async def location_handler(message: types.Message):
lat = message.location.latitude
lon = message.location.longitude
user = await db.users.find_one({'uid': message.from_user.id})
if user is None:
return await start_handler(message)
if user['stage'] != Stage.geo:
return # ignore
if (get_spherical_distance(lat, lon, config.LAT, config.LON) > config.RADIUS) or \
(message.forward_from is not None):
return await message.reply(t('GEO_FAILED', locale=user['lang']), reply_markup=keyboards.get_geo_kbd())
else:
await db.users.find_one_and_update({'uid': message.from_user.id}, {'$set': {'stage': Stage.menu}})
await message.reply(t('GEO_SUCCESS', locale=user['lang']),
reply_markup=types.ReplyKeyboardRemove())
await aq.aapi.add_user_to_queue(user['get_queue'], user['uid'])
user_data = await aq.aapi.get_user_info(user['uid'])
queues = user_data['queues']
queue_id = user['get_queue']
queue = list(filter(lambda x: queue_id == x['id'], queues))[0]
await message.answer(t('USER_QUEUE_INFO', locale=user['lang'], queue_name=queue['name'],
pos=queue['position']['relativePosition']),
reply_markup=keyboards.get_update_my_queue_kbd(queue_id,
user['lang']),
parse_mode=types.ParseMode.HTML)
def test_proximity_sort(self):
genericCollectionSlice = HTTPGenericCollectionSlice()
center = (40.73, -73.99) # ~NYC
genericCollectionSlice.sort = "proximity"
genericCollectionSlice.offset = 0
genericCollectionSlice.limit = 10
genericCollectionSlice.coordinates = "%s,%s" % (center[0], center[1])
ret0 = self._getStamps(genericCollectionSlice)
self.assertLength(ret0, 9)
earthRadius = 3959.0 # miles
prev_dist = -earthRadius
# ensure results are approximately sorted by distance
for s in ret0:
coords = (s.entity.coordinates.lat, s.entity.coordinates.lng)
dist = utils.get_spherical_distance(center, coords) * earthRadius
# allow a one-mile fudge factor because we're using spherical
# distance here, and the distance calculation when sorting
# results is less precise but faster to calculate (L2 norm)
self.assertTrue(dist >= prev_dist - 1)
prev_dist = dist
def getSuggestedUserIds(self, userId, request):
"""
Returns personalized user suggestions based on several weighting
signals, namely: friend overlap, stamp overlap, stamp category
overlap, geographical proximity of stamp clusters, FB / Twitter
friendship, as well as several smaller quality signals.
"""
# TODO: support ignoring a friend suggestion
# TODO: ignore previously followed friends that you've since unfollowed
# TODO: better support for new users w/out stamps or friends
friends_of_friends = {}
visited_users = set()
pruned = set()
todo = []
max_distance = 2
count = 0
friends = None
coords = None
if request.coordinates is not None and request.coordinates.lat is not None and request.coordinates.lng is not None:
coords = (request.coordinates.lat, request.coordinates.lng)
def visit_user(user_id, distance):
if user_id in visited_users:
return
if distance == max_distance:
try:
count = friends_of_friends[user_id]
friends_of_friends[user_id] = count + 1
except Exception:
friends_of_friends[user_id] = 1
else:
visited_users.add(user_id)
heapq.heappush(todo, (distance, user_id))
# seed the algorithm with the initial user at distance 0
visit_user(userId, 0)
while True:
try:
distance, user_id = heapq.heappop(todo)
except IndexError:
break # heap is empty
if distance < max_distance:
friend_ids = self.getFriends(user_id)
distance = distance + 1
if friends is None:
friends = set(friend_ids)
friends.add(userId)
for friend_id in friend_ids:
visit_user(friend_id, distance)
potential_friends = defaultdict(dict)
total = sum(friends_of_friends.itervalues())
weight = 1.0 / total if total > 0 else 0.0
for user_id, friend_overlap in friends_of_friends.iteritems():
if friend_overlap > 1:
value = (friend_overlap ** 3) * weight
potential_friends[user_id]['num_friend_overlap'] = friend_overlap
potential_friends[user_id]['friend_overlap'] = value
user_entity_ids, user_categories, user_clusters, user = self._get_stamp_info(userId)
inv_len_user_entity_ids = len(user_entity_ids)
inv_len_user_entity_ids = 1.0 / inv_len_user_entity_ids if inv_len_user_entity_ids > 0 else 0.0
#for cluster in user_clusters:
# print "(%s) %d %s" % (cluster['avg'], len(cluster['data']), cluster['data'])
# seed potential friends with users who have stamped at least one of the same entities
for entity_id in user_entity_ids:
stamps = self.stamp_collection.getStampsForEntity(entity_id, limit=200)
