def main(tseries_fpath, assign_fpath, centroids_fpath, plot_foldpath):
initialize_matplotlib()
X = np.genfromtxt(tseries_fpath)[:, 1:].copy()
y = np.genfromtxt(assign_fpath)
centroids = np.genfromtxt(centroids_fpath)
num_classes = len(set(y))
for k in range(num_classes):
centroid_plot_foldpath = os.path.join(plot_foldpath, str(k))
os.mkdir(centroid_plot_foldpath)
centroid = centroids[k]
plot_series(centroid, centroid_plot_foldpath, 'centroid', True)
members = X[y == k]
n_samples = members.shape[0]
sample_rows = np.arange(n_samples)
np.random.shuffle(sample_rows)
members_to_plot = members[sample_rows[:10]]
for i in range(members_to_plot.shape[0]):
print(k, i)
plot_series(members_to_plot[i], centroid_plot_foldpath,
'ex-%d' % i)
def main(features_fpath,
classes_fpath,
out_fpath,
trans_fpath,
col_to_use=2,
is_text_features=False):
initialize_matplotlib()
classes = np.loadtxt(classes_fpath)
if is_text_features:
to_plot, sum_classes, labels = \
load_text_file(features_fpath, col_to_use, classes)
ref = False
else:
to_plot, sum_classes, labels = \
load_svm_file(features_fpath, classes)
ref = True
trans = {}
with open(trans_fpath) as f:
for l in f:
spl = l.split()
trans[int(spl[0])] = int(spl[1])
data = generate_data_plot(to_plot, sum_classes, labels, classes)
stacked_bars(labels, data, out_fpath, trans, ref)
def main(tseries_fpath, assign_fpath, centroids_fpath, plot_foldpath):
initialize_matplotlib()
X = np.genfromtxt(tseries_fpath)[:,1:].copy()
y = np.genfromtxt(assign_fpath)
centroids = np.genfromtxt(centroids_fpath)
num_classes = len(set(y))
for k in xrange(num_classes):
centroid_plot_foldpath = os.path.join(plot_foldpath, str(k))
os.mkdir(centroid_plot_foldpath)
centroid = centroids[k]
plot_series(centroid, centroid_plot_foldpath, 'centroid', True)
members = X[y == k]
n_samples = members.shape[0]
sample_rows = np.arange(n_samples)
np.random.shuffle(sample_rows)
members_to_plot = members[sample_rows[:10]]
for i in xrange(members_to_plot.shape[0]):
print(k, i)
plot_series(members_to_plot[i], centroid_plot_foldpath, 'ex-%d' % i)
def main(tseries_fpath, k, plot_foldpath):
import mkl
mkl.set_num_threads(16)
initialize_matplotlib()
X = np.genfromtxt(tseries_fpath)[:, 1:]
aux = X.sum(axis=1)
fix = np.where(aux == 0)[0]
X[fix] += .001 #fixing zero only rows
X = X.copy()
cent, assign, shift, dists_cent = ksc.inc_ksc(X, k)
for i in range(cent.shape[0]):
t_series = cent[i]
plt.plot(t_series, '-k')
plt.gca().get_xaxis().set_visible(False)
plt.gca().get_yaxis().set_visible(False)
#plt.ylabel('Views')
#plt.xlabel('Time')
plt.savefig(os.path.join(plot_foldpath, '%d.pdf' % i))
plt.close()
half = t_series.shape[0] // 2
to_shift = half - np.argmax(t_series)
to_plot_peak_center = dist.shift(t_series, to_shift, rolling=True)
plt.plot(to_plot_peak_center, '-k')
plt.gca().get_xaxis().set_visible(False)
plt.gca().get_yaxis().set_visible(False)
#plt.ylabel('Views')
#plt.xlabel('Time')
plt.savefig(os.path.join(plot_foldpath, '%d-peak-center.pdf' % i))
plt.close()
to_shift = 0 - np.argmin(t_series)
to_plot_min_first = dist.shift(t_series, to_shift, rolling=True)
plt.plot(to_plot_min_first, '-k')
plt.gca().get_xaxis().set_visible(False)
plt.gca().get_yaxis().set_visible(False)
#plt.ylabel('Views')
#plt.xlabel('Time')
plt.savefig(os.path.join(plot_foldpath, '%d-min-first.pdf' % i))
plt.close()
np.savetxt(os.path.join(plot_foldpath, 'cents.dat'), cent, fmt='%.5f')
np.savetxt(os.path.join(plot_foldpath, 'assign.dat'), assign, fmt='%d')
np.savetxt(os.path.join(plot_foldpath, 'shift.dat'), shift, fmt='%d')
