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)
import matplotlib.colors as mcolor
import matplotlib as mpl
from scipy.stats import zscore
import random as rd
import persistent as p
import ir_evaluation as ir
from collections import namedtuple
LOOP = namedtuple('Loop', 'path dst size')
FEATURES = ['likes', 'users', 'checkins', 'publicness', 'density',
'category', 'art', 'education', 'food', 'night', 'recreation',
'shop', 'professional', 'residence', 'transport', 'focus',
'photogenicity', 'weekend']
for i in range(6, 15):
FEATURES[i] += ' surrounding'
FEATURES.extend(['activity at ' + t for t in vf.named_ticks('day', 1, 4)])
FEATURES.append('opening')
FEATURES.extend(['surrounding activity at ' + t
for t in vf.named_ticks('day', 1, 4)])
RESTRICTED = np.array(range(len(FEATURES))) # pylint: disable=E1101
LCATS = {}
def load_matrix(city, hide_category=False):
"""Open `city` matrix or compute it."""
filename = city
if not filename.endswith('.mat'):
filename = city + '_fv.mat'
mat = vf.sio.loadmat(filename)
log_nb_users = []
# pylint: disable=E1101
clusterer = cl.DBSCAN(eps=5, min_samples=8, metric='cityblock')
clusterer = cl.AffinityPropagation(damping=.55, affinity='euclidean')
clusterer = cl.SpectralClustering(3, affinity='cosine', n_init=3)
hel = cn.load_matrix(city)
features = hel['v']
scale = pp.MinMaxScaler(copy=False)
scale.fit_transform(features[:, 0:3])
scores = []
for k in range(3, 16):
clusterer = cl.KMeans(k, n_init=10, tol=1e-5, max_iter=500)
labels = clusterer.fit_predict(features)
scores.append(mt.silhouette_score(features, labels))
print(Counter(labels))
np.argsort(scores)[::-1]+3
ppl.plot(range(3, 16), scores[0:], '+')
clusterer = cl.MeanShift(min_bin_freq=3, cluster_all=False)
clusterer = cl.KMeans(6, n_init=20, tol=1e-5, max_iter=500)
visits = xp.get_visits(CLIENT, xp.Entity.venue, city)
visitors = xp.get_visitors(CLIENT, city)
density = vf.estimate_density(city)
c0, _ = vf.venues_info([_ for _ in hel['i'][labels == 0].tolist()
if _ in visits],
visits, visitors, density, depth=2, tags_freq=False)
c5, v = vf.venues_info([v for v in hel['i'][labels == 5].tolist()
if v in visits],
visits, visitors, density, depth=2, tags_freq=False)
c0.describe()
c5.describe()
scale = pp.MinMaxScaler(copy=False)
scale.fit_transform(features[:, 0:3])
scores = []
for k in range(3, 16):
clusterer = cl.KMeans(k, n_init=10, tol=1e-5, max_iter=500)
labels = clusterer.fit_predict(features)
scores.append(mt.silhouette_score(features, labels))
print(Counter(labels))
np.argsort(scores)[::-1] + 3
ppl.plot(range(3, 16), scores[0:], '+')
clusterer = cl.MeanShift(min_bin_freq=3, cluster_all=False)
clusterer = cl.KMeans(6, n_init=20, tol=1e-5, max_iter=500)
visits = xp.get_visits(CLIENT, xp.Entity.venue, city)
visitors = xp.get_visitors(CLIENT, city)
density = vf.estimate_density(city)
c0, _ = vf.venues_info(
[_ for _ in hel['i'][labels == 0].tolist() if _ in visits],
visits,
visitors,
density,
depth=2,
tags_freq=False)
c5, v = vf.venues_info(
[v for v in hel['i'][labels == 5].tolist() if v in visits],
visits,
visitors,
density,
depth=2,
tags_freq=False)
c0.describe()
