def make_full_person_graph(root_user):
LOGGER.debug(
"user %s interests are %s",
root_user.id,
", ".join([i.text for i in root_user.interests if len(i.sim_list) > 1]),
)
interests = set([i for i in root_user.interests])
clusters = cluster_user_interests(interests)
print "person clusters are:"
for rep, c in clusters.items():
print "\t%s:%s" % (rep.text, [i.text for i in c])
weights = dict([(r, 1.0) for r in clusters])
(users, relations) = find_user_results(clusters.keys(), weights, root_user, clusters)
for u in users:
print_user_relations(u, relations[u], "chose user with interests", "\t")
def make_full_person_graph(root_user):
LOGGER.debug(
'user %s interests are %s', root_user.id,
', '.join([i.text for i in root_user.interests
if len(i.sim_list) > 1]))
interests = set([i for i in root_user.interests])
clusters = cluster_user_interests(interests)
print 'person clusters are:'
for rep, c in clusters.items():
print '\t%s:%s' % (rep.text, [i.text for i in c])
weights = dict([(r, 1.0) for r in clusters])
(users, relations) = find_user_results(clusters.keys(), weights, root_user,
clusters)
for u in users:
print_user_relations(u, relations[u], 'chose user with interests',
'\t')
def find_user_results(roots, weights, root_user=None, clusters=None):
LOGGER.debug("roots are %s", ", ".join([i.text for i in roots]))
candidate_interests = set()
rev_cluster_map = {}
for root, c in clusters.items():
for interest in c:
candidate_interests.update(interest.get_similar()[:500])
rev_cluster_map[interest] = root
LOGGER.debug("num candidates is %s", len(candidate_interests))
# generate possible relations
closest_root = {}
for i in candidate_interests:
sims = [(i.get_similarity2(j), j) for j in roots]
max_sim = max([s for (s, j) in sims])
if max_sim >= 0.01:
assert max_sim > 0
best_roots = [j for (s, j) in sims if s == max_sim]
closest_root[i] = random.choice(best_roots)
# similarities for candidate interests to any one of the element in the cluster
interest_rels = {}
for (i, root) in closest_root.items():
interest_rels[i] = max([i.get_similarity2(j) for j in clusters[root]])
# build up relations
user_relations = {}
for (related, root) in closest_root.items():
for user in utils.get_users_with_interest(related):
if not user in user_relations:
user_relations[user] = collections.defaultdict(list)
user_relations[user][root].append(related)
# sort interests within relations by similarity
for (user, relations) in user_relations.items():
for (root, related) in relations.items():
related.sort(key=lambda i: interest_rels[i])
related.reverse()
# score users
user_relevances = {}
user_profiles = {}
for (user, relations) in user_relations.items():
rel = 0.0
profile = []
for root in roots:
if root in relations:
sims = [interest_rels[i] for i in relations[root]]
score = sum([s * (0.5 ** penalty) for (penalty, s) in enumerate(sims)])
profile.append(len(relations))
rel += score
else:
profile.append(0)
norm = sum([x * x for x in profile]) ** 0.5
profile = [x / norm for x in profile]
user_relevances[user] = rel
user_profiles[user] = profile
# choose users
candidates = set(user_relevances.keys())
if root_user and root_user in candidates:
candidates.remove(root_user)
chosen = set()
while candidates and len(chosen) < 20:
# print 'iteration %d, chosen are:' % len(chosen)
# for u in chosen:
# print_user_relations(u, user_relations[u], '\tinterests', '\t\t')
best_user = None
best_score = None
# print 'candidates are:'
for u1 in candidates:
sims = []
for u2 in chosen:
dot = sum([x * y for (x, y) in zip(user_profiles[u1], user_profiles[u2])])
sims.append(dot)
sims.sort()
redundancy = sum(sims[-2:]) # three largest similarities
score = user_relevances[u1] - redundancy
# caption = '\tcandidate score=%.6f, sim=%.6f redund=%.6f' % (score, user_relevances[u1], redundancy)
# print_user_relations(u1, user_relations[u1], caption, '\t\t')
if score > best_score:
best_score = score
best_user = u1
# caption = 'best has score=%.6f' % best_score
# print_user_relations(best_user, user_relations[best_user], caption, '\t')
candidates.remove(best_user)
chosen.add(best_user)
return chosen, dict([(u, user_relations[u]) for u in chosen])
def find_user_results(roots, weights, root_user=None, clusters=None):
LOGGER.debug('roots are %s', ', '.join([i.text for i in roots]))
candidate_interests = set()
rev_cluster_map = {}
for root, c in clusters.items():
for interest in c:
candidate_interests.update(interest.get_similar()[:500])
rev_cluster_map[interest] = root
LOGGER.debug('num candidates is %s', len(candidate_interests))
# generate possible relations
closest_root = {}
for i in candidate_interests:
sims = [(i.get_similarity2(j), j) for j in roots]
max_sim = max([s for (s, j) in sims])
if max_sim >= 0.01:
assert (max_sim > 0)
best_roots = [j for (s, j) in sims if s == max_sim]
closest_root[i] = random.choice(best_roots)
# similarities for candidate interests to any one of the element in the cluster
interest_rels = {}
for (i, root) in closest_root.items():
interest_rels[i] = max([i.get_similarity2(j) for j in clusters[root]])
# build up relations
user_relations = {}
for (related, root) in closest_root.items():
for user in utils.get_users_with_interest(related):
if not user in user_relations:
user_relations[user] = collections.defaultdict(list)
user_relations[user][root].append(related)
# sort interests within relations by similarity
for (user, relations) in user_relations.items():
for (root, related) in relations.items():
related.sort(key=lambda i: interest_rels[i])
related.reverse()
# score users
user_relevances = {}
user_profiles = {}
for (user, relations) in user_relations.items():
rel = 0.0
profile = []
for root in roots:
if root in relations:
sims = [interest_rels[i] for i in relations[root]]
score = sum(
[s * (0.5**penalty) for (penalty, s) in enumerate(sims)])
profile.append(len(relations))
rel += score
else:
profile.append(0)
norm = sum([x * x for x in profile])**0.5
profile = [x / norm for x in profile]
user_relevances[user] = rel
user_profiles[user] = profile
# choose users
candidates = set(user_relevances.keys())
if root_user and root_user in candidates:
candidates.remove(root_user)
chosen = set()
while candidates and len(chosen) < 20:
#print 'iteration %d, chosen are:' % len(chosen)
#for u in chosen:
#print_user_relations(u, user_relations[u], '\tinterests', '\t\t')
best_user = None
best_score = None
#print 'candidates are:'
for u1 in candidates:
sims = []
for u2 in chosen:
dot = sum([
x * y
for (x, y) in zip(user_profiles[u1], user_profiles[u2])
])
sims.append(dot)
sims.sort()
redundancy = sum(sims[-2:]) # three largest similarities
score = user_relevances[u1] - redundancy
#caption = '\tcandidate score=%.6f, sim=%.6f redund=%.6f' % (score, user_relevances[u1], redundancy)
#print_user_relations(u1, user_relations[u1], caption, '\t\t')
if score > best_score:
best_score = score
best_user = u1
#caption = 'best has score=%.6f' % best_score
#print_user_relations(best_user, user_relations[best_user], caption, '\t')
candidates.remove(best_user)
chosen.add(best_user)
return chosen, dict([(u, user_relations[u]) for u in chosen])