np.savetxt(os.path.join(plot_foldpath, 'dists_cent.dat'),
dists_cent,
fmt='%.5f')
def main(features_fpath, classes_fpath, out_fpath, trans_fpath, col_to_use=2, is_text_features=False):
initialize_matplotlib()
classes = np.loadtxt(classes_fpath)
if is_text_features:
to_plot, sum_classes, labels = load_text_file(features_fpath, col_to_use, classes)
ref = False
else:
to_plot, sum_classes, labels = load_svm_file(features_fpath, classes)
ref = True
trans = {}
with open(trans_fpath) as f:
for l in f:
spl = l.split()
trans[int(spl[0])] = int(spl[1])
data = generate_data_plot(to_plot, sum_classes, labels, classes)
stacked_bars(labels, data, out_fpath, trans, ref)
def main(features_fpath):
initialize_matplotlib()
X = np.genfromtxt(features_fpath)[:,1:]
for r, k in sorted(refs.items()):
idxs = X[:,k] > 0
time_to_ref = (X[:,UP_DATE][idxs] - X[:,k][idxs])
print(r, np.mean(time_to_ref), np.std(time_to_ref))
print('peak_frac', np.mean(X[:,-3]), np.std(X[:,-3]))
time_to_peak = (X[:,-4] - X[:,UP_DATE]) / 7
print('peak_date', np.mean(time_to_peak), np.std(time_to_peak))
import time
plt.hist(X[:,UP_DATE], bins=20)
ticks, labels = plt.xticks()
plt.xticks(ticks, [time.strftime('%m/%y', time.localtime(x)) for x in ticks])
plt.ylabel('\# Videos')
plt.xlabel('Month/Year')
plt.savefig('hist.pdf')
def main(features_fpath):
initialize_matplotlib()
X = np.genfromtxt(features_fpath)[:, 1:]
for r, k in sorted(refs.items()):
idxs = X[:, k] > 0
time_to_ref = (X[:, UP_DATE][idxs] - X[:, k][idxs])
print(r, np.mean(time_to_ref), np.std(time_to_ref))
print('peak_frac', np.mean(X[:, -3]), np.std(X[:, -3]))
time_to_peak = (X[:, -4] - X[:, UP_DATE]) / 7
print('peak_date', np.mean(time_to_peak), np.std(time_to_peak))
import time
plt.hist(X[:, UP_DATE], bins=20)
ticks, labels = plt.xticks()
plt.xticks(ticks,
[time.strftime('%m/%y', time.localtime(x)) for x in ticks])
plt.ylabel('\# Videos')
plt.xlabel('Month/Year')
plt.savefig('hist.pdf')
def main(features_fpath, classes_fpath, user_users=False):
initialize_matplotlib()
classes = np.loadtxt(classes_fpath)
num_classes = len(set(classes))
to_compare = load_text_file(features_fpath, classes, user_users)
print(end='\t')
for i in range(num_classes):
print(i, end='\t')
print()
for j in range(num_classes):
print(j, end='\t')
for i in range(num_classes):
first_set = to_compare[i]
second_set = to_compare[j]
asym_j = asym_jaccard(first_set, second_set)
print('%.3f' % asym_j, end='\t')
print()
def main(features_fpath, classes_fpath, user_users=False):
initialize_matplotlib()
classes = np.loadtxt(classes_fpath)
num_classes = len(set(classes))
to_compare = load_text_file(features_fpath, classes, user_users)
print(end='\t')
for i in xrange(num_classes):
print(i, end='\t')
print()
for j in xrange(num_classes):
print(j, end='\t')
for i in xrange(num_classes):
first_set = to_compare[i]
second_set = to_compare[j]
asym_j = asym_jaccard(first_set, second_set)
print('%.3f' % asym_j, end='\t')
print()
def main(tseries_fpath, plot_foldpath):
assert os.path.isdir(plot_foldpath)
initialize_matplotlib()
X = np.genfromtxt(tseries_fpath)[:, 1:].copy()
n_samples = X.shape[0]
sample_rows = np.arange(n_samples)
clust_range = range(2, 16)
n_clustering_vals = len(clust_range)
intra_array = np.zeros(shape=(25, n_clustering_vals))
inter_array = np.zeros(shape=(25, n_clustering_vals))
bcvs_array = np.zeros(shape=(25, n_clustering_vals))
costs_array = np.zeros(shape=(25, n_clustering_vals))
r = 0
for i in xrange(5):
np.random.shuffle(sample_rows)
rand_sample = sample_rows[:200]
X_new = X[rand_sample]
