def __init__(self, config):
self._access_token = config.get('twitter','access_token')
self._access_token_secret = config.get('twitter','access_token_secret')
self._consumer_key = config.get('twitter','consumer_key')
self._consumer_secret = config.get('twitter','consumer_secret')
# Retrieve terms to track
track_file = open(config.get('track','file'), 'r')
self._track_terms = [line.rstrip('\n').rstrip('\r') for line in track_file]
self._start_index = int(config.get('track','offset'))
# Store tweets temporarily and dump them to file at an interval
self._tweets_to_insert = []
# Initialize Kafka or File Writer
if config.get('output','type') == 'kafka':
self._writer = kafka.KafkaConnection(brokers=config.get('output','kafka_brokers'),
topic=config.get('output','kafka_topic'))
else:
data_dir = 'data/'+datetime.datetime.now().strftime('%Y-%m-%d')+'-'
self._writer = filewriter.FileWriter(filename=data_dir+config.get('output','filename'))
#This handles Twitter authetification and the connection to Twitter
self._auth = tweepy.OAuthHandler(self._consumer_key, self._consumer_secret)
self._auth.set_access_token(self._access_token, self._access_token_secret,)
self._connect()
# Initialize twitter statistics
self._twitter_stats = {'tweets':0}
self._max_tweet_id = {}
self._twitter_streams = []
def handle_output(puid_type, puid_str, file_no, int_sig_no):
sigID = 0
for x in content_list:
if x[0] == 'Internal Signature ID':
fr = filewriter.FileWriter(puid_type) #create file writing object
if x[1] != sigID:
sigID = x[1]
if content_list[1][0] == 'File Extension':
ext = content_list[1][1]
else:
ext = 'nul'
#New internal sig, new file - create
fr.write_file(puid_type, file_no, sigID, puid_str, ext)
if x[0] == 'Byte sequence':
if x[1][0] == 'Absolute from BOF':
fr.write_header(x[1][0], x[1][1], x[1][2], x[1][3])
if x[1][0] == 'Absolute from EOF':
fr.write_footer(x[1][0], x[1][1], x[1][2], x[1][3])
if x[1][0] == 'Variable':
fr.write_var(x[1][0], x[1][1], x[1][2], x[1][3])
def handle_output(puid_type, puid_str, file_no, int_sig_no):
sigID = 0
for x in content_list:
if x[0] == 'Internal Signature ID':
fr = filewriter.FileWriter(puid_type) #create file writing object
if x[1] != sigID:
sigID = x[1]
if content_list[1][0] == 'File Extension':
ext = content_list[1][1]
else:
ext = 'nul'
#New internal sig, new file - create
fr.write_file(puid_type, file_no, sigID, puid_str, ext)
if x[0] == 'Byte sequence':
pos = x[1][0]
min = x[1][1]
max = x[1][2]
seq = x[1][3]
if min == 'null':
min = 0
if max == 'null':
max = 0
min = int(min)
max = int(max)
if pos == 'Absolute from BOF':
fr.write_header(pos, min, max, seq)
if pos == 'Absolute from EOF':
fr.write_footer(pos, min, max, seq)
if pos == 'Variable':
if min > 0:
print puid_str + " " + str(min)
fr.write_var(pos, min, max, seq)
maxAverageDiameterThreshold = args.maxAverageDiameterThreshold
# call samplegenerator which calls RNAxplorer (in matrix2d objects) and executes a clustering (2D or DIANA, etc.) only to select
# new structure representatives for samplegeneration.
structures = samplegenerator.mainloop(twoDSamplingParameters)
# call final clusteralg.
clusters = DIANA.doClustering(structures, maxDiameterThreshold,
maxAverageDiameterThreshold)
DIANA.printClusters(clusters)
representatives = selectRepresentatives(seq, clusters)
# prepare representatives and sort them, to make the comparison of the output easier.
repsAndEnergies = [(x, RNA.energy_of_struct(seq, x))
for x in representatives]
repsAndEnergies.sort(key=operator.itemgetter(1, 0))
# rate computation.
rateMatrix = Rates.arrheniusRates(seq, repsAndEnergies)
# write files for treekin (matrix and structures)
fw = filewriter.FileWriter()
fw.writeMatrixToFile(rateMatrix, param.RatesFilePath)
fw.writeRepresentativesToFile(seq, repsAndEnergies,
param.StructuresFilePath)
# run treekin
to_call = "cat " + param.StructuresFilePath + " | treekin --p0 " + str(param.StartStructureID) + "=1 --ratesfile " + param.RatesFilePath + " --t0 " + \
str(param.StartTime) + " --t8 " + str(param.EndTime) + " -m I > " + param.KineticFile
os.system(to_call)