def run_search():
#G = load_30k_graph_object()
article_pairs = load_article_pairs()
adj_list_30k = load_30k_adj_list()
num_fail = 0
num_successes = 0
results = []
c = 0
for (article1_name, article2_name) in article_pairs[:100]:
print c
#print "Article 1: %s, article 2: %s" % (article1_name, article2_name)
src_id = int(title_to_linenum[article1_name])
dst_id = int(title_to_linenum[article2_name])
success_dec_path_lengths = []
suc = 0
fail = 0
#try:
(success_or_fail, dec_search_path_length) = util.run_decentralized_search(src_id, dst_id, \
adj_list_30k, linenum_to_title, util.get_article_distance)
#shortest_path_length = get_graph_shortest_path(G, src_id, dst_id)
#(ont_dist, lca_height) = get_ontology_distance(article1_name, article2_name)
# failure
if success_or_fail == "FAILURE":
fail += 1
num_fail += 1
else:
suc += 1
num_successes += 1
success_dec_path_lengths.append(dec_search_path_length)
# except KeyError:
# continue
x = (article1_name, article2_name, suc, fail, success_dec_path_lengths)
results.append(x)
c += 1
#print success_or_fail
print "%d successes, %d failures" % (num_successes, num_fail)
# save object to file
load_data.save_object(results, "bin/results/feat3.pk1")
def run_random_search():
article_pairs = load_article_pairs()
adj_list_30k = load_30k_adj_list()
# tuple of (a1_name, a2_name, # success, # fail, success_dec_path_lengths)
results = []
for (article1_name, article2_name) in article_pairs[:100]:
src_id = int(title_to_linenum[article1_name])
dst_id = int(title_to_linenum[article2_name])
success_dec_path_lengths = []
num_successes = 0
num_fail = 0
try:
for i in range(1000):
(success_or_fail, dec_search_path_length) = util.run_decentralized_search(src_id, dst_id, \
adj_list_30k, linenum_to_title, util.get_article_distance)
# failure
if success_or_fail == "FAILURE":
num_fail += 1
else:
num_successes += 1
success_dec_path_lengths.append(dec_search_path_length)
except KeyError:
continue
x = (article1_name, article2_name, num_successes, num_fail, success_dec_path_lengths)
results.append(x)
print "%d successes, %d failures" % (num_successes, num_fail)
print "Number of pairs actually completed: %d" % len(results)
# save object to file
load_data.save_object(results, "bin/results/random_dec_search_1ktrials.pk1")
def run_experiment():
N = 5
num_success = 0
# pick some number of random pairs of articles.
# for each pair, compute the dist given by decentralized search: that's the predicted dist
# for that same pair, also compute the distance using the ontology tree
while num_success < N:
article1_name = random.choice(articles)
article2_name = random.choice(articles)
while article1_name == article2_name:
article2_name = random.choice(articles)
print "Article 1: %s, article 2: %s" % (article1_name, article2_name)
src_id = int(title_to_linenum[article1_name])
dst_id = int(title_to_linenum[article2_name])
# predicted distance
(success_or_fail, predicted_distance) = util.run_decentralized_search(src_id, dst_id, \
adj_list, linenum_to_title, util.get_article_distance)
# failure or error
if success_or_fail == None or success_or_fail == "FAILURE":
if success_or_fail != None:
print "%s. Article 1: %s, Article 2: %s" % \
(success_or_fail, article1_name, article2_name)
else:
print "KeyError..."
# success
else:
num_success += 1
# ontology distance
ontology_distance = get_ontology_distance(article1_name, article2_name)
print "%s. Article 1: %s, Article 2: %s, Predicted distance = %d, Ontology distance = %d" % \
(success_or_fail, article1_name, article2_name, predicted_distance, ontology_distance)