D_new = dist.dist_all(X_new, X_new, rolling=True)[0]
for j in xrange(5):
for k in clust_range:
intra, inter, bcv, cost = run_clustering(X_new, k, D_new)
intra_array[r, k - 2] = intra
inter_array[r, k - 2] = inter
bcvs_array[r, k - 2] = bcv
costs_array[r, k - 2] = cost
r += 1
print(r)
intra_err = np.zeros(n_clustering_vals)
inter_err = np.zeros(n_clustering_vals)
bcvs_err = np.zeros(n_clustering_vals)
costs_err = np.zeros(n_clustering_vals)
for k in clust_range:
j = k - 2
intra_err[j] = hci(intra_array[:, j], 0.95)
inter_err[j] = hci(inter_array[:, j], 0.95)
bcvs_err[j] = hci(bcvs_array[:, j], 0.95)
costs_err[j] = hci(costs_array[:, j], 0.95)
plt.errorbar(clust_range, np.mean(inter_array, axis=0), fmt="gD", label="Inter Cluster", yerr=inter_err)
plt.errorbar(clust_range, np.mean(bcvs_array, axis=0), fmt="bo", label="BetaCV", yerr=bcvs_err)
plt.errorbar(clust_range, np.mean(intra_array, axis=0), fmt="rs", label="Intra Cluster", yerr=intra_err)
plt.ylabel("Average Distance")
plt.xlabel("Number of clusters")
plt.xlim((0.0, 16))
plt.ylim((0.0, 1.0))
plt.legend(frameon=False, loc="lower left")
plt.savefig(os.path.join(plot_foldpath, "bcv.pdf"))
plt.close()
plt.errorbar(clust_range, np.mean(costs_array, axis=0), fmt="bo", label="Cost", yerr=costs_err)
plt.ylabel("Cost (F)")
plt.xlabel("Number of clusters")
plt.xlim((0.0, 16))
plt.ylim((0.0, 1.0))
plt.legend(frameon=False, loc="lower left")
plt.savefig(os.path.join(plot_foldpath, "cost.pdf"))
plt.close()
def main(tseries_fpath, plot_foldpath):
assert os.path.isdir(plot_foldpath)
initialize_matplotlib()
X = np.genfromtxt(tseries_fpath)[:, 1:].copy()
n_samples = X.shape[0]
sample_rows = np.arange(n_samples)
clust_range = range(2, 16)
n_clustering_vals = len(clust_range)
intra_array = np.zeros(shape=(25, n_clustering_vals))
inter_array = np.zeros(shape=(25, n_clustering_vals))
bcvs_array = np.zeros(shape=(25, n_clustering_vals))
costs_array = np.zeros(shape=(25, n_clustering_vals))
r = 0
for i in xrange(5):
np.random.shuffle(sample_rows)
rand_sample = sample_rows[:200]
X_new = X[rand_sample]
D_new = dist.dist_all(X_new, X_new, rolling=True)[0]
for j in xrange(5):
for k in clust_range:
intra, inter, bcv, cost = run_clustering(X_new, k, D_new)
intra_array[r, k - 2] = intra
inter_array[r, k - 2] = inter
bcvs_array[r, k - 2] = bcv
costs_array[r, k - 2] = cost
r += 1
print(r)
intra_err = np.zeros(n_clustering_vals)
inter_err = np.zeros(n_clustering_vals)
bcvs_err = np.zeros(n_clustering_vals)
costs_err = np.zeros(n_clustering_vals)
for k in clust_range:
j = k - 2
intra_err[j] = hci(intra_array[:, j], .95)
inter_err[j] = hci(inter_array[:, j], .95)
bcvs_err[j] = hci(bcvs_array[:, j], .95)
costs_err[j] = hci(costs_array[:, j], .95)
plt.errorbar(clust_range,
np.mean(inter_array, axis=0),
fmt='gD',
label='Inter Cluster',
yerr=inter_err)
plt.errorbar(clust_range,
np.mean(bcvs_array, axis=0),
fmt='bo',
label='BetaCV',
yerr=bcvs_err)
plt.errorbar(clust_range,
np.mean(intra_array, axis=0),
fmt='rs',
label='Intra Cluster',
yerr=intra_err)
plt.ylabel('Average Distance')
plt.xlabel('Number of clusters')
plt.xlim((0., 16))
plt.ylim((0., 1.))
plt.legend(frameon=False, loc='lower left')
plt.savefig(os.path.join(plot_foldpath, 'bcv.pdf'))
plt.close()
plt.errorbar(clust_range,
np.mean(costs_array, axis=0),
fmt='bo',
label='Cost',
yerr=costs_err)
plt.ylabel('Cost (F)')
plt.xlabel('Number of clusters')
plt.xlim((0., 16))
plt.ylim((0., 1.))
plt.legend(frameon=False, loc='lower left')
plt.savefig(os.path.join(plot_foldpath, 'cost.pdf'))
plt.close()