for stamp in stamps:
user_id = stamp.user.user_id
if user_id not in friends:
try:
potential_friends[user_id]['num_stamp_overlap'] = potential_friends[user_id]['num_stamp_overlap'] + 1
except Exception:
potential_friends[user_id]['num_stamp_overlap'] = 1
# seed potential friends with facebook friends
if request.facebook_token is not None:
facebook_friends = self.api._getFacebookFriends(request.facebook_token)
for friend in facebook_friends:
user_id = friend.user_id
if user_id not in friends:
potential_friends[user_id]['facebook_friend'] = True
# seed potential friends with twitter friends
if request.twitter_key is not None and request.twitter_secret is not None:
twitter_friends = self.api._getTwitterFriends(request.facebook_token)
for friend in twitter_friends:
user_id = friend.user_id
if user_id not in friends:
potential_friends[user_id]['twitter_friend'] = True
# process each potential friend
for user_id, values in potential_friends.iteritems():
try:
if user_id in self._suggested:
raise
if 'num_friend_overlap' not in values and 'facebook_friend' not in values and 'twitter_friend' not in values and values['num_stamp_overlap'] <= 1:
raise
except Exception:
pruned.add(user_id)
continue
count = count + 1
entity_ids, categories, clusters, friend = self._get_stamp_info(user_id)
overlap = 0
try:
overlap = values['num_stamp_overlap']
values['stamp_overlap'] = overlap * overlap * inv_len_user_entity_ids
except Exception:
pass
summation = 0.0
for category in [ 'place', 'music', 'film', 'book', 'app', 'other' ]:
diff = user_categories[category] - categories[category]
summation += diff * diff
category_dist = 1.0 - math.sqrt(summation)
values['category_overlap'] = category_dist
earthRadius = 3959.0 # miles
sum0 = len(user_entity_ids)
sum1 = len(entity_ids)
sum0 = 1.0 / sum0 if sum0 > 0 else 0.0
sum1 = 1.0 / sum1 if sum1 > 0 else 0.0
score = -1
max_val = [ (0, None), (0, None) ]
# compare seed user's stamp clusters with this user's stamp clusters
for cluster0 in user_clusters:
ll0 = cluster0['avg']
len0 = len(cluster0['data']) * sum0
min_dist = 10000000
min_len = -1
for cluster1 in clusters:
ll1 = cluster1['avg']
len1 = len(cluster1['data']) * sum1
dist = earthRadius * utils.get_spherical_distance(ll0, ll1)
if dist >= 0 and dist < min_dist:
min_dist = dist
min_len = len1
if min_len > 0:
inv_dist = 1.0 / math.log(min_dist) if min_dist > 1.0 else 0.0
value = len0 * min_len * inv_dist
score = score + value
if max_val[0][1] is None or value > max_val[0][0]:
if max_val[1][1] is None or value > max_val[1][0]:
max_val[0] = max_val[1]
max_val[1] = (value, ll0)
else:
max_val[0] = (value, ll0)
if score >= 0 and len(user_clusters) > 0:
score = score / len(user_clusters)
if score < 0:
score = None
values['proximity'] = score
values['clusters'] = max_val
if coords is not None:
min_dist = None
for cluster in clusters:
ll0 = cluster['avg']
#len0 = len(cluster['data']) * sum1
dist = earthRadius * utils.get_spherical_distance(coords, ll0)
if min_dist is None or dist < min_dist:
min_dist = dist
values['current_proximity'] = dist
num_stamps = friend.num_stamps if 'num_stamps' in friend else 0
num_stamps -= overlap
values['has_stamps'] = (num_stamps >= 1)
values['num_stamps'] = math.log(num_stamps) if num_stamps >= 1 else 0.0
logs.info("potential friends: %d" % len(potential_friends))
logs.info("friends of friends: %d" % len(friends_of_friends))
logs.info("processed: %d; pruned: %d" % (count, len(pruned)))
limit = request.limit if request.limit is not None else 10
offset = request.offset if request.offset is not None else 0
if len(pruned) > 0 and len(potential_friends) - len(pruned) >= offset + limit:
logs.debug("pruning %d potential friends (out of %d)" % (len(pruned), len(potential_friends)))
potential_friends = dict(filter(lambda f: f[0] not in pruned, potential_friends.iteritems()))
logs.debug("removed %d potential friends (now %d)" % (len(pruned), len(potential_friends)))
"""
# debugging utility to view top scores across certain categories
def print_top(key, reverse=True, default=-1):
print "%s %s %s" % ("-" * 40, key, "-" * 40)
users2 = sorted(potential_friends.iteritems(), key=lambda kv: kv[1][key] if key in kv[1] else default, reverse=True)[:10]
for user in users2:
import pprint as p
p.pprint(user)
print_top('friend_overlap')
print_top('stamp_overlap')
print_top('category_overlap')
print_top('proximity')
"""
