Python read_dictionary_file Exemples

Exemple #1

Fichier : run_hefbib.py Projet : longislandicetea/HINExpertFinding

def run_level1():
	phrase_dist_files = [
		PHRASE_DIST_PATH + '1dm-seed-ext',
		PHRASE_DIST_PATH + '2ml-seed-ext',
		PHRASE_DIST_PATH + '3db-seed-ext',
		PHRASE_DIST_PATH + '4ir-seed-ext'
	]
	
	# set venue prior
	venue_name_idx, venue_idx_name = fio.read_dictionary_file(DATA_PATH + 'id_venue')
	venue_topical_prior = np.ones((5, 23))
	# dm
	venue_topical_prior[1][venue_name_idx['KDD']] = 100
	venue_topical_prior[1][venue_name_idx['ICDE']] = 70
	venue_topical_prior[1][venue_name_idx['CIKM']] = 50
	# ml
	venue_topical_prior[2][venue_name_idx['ICML']] = 100
	# db
	venue_topical_prior[3][venue_name_idx['VLDB']] = 95
	venue_topical_prior[3][venue_name_idx['SIGMOD']] = 70
	venue_topical_prior[3][venue_name_idx['ICDE']] = 50
	# ir
	venue_topical_prior[4][venue_name_idx['SIGIR']] = 95
	print "Set priors complete."

	run_hefbib(
		input_corpus=DATA_PATH + 'AMiner-Paper-after1996-23venues-authorid-validcites-reindex-phrases-index.txt', 
		input_phrase_dists=phrase_dist_files, 
		background_prob_lst=[0.3] * 4,
		tot_num_topics=4,
		tot_num_phrases=5100,
		tot_num_authors=38491,
		tot_num_venues=23,
		ef_alpha=np.ones(5),  # always be tot_num_topics + 1
		ef_beta=np.ones(38491), 
		ef_gamma=venue_topical_prior,
		ef_omega=None, 
		ef_iter=1000,
		br_iter=110,
		output_file=DATA_PATH + 'logs/ahaha')

Exemple #2

Fichier : run_hefbib.py Projet : longislandicetea/HINExpertFinding

def run_level2_dm():
	phrase_dist_files = [
		PHRASE_DIST_PATH + '1dm-1fp-seed-ext',
		PHRASE_DIST_PATH + '1dm-2ds-seed-ext',
		PHRASE_DIST_PATH + '1dm-3net-seed-ext'
	]
	
	# set venue prior
	venue_name_idx, venue_idx_name = fio.read_dictionary_file(DATA_PATH + 'id_venue')
	venue_topical_prior = np.ones((4, 23))
	# dm - frequent pattern
	venue_topical_prior[1][venue_name_idx['KDD']] = 100
	venue_topical_prior[1][venue_name_idx['ICDE']] = 70
	venue_topical_prior[1][venue_name_idx['CIKM']] = 50
	# dm - data stream
	venue_topical_prior[2][venue_name_idx['KDD']] = 100
	venue_topical_prior[2][venue_name_idx['ICDE']] = 70
	venue_topical_prior[2][venue_name_idx['CIKM']] = 50
	# dm - social network
	venue_topical_prior[3][venue_name_idx['KDD']] = 100
	venue_topical_prior[3][venue_name_idx['ICDE']] = 70
	venue_topical_prior[3][venue_name_idx['CIKM']] = 50
	print "Set priors complete."

	run_hefbib(
		input_corpus=DATA_PATH + 'AMiner-Paper-after1996-23venues-authorid-validcites-reindex-phrases-index.txt', 
		input_phrase_dists=phrase_dist_files, 
		background_prob_lst=[0.2] * 3,
		tot_num_topics=3,
		tot_num_phrases=5100,
		tot_num_authors=38491,
		tot_num_venues=23,
		ef_alpha=np.ones(4),  # always be tot_num_topics + 1
		ef_beta=np.ones(38491), 
		ef_gamma=venue_topical_prior,
		ef_omega=None, 
		ef_iter=1500,
		br_iter=110,
		output_file=DATA_PATH + 'logs/ahaha')