def infer_params(self, click_model, search_sessions, holdout_search_sessions=None):
if search_sessions is None or len(search_sessions) == 0:
return
if holdout_search_sessions is not None:
loglikelihood = LogLikelihood()
prompt = 'Starting EM for %s click model:' % click_model.__class__.__name__
print
print prompt
print '=' * len(prompt)
for iteration in xrange(self.iter_num):
new_click_model = click_model.__class__()
for search_session in search_sessions:
current_session_params = click_model.get_session_params(search_session)
new_session_params = new_click_model.get_session_params(search_session)
for rank, result in enumerate(search_session.web_results):
for param_name, param in new_session_params[rank].items():
param.update(search_session, rank, current_session_params)
click_model.params = new_click_model.params
if holdout_search_sessions is not None:
print 'Iteration %d/%d finished: %.12f log-likelihood.' % (iteration + 1, self.iter_num, loglikelihood.evaluate(click_model, holdout_search_sessions))
else:
print 'Iteration %d/%d finished.' % (iteration + 1, self.iter_num)
logger.info('train query num: {}'.format(len(train_dataset)))
logger.info('dev query num: {}'.format(len(dev_dataset)))
logger.info('test query num: {}'.format(len(test_dataset)))
logger.info('human label has {} queries'.format(len(relevance_queries)))
# Train
logger.info('Start training')
start = time.time()
click_model.train(train_dataset)
end = time.time()
logger.info('Finish training. Time consumed: {} seconds'.format(end -
start))
# Log likelihood
logger.info('Computing log likelihood')
loglikelihood = LogLikelihood()
start = time.time()
ll_value = loglikelihood.evaluate(click_model, test_dataset)
end = time.time()
logger.info('Log likelihood: {}. Time consumed: {} seconds'.format(
ll_value, end - start))
# Perplexity
logger.info('Computing perplexity')
perplexity = Perplexity()
start = time.time()
perp_value = perplexity.evaluate(click_model, test_dataset)[0]
end = time.time()
logger.info('Perplexity: {}. Time consumed: {} seconds'.format(
perp_value, end - start))
train_queries = Utils.get_unique_queries(train_sessions)
test_sessions = Utils.filter_sessions(search_sessions[train_test_split:], train_queries)
test_queries = Utils.get_unique_queries(test_sessions)
print("===============================")
print("Training on %d search sessions (%d unique queries)." % (len(train_sessions), len(train_queries)))
print("===============================")
start = time.time()
click_model.train(train_sessions)
end = time.time()
print("\tTrained %s click model in %i secs:\n%r" % (click_model.__class__.__name__, end - start, click_model))
print("-------------------------------")
print("Testing on %d search sessions (%d unique queries)." % (len(test_sessions), len(test_queries)))
print("-------------------------------")
loglikelihood = LogLikelihood()
perplexity = Perplexity()
start = time.time()
ll_value = loglikelihood.evaluate(click_model, test_sessions)
end = time.time()
print("\tlog-likelihood: %f; time: %i secs" % (ll_value, end - start))
start = time.time()
perp_value = perplexity.evaluate(click_model, test_sessions)[0]
end = time.time()
print("\tperplexity: %f; time: %i secs" % (perp_value, end - start))
sys.exit(1)
click_model = globals()[sys.argv[1]]()
search_sessions_path = sys.argv[2]
search_sessions_num = int(sys.argv[3])
search_sessions = YandexRelPredChallengeParser().parse(search_sessions_path, search_sessions_num)
train_test_split = int(len(search_sessions) * 0.75)
train_sessions = search_sessions[:train_test_split]
train_queries = Utils.get_unique_queries(train_sessions)
test_sessions = Utils.filter_sessions(search_sessions[train_test_split:], train_queries)
test_queries = Utils.get_unique_queries(test_sessions)
print "-------------------------------"
print "Training on %d search sessions (%d unique queries)." % (len(train_sessions), len(train_queries))
print "-------------------------------"
click_model.train(train_sessions)
print "\tTrained %s click model:\n%r" % (click_model.__class__.__name__, click_model)
print "-------------------------------"
print "Testing on %d search sessions (%d unique queries)." % (len(test_sessions), len(test_queries))
print "-------------------------------"
loglikelihood = LogLikelihood()
print "\tlog-likelihood: %f" % loglikelihood.evaluate(click_model, test_sessions)
perplexity = Perplexity()
print "\tperplexity: %f" % perplexity.evaluate(click_model, test_sessions)[0]
search_sessions_path, search_sessions_num)
train_test_split = int(len(search_sessions) * 0.75)
train_sessions = search_sessions[:train_test_split]
train_queries = Utils.get_unique_queries(train_sessions)
test_sessions = Utils.filter_sessions(search_sessions[train_test_split:],
train_queries)
test_queries = Utils.get_unique_queries(test_sessions)
print "-------------------------------"
print "Training on %d search sessions (%d unique queries)." % (
len(train_sessions), len(train_queries))
print "-------------------------------"
click_model.train(train_sessions)
print "\tTrained %s click model:\n%r" % (click_model.__class__.__name__,
click_model)
print "-------------------------------"
print "Testing on %d search sessions (%d unique queries)." % (
len(test_sessions), len(test_queries))
print "-------------------------------"
loglikelihood = LogLikelihood()
print "\tlog-likelihood: %f" % loglikelihood.evaluate(
click_model, test_sessions)
perplexity = Perplexity()
print "\tperplexity: %f" % perplexity.evaluate(click_model,
test_sessions)[0]
sys.exit(1)
click_model = globals()[sys.argv[1]]()
search_sessions_path = sys.argv[2]
search_sessions_num = int(sys.argv[3])
search_sessions = YandexRelPredChallengeParser().parse(search_sessions_path, search_sessions_num)
train_test_split = int(len(search_sessions) * 0.75)
train_sessions = search_sessions[:train_test_split]
train_queries = Utils.get_unique_queries(train_sessions)
test_sessions = Utils.filter_sessions(search_sessions[train_test_split:], train_queries)
test_queries = Utils.get_unique_queries(test_sessions)
print "-------------------------------"
print "Training on %d search sessions (%d unique queries)." % (len(train_sessions), len(train_queries))
print "-------------------------------"
click_model.train(search_sessions)
#print "\tTrained %s click model:\n%r" % (click_model.__class__.__name__, click_model)
print "-------------------------------"
print "Testing on %d search sessions (%d unique queries)." % (len(test_sessions), len(test_queries))
print "-------------------------------"
loglikelihood = LogLikelihood()
print "\tlog-likelihood: %f" % loglikelihood.evaluate(click_model, test_queries)
perplexity = Perplexity()
print "\tperplexity: %f" % perplexity.evaluate(click_model, test_queries)[0]