def main():
t0 = time.time()
folder = 'text/'
tweets = Tweets.load_from_folder(folder)
print "Tweets loaded {0}s".format(time.time() - t0)
duration = 60
results = []
runs = [
"nhl", "any", "nba", "nfl"
]
for run in runs:
t0 = time.time()
for day in range(7,28):
for hour in range(0,24):
for minute in [0,15,30,45]:
end = datetime.datetime(2014, 11, day, hour=hour, minute=minute)
start = end - datetime.timedelta(seconds=60 * duration)
data = tweets.get_collection(start, end, run if run != 'any' else None)
if len(data) == 0:
break
result_date = start.strftime('%Y-%m-%d %H:%M') + " - " + end.strftime('%Y-%m-%d %H:%M')
result_clusters = cluster(data,5, [])
results.append({"date": result_date, "clusters": result_clusters})
#dot()
print end, len(data)
print
with open("viz/" + run + "_15_60.json", "w") as f:
json.dump(results, f)
print run + ' done, ', time.time() - t0, 'seconds'
def main():
t0 = time.time()
folder = 'text/'
tweets = Tweets.load_from_folder(folder)
print "Tweets loaded"
duration = 30
results = []
for day in range(7,28):
for hour in range(0,24):
for minute in [0,15,30,45]:
end = datetime.datetime(2014, 11, day, hour=hour, minute=minute)
start = end - datetime.timedelta(seconds=60 * duration)
data = tweets.get_collection(start, end)
if len(data) == 0:
break
result_date = start.strftime('%Y-%m-%d %H:%M') + " - " + end.strftime('%Y-%m-%d %H:%M')
result_clusters = cluster(data,5, [])
results.append({"date": result_date, "clusters": result_clusters})
#dot()
print end, len(data)
print
with open("viz/any_15_30.json", "w") as f:
json.dump(results, f)
print 'done, ', time.time() - t0, 'seconds'
