = { vertice: set(edges) for (vertice, edges) in graph.iteritems() }
#calculate avg_deg
avgDegree = float(sum([len(edges) for edges in trueGraph.values()])) / len(graph)
average_degree = "{0:.2f}".format(avgDegree)
outputFile.write('%s\n' % average_degree)