# TODO: optimize this sorted loop to only retain the top n results?
users = sorted(potential_friends.iteritems(), key=self._get_potential_friend_score, reverse=True)
users = users[offset : offset + limit]
func = lambda kv: (kv[0], self._get_potential_friend_score(kv, explain=True, coords=coords)[1])
return map(func, users)
def _get_stamp_info(self, user_id):
"""
Processes a single user, returning aggregate statistics about their
stamp behavior, including all entity_id's that the user's stamped,
a histogram of the categories those stamps fall into, a description
of their geographical stamp clusters, and the user object itself.
"""
stampIds = self.collection_collection.getUserStampIds(user_id)
stamps = self.stamp_collection.getStamps(stampIds, limit=1000, sort='modified')
user = self.user_collection.getUser(user_id)
categories = defaultdict(int)
num_stamps = len(stamps)
entity_ids = frozenset(s.entity_id for s in stamps)
for stamp in stamps:
categories[stamp.entity.category] = categories[stamp.entity.category] + 1.0 / num_stamps
earthRadius = 3959.0 # miles
clusters = [ ]
trivial = True
# find stamp clusters
for stamp in stamps:
if stamp.lat is not None and stamp.lng is not None:
found_cluster = False
ll = [ stamp.lat, stamp.lng ]
#print "%s) %s" % (stamp.title, ll)
for cluster in clusters:
dist = earthRadius * utils.get_spherical_distance(ll, cluster['avg'])
#print "%s) %s vs %s => %s (%s)" % (stamp.title, ll, cluster['avg'], dist, cluster['data'])
if dist < 10:
cluster['data'].append(stamp.title)
len_cluster = len(cluster['data'])
found_cluster = True
trivial = False
cluster['sum'][0] = cluster['sum'][0] + ll[0]
cluster['sum'][1] = cluster['sum'][1] + ll[1]
cluster['avg'][0] = cluster['sum'][0] / len_cluster
cluster['avg'][1] = cluster['sum'][1] / len_cluster
#print "%s) %d %s" % (stamp.title, len_cluster, cluster)
break
if not found_cluster:
clusters.append({
'avg' : [ ll[0], ll[1] ],
'sum' : [ ll[0], ll[1] ],
'data' : [ stamp.title ],
})
clusters2 = []
if trivial:
clusters2 = clusters
else:
# attempt to remove trivial clusters as outliers
for cluster in clusters:
if len(cluster['data']) > 1:
clusters2.append(cluster)
return entity_ids, categories, clusters2, user
def get_clusters(self, entities, limit=None):
earthRadius = 3959.0 # miles
threshold = 10.0
clusters = [ ]
trivial = True
# find entity clusters
for entity in entities:
found_cluster = False
coords = entity.coordinates
if coords is None:
continue
# TODO: really should be retaining this for stamps overall instead of just subset here...
ll = [ coords.lat, coords.lng ]
for cluster in clusters:
dist = earthRadius * utils.get_spherical_distance(ll, cluster['avg'])
if dist < threshold:
cluster['data'].append((ll[0], ll[1]))
len_cluster = len(cluster['data'])
found_cluster = True
trivial = False
cluster['sum'][0] = cluster['sum'][0] + ll[0]
cluster['sum'][1] = cluster['sum'][1] + ll[1]
4
cluster['avg'][0] = cluster['sum'][0] / len_cluster
cluster['avg'][1] = cluster['sum'][1] / len_cluster
break
if not found_cluster:
clusters.append({
'avg' : [ ll[0], ll[1] ],
'sum' : [ ll[0], ll[1] ],
'data' : [ (ll[0], ll[1]) ],
})
clusters_out = []
if trivial:
clusters_out = clusters
else:
# attempt to remove trivial clusters as outliers
for cluster in clusters:
if len(cluster['data']) > 1:
clusters_out.append(cluster)
if len(clusters_out) <= 0:
clusters_out.append(clusters[0])
if len(clusters) > 0:
clusters = sorted(clusters_out, key=lambda c: len(c['data']), reverse=True)
#for cluster in clusters:
# utils.log(pprint.pformat(cluster))
return clusters[0]
return None
