def main():
import preproc_qqtopic
import extract_keyword2
#import worddf
dbfile = '../data/noise_test.db'
lognoisefile = '../result/noise_test.log'
noisefile = open(lognoisefile,'w')
noisefile.write(out_result_header())
rang = xrange(0,250, 60)
for num in rang:
dbfile = '../data/noise%d_test.db' % (num,)
files = sample_docs(num)
if os.path.exists(dbfile):
os.remove(dbfile)
dbcon = preproc_qqtopic.init_db(dbfile)
preproc_qqtopic.load_topiclist(dbcon,'../data/topicgj')
cnt = preproc_qqtopic.load_topic(dbcon,'noise_data',files)
dbcon.close()
print 'add number of noise document: %d' % cnt
eva = WordWeightEvaluation(30, '../data/worddf')
ke = extract_keyword2.DBKeywordExtractor(dbfile, eva)
ke.init_db()
ke.content_keyword()
ke.title_keyword()
ke.topic_keyword()
ke.close_db()
def main():
import preproc_qqtopic
import extract_keyword2
import worddf
dbfile = '../data/steady_test.db'
logsteadyfile = '../result/steady_test.log'
steadyfile = open(logsteadyfile,'w')
steadyfile.write(out_result_header())
if not os.path.exists(dbfile):
preproc_qqtopic.load_topiclist(dbfile,'../data/topicgj')
ke = extract_keyword2.DBKeywordExtractor(dbfile)
ke.init_db()
ke.content_keyword()
ke.title_keyword()
ke.topic_keyword()
ke.close_db()
cb = CommunityBuilder(dbfile)
metrics = list()
c = 50
real = cmpcluster.load_doc_labels(dbfile)
print 'steady_test'
for i in range(c):
print 'Time %d' % (i+1)
predicted = cb.build()
metrics.append(cmp_cluster(predicted,real))
mean,std = mean_std(metrics)
meanstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(mean)
stdstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(std)
steadyfile.write(meanstr)
steadyfile.write(stdstr)
steadyfile.close()
os.system('emacs '+logsteadyfile)
def main():
import preproc_qqtopic
import extract_keyword2
import worddf
dbfile = '../data/steady_test.db'
logsteadyfile = '../result/steady_test.log'
steadyfile = open(logsteadyfile, 'w')
steadyfile.write(out_result_header())
if not os.path.exists(dbfile):
preproc_qqtopic.load_topiclist(dbfile, '../data/topicgj')
ke = extract_keyword2.DBKeywordExtractor(dbfile)
ke.init_db()
ke.content_keyword()
ke.title_keyword()
ke.topic_keyword()
ke.close_db()
cb = CommunityBuilder(dbfile)
metrics = list()
c = 50
real = cmpcluster.load_doc_labels(dbfile)
print 'steady_test'
for i in range(c):
print 'Time %d' % (i + 1)
predicted = cb.build()
metrics.append(cmp_cluster(predicted, real))
mean, std = mean_std(metrics)
meanstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(mean)
stdstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(std)
steadyfile.write(meanstr)
steadyfile.write(stdstr)
steadyfile.close()
os.system('emacs ' + logsteadyfile)