# Calculate similarity values for given article
sim_matrix = []
if version.lower() == 'p':
if rank == 0:
for i in range(1,size):
comm.send(1, dest = i)
sim_matrix = sorted(enumerate(Process.main_parallel_sim(comm, ind, abstracts, type, mattype)), key=lambda ind:ind[1])
else:
tosend = comm.recv(source = 0)
if tosend == 1:
Process.main_parallel_sim(comm, ind, abstracts, type, mattype)
elif tosend == 0:
sys.exit()
else:
if rank == 0:
sim_matrix = sorted(enumerate(Process.main_serial_sim(comm, ind, abstracts, type, mattype)), key=lambda ind:ind[1])
else:
sys.exit()
# print 5 most similar articles
if rank == 0:
print "Similar articles:\n"
setabs = 0
while True:
if len(sim_matrix)/5 <= setabs+1:
print "No more articles to see ..."
if version.lower() == 'p':
for i in range(1,size):
comm.send(0, dest = i)
sys.exit("Thanks for visiting!")
for i in range(5):
ind, val = sim_matrix[i+setabs*5+1]
sfreqend = time.time()
# create dict of tfidf
stfidfstart = time.time()
Process.serial_tfidf(abstracts, 'bow', termbow, len(bigramdict))
Process.serial_tfidf(abstracts, 'bigram', termbigram)
stfidfend = time.time()
# do some topic modeling
stopicstart = time.time()
Process.serial_topics(abstracts, Process.numtopics)
stopicend = time.time()
# test similarity
ssimbowstart = MPI.Wtime()
Process.main_serial_sim(comm, 0, abstracts, 'bow', 'cossim')
ssimbowend = MPI.Wtime()
ssimbigramstart = MPI.Wtime()
Process.main_serial_sim(comm, 0, abstracts, 'bigram', 'cossim')
ssimbigramend = MPI.Wtime()
ssimjacstart = MPI.Wtime()
Process.main_serial_sim(comm, 0, abstracts, 'bow', 'jaccard')
ssimjacend = MPI.Wtime()
# print times
print "Serial times"
print "Load time: %f secs" % (sloadend - sloadstart)
print "Create dictionary time: %f secs" % (sdictend - sdictstart)
print "Clean text time: %f secs" % (scleanend - scleanstart)
print "Frequency time: %f secs" % (sfreqend - sfreqstart)
print "TF-IDF time: %f secs" % (stfidfend - stfidfstart)
