def plot_city(city, weekly=False, clusters=5):
"""Plot the 5 time clusters of `city` and save them on disk."""
shift = 2 # start from 1am instead of midnight
chunk = 4
venue_visits = xp.get_visits(CLIENT, xp.Entity.venue, city)
# Compute aggregated frequency for venues with at least 5 visits
enough = {
k: xp.to_frequency(xp.aggregate_visits(v, shift, chunk)[int(weekly)])
for k, v in venue_visits.iteritems() if len(v) > 5
}
sval = np.array(enough.values())
num_cluster = clusters
min_disto = 1e9
for _ in range(7):
tak, tkl = DO_CLUSTER(sval, num_cluster)
current_disto = vf.get_distorsion(tak, tkl, sval)
if current_disto < min_disto:
min_disto, ak, kl = current_disto, tak, tkl
std_ord = np.argsort((np.argsort(ak)), 0)[:, -1]
# vf.draw_classes(ak[std_ord, :], shift, chunk)
# vf.plt.title('{}, {} venues'.format(city, len(enough)))
# vf.plt.ylim([0, 0.28 if weekly else 0.9])
city = 'times/' + city
city += '_weekly' if weekly else '_daily'
sio.savemat(city + '_time', {'t': ak[std_ord, :]}, do_compression=True)
def plot_city(city, weekly=False, clusters=5):
"""Plot the 5 time clusters of `city` and save them on disk."""
shift = 2 # start from 1am instead of midnight
chunk = 4
venue_visits = xp.get_visits(CLIENT, xp.Entity.venue, city)
# Compute aggregated frequency for venues with at least 5 visits
enough = {
k: xp.to_frequency(xp.aggregate_visits(v, shift, chunk)[int(weekly)])
for k, v in venue_visits.iteritems()
if len(v) > 5
}
sval = np.array(enough.values())
num_cluster = clusters
min_disto = 1e9
for _ in range(7):
tak, tkl = DO_CLUSTER(sval, num_cluster)
current_disto = vf.get_distorsion(tak, tkl, sval)
if current_disto < min_disto:
min_disto, ak, kl = current_disto, tak, tkl
std_ord = np.argsort((np.argsort(ak)), 0)[:, -1]
# vf.draw_classes(ak[std_ord, :], shift, chunk)
# vf.plt.title('{}, {} venues'.format(city, len(enough)))
# vf.plt.ylim([0, 0.28 if weekly else 0.9])
city = "times/" + city
city += "_weekly" if weekly else "_daily"
sio.savemat(city + "_time", {"t": ak[std_ord, :]}, do_compression=True)
def photos_around(id_, centroid, offset, daily, radius=200):
"""Gather photos timestamp in a `radius` around `id_` and return its time
pattern (`daily` or not), and its distance to every `centroid`."""
center = get_loc(id_)
photos = xp.get_visits(CLIENT, xp.Entity.photo, ball=(center, radius))
kind = xp.to_frequency(xp.aggregate_visits(photos.values(), offset)[daily])
nb_class = centroid.shape[0]
# pylint: disable=E1101
classes = np.linalg.norm(np.tile(kind, (nb_class, 1)) - centroid, axis=1)
return len(photos), kind, classes, np.argmin(classes)
def describe_city(city):
"""Compute feature vector for selected venue in `city`."""
CATS2 = p.load_var('cat_depth_2.my')
# a few venues don't have level 2 categories (TODO add it manually?)
CATS2.update({cat: int(idx*1e5) for idx, cat in enumerate(CATS)})
info = global_info(city)
lvenues, lcheckins, lphotos = info[:3]
visits, visitors, density = info[3:6]
nb_visitors = np.unique(np.array([v for place in visitors.itervalues()
for v in place])).size
svenues, scheckins, sphotos = info[6:]
categories = categories_repartition(city, svenues, lvenues, RADIUS)
venues = DB.venue.find({'city': city, 'closed': {'$ne': True},
'cat': {'$ne': None}, 'usersCount': {'$gt': 1}},
{'cat': 1})
chosen = [v['_id'] for v in venues
if len(visits.get(v['_id'], [])) > 4 and
len(np.unique(visitors.get(v['_id'], []))) > 1 and
not is_event(v['cat'])]
print("Chosen {} venues in {}.".format(len(chosen), city))
info, _ = venues_info(chosen, visits, visitors, density, depth=2,
tags_freq=False)
print("{} of them will be in the matrix.".format(len(info)))
numeric = np.zeros((len(info), 31), dtype=np.float32)
numeric[:, :5] = np.array([info['likes'], info['users'], info['checkins'],
info['H'], info['Den']]).T
print('venues with no level 2 category:')
print([info.index[i] for i, c in enumerate(info['cat'])
if CATS2[c] % int(1e5) == 0])
numeric[:, 5] = [CATS2[c] for c in info['cat']]
numeric[:, 24] = np.array(info['Ht'])
for idx, vid in enumerate(info.index):
surrounding = full_surrounding(vid, lvenues, lphotos, lcheckins,
svenues, scheckins, sphotos, city)
cat, focus, ratio, around_visits = surrounding
numeric[idx, 6:15] = cat
numeric[idx, 15] = focus
numeric[idx, 16] = ratio
own_visits = visits[vid]
numeric[idx, 17] = is_week_end_place(own_visits)
daily_visits = xp.aggregate_visits(own_visits, 1, 4)[0]
numeric[idx, 18:24] = xp.to_frequency(daily_visits)
numeric[idx, 25:31] = xp.to_frequency(around_visits)
weird = np.argwhere(np.logical_or(np.isnan(numeric), np.isinf(numeric)))
numeric[weird] = 0.0
sio.savemat(city+'_fv', {'v': numeric, 'c': categories,
'i': np.array(list(info.index)),
'stat': [nb_visitors]}, do_compression=True)
def full_surrounding(vid, vmapping, pmapping, cmapping, svenues, scheckins,
sphotos, city, radius=350):
"""Return a list of photos, checkins and venues categories in a `radius`
around `vid`, within `city`. The mappings are dict({id: 2dpos})"""
cat_distrib = categories_repartition(city, svenues, vmapping, radius, vid)
center = vmapping[vid]
pids, infos, _ = sphotos.around(center, radius)
pvenue = infos[0]
cids, infos, _ = scheckins.around(center, radius)
ctime = infos[0]
focus = photo_focus(vid, center, pids, pvenue, radius, pmapping)
photogeny, c_smoothed = photo_ratio(center, pids, cids, radius, pmapping,
cmapping)
if len(ctime) < 5:
print(vid + ' is anomalous because there is less than 5 check-in in a 350m radius')
if len(ctime) == 0:
surround_visits = np.ones(6)
else:
surround_visits = xp.aggregate_visits(ctime, 1, 4, c_smoothed)[0]
return cat_distrib, focus, photogeny, surround_visits