sentsPerProc = int(math.floor(len(sentences)*1.0/numOfProcesses))
processes = []
lock = Lock()
test_json_file = open(test_json, 'w', 0)
for i in range(numOfProcesses):
if i == numOfProcesses - 1:
p = Process(target=parse, args=(sentences[i*sentsPerProc:], test_json_file, lock))
else:
p = Process(target=parse, args=(sentences[i*sentsPerProc:(i+1)*sentsPerProc], test_json_file, lock))
p.start()
processes.append(p)
for proc in processes:
proc.join()
test_json_file.close()
print 'Start feature extraction'
pipeline(train_json, indir + '/brown', outdir)
filter(outdir+'/feature.map', outdir+'/train_x.txt', outdir+'/feature.txt', outdir+'/train_x_new.txt')
pipeline_test(test_json, indir + '/brown', outdir+'/feature.txt',outdir+'/type.txt', outdir)
supertype(outdir)
distribution(outdir)
# Perform no pruning to generate training data
print 'Start training and test data generation'
feature_number = get_number(outdir+'/feature.txt')
type_number = get_number(outdir+'/type.txt')
prune(outdir, outdir, 'no', feature_number, type_number)
# Generate type type correlation
print 'Start type correlation calculation'
share_entity(indir + '/type_entities.txt', outdir + '/type.txt', outdir + '/type_type_kb.txt')
print 'Start rm feature extraction'
pipeline(train_json,
indir + '/brown',
outdir,
requireEmType=False,
isEntityMention=False)
pipeline_qa(qa_json,
indir + '/brown',
outdir + '/feature.map',
outdir + '/type.txt',
outdir,
requireEmType=False,
isEntityMention=False)
filter(outdir + '/feature.map', outdir + '/train_x.txt',
outdir + '/feature.txt', outdir + '/train_x_new.txt',
feature_freq_threshold)
filter(outdir + '/feature.map', outdir + '/qa_x.txt',
outdir + '/feature.txt', outdir + '/qa_x_new.txt',
feature_freq_threshold)
pipeline_test(test_json,
indir + '/brown',
outdir + '/feature.txt',
outdir + '/type.txt',
outdir,
requireEmType=False,
isEntityMention=False)
### Perform no pruning to generate training data
print 'Start rm training and test data generation'
feature_number = get_number(outdir + '/feature.txt')