def mnist_eucl_proc(digits, num_points, num_avg):
"""Evaluate kmeans accuracy """
eucl_dist = lambda a, b: np.linalg.norm(a - b)
proc_dist1 = lambda a, b: procrustes.procrustes(a, b)
proc_dist2 = lambda a, b: procrustes.procrustes2(a, b)
proc_dist3 = lambda a, b: procrustes.procrustes3(a, b, 50)
k = len(digits)
a1, a2, a3, a4, a5 = [], [], [], [], []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points] * k,
digits)
l1, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
l2, _, _, _ = kmeans.kmeans_(k, ext_shapes, proc_dist1)
l3, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist3)
l4, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist1)
l5, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist2)
a1.append(kmeans.accuracy(labels, l1))
a2.append(kmeans.accuracy(labels, l2))
a3.append(kmeans.accuracy(labels, l3))
a4.append(kmeans.accuracy(labels, l4))
a5.append(kmeans.accuracy(labels, l5))
print "d_E = %f" % np.mean(a1)
print "d_{P_0} = %f" % np.mean(a2)
print "d_{P_3} = %f" % np.mean(a3)
print "d_{P} = %f" % np.mean(a4)
print "d_{P_l} = %f" % np.mean(a5)
def mnist_eucl_proc(digits, num_points, num_avg):
"""Evaluate kmeans accuracy """
eucl_dist = lambda a, b: np.linalg.norm(a-b)
proc_dist1 = lambda a, b: procrustes.procrustes(a, b)
proc_dist2 = lambda a, b: procrustes.procrustes2(a, b)
proc_dist3 = lambda a, b: procrustes.procrustes3(a, b, 50)
k = len(digits)
a1, a2, a3, a4, a5 = [], [], [], [], []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points]*k,
digits)
l1, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
l2, _, _, _ = kmeans.kmeans_(k, ext_shapes, proc_dist1)
l3, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist3)
l4, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist1)
l5, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist2)
a1.append(kmeans.accuracy(labels, l1))
a2.append(kmeans.accuracy(labels, l2))
a3.append(kmeans.accuracy(labels, l3))
a4.append(kmeans.accuracy(labels, l4))
a5.append(kmeans.accuracy(labels, l5))
print "d_E = %f" % np.mean(a1)
print "d_{P_0} = %f" % np.mean(a2)
print "d_{P_3} = %f" % np.mean(a3)
print "d_{P} = %f" % np.mean(a4)
print "d_{P_l} = %f" % np.mean(a5)
def clustering_eucl(nrange, digits, num_sample, outfile):
"""Cluster originals and binaries with K-means/Euclidean."""
eucl_dist = lambda a, b: np.linalg.norm(a-b)
k = len(digits)
a1, a2 = [], []
for n in nrange:
print "Doing %i of %i"%(n, nrange[-1])
ns = [n]*k
for m in range(num_sample):
originals, shapes, ext_shapes, labels = pick_data(ns, digits)
l1, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
l2, _, _, _ = kmeans.kmeans_(k, shapes, eucl_dist)
ac1 = kmeans.accuracy(labels, l1)
ac2 = kmeans.accuracy(labels, l2)
a1.append([n, ac1])
a2.append([n, ac2])
print ' ', ac1, ac2
a1 = np.array(a1)
a2 = np.array(a2)
# plotting results
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(a1[:,0], a1[:,1], 'o', color='b', alpha=.5, label=r'$d_E$')
ax.plot(a2[:,0], a2[:,1], 'o', color='r', alpha=.5, label=r'$d_{E_b}$')
a1_avg, a2_avg = [], []
for n in nrange:
mu1 = a1[np.where(a1[:,0]==n)][:,1].mean()
mu2 = a2[np.where(a2[:,0]==n)][:,1].mean()
a1_avg.append([n, mu1])
a2_avg.append([n, mu2])
a1_avg = np.array(a1_avg)
a2_avg = np.array(a2_avg)
ax.plot(a1_avg[:,0], a1_avg[:,1], '-', color='b')
ax.plot(a2_avg[:,0], a2_avg[:,1], '-', color='r')
ax.set_xlabel(r'$N_i$')
ax.set_ylabel(r'$A$')
leg = ax.legend(loc=0)
leg.get_frame().set_alpha(0.6)
ax.set_title(r'$\{%s\}$'%(','.join([str(d) for d in digits])))
fig.savefig(outfile)
def clustering_eucl(nrange, digits, num_sample, outfile):
"""Cluster originals and binaries with K-means/Euclidean."""
eucl_dist = lambda a, b: np.linalg.norm(a - b)
k = len(digits)
a1, a2 = [], []
for n in nrange:
print "Doing %i of %i" % (n, nrange[-1])
ns = [n] * k
for m in range(num_sample):
originals, shapes, ext_shapes, labels = pick_data(ns, digits)
l1, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
l2, _, _, _ = kmeans.kmeans_(k, shapes, eucl_dist)
ac1 = kmeans.accuracy(labels, l1)
ac2 = kmeans.accuracy(labels, l2)
a1.append([n, ac1])
a2.append([n, ac2])
print ' ', ac1, ac2
a1 = np.array(a1)
a2 = np.array(a2)
# plotting results
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(a1[:, 0], a1[:, 1], 'o', color='b', alpha=.5, label=r'$d_E$')
ax.plot(a2[:, 0], a2[:, 1], 'o', color='r', alpha=.5, label=r'$d_{E_b}$')
a1_avg, a2_avg = [], []
for n in nrange:
mu1 = a1[np.where(a1[:, 0] == n)][:, 1].mean()
mu2 = a2[np.where(a2[:, 0] == n)][:, 1].mean()
a1_avg.append([n, mu1])
a2_avg.append([n, mu2])
a1_avg = np.array(a1_avg)
a2_avg = np.array(a2_avg)
ax.plot(a1_avg[:, 0], a1_avg[:, 1], '-', color='b')
ax.plot(a2_avg[:, 0], a2_avg[:, 1], '-', color='r')
ax.set_xlabel(r'$N_i$')
ax.set_ylabel(r'$A$')
leg = ax.legend(loc=0)
leg.get_frame().set_alpha(0.6)
ax.set_title(r'$\{%s\}$' % (','.join([str(d) for d in digits])))
fig.savefig(outfile)
def kmeans_procrustes(k, data, true_labels):
def dist_func(X, Y):
d = distance.procrustes(X, Y)
print d
return d
labels, mus, obj, count = kmeans.kmeans_(k, data, dist_func, 30)
error = clusval.class_error(true_labels, labels)
return error
def kmeans_procrustes(k, data, true_labels):
def dist_func(X, Y):
d = distance.procrustes(X, Y)
print d
return d
labels, mus, obj, count = kmeans.kmeans_(k, data, dist_func, 30)
error = clusval.class_error(true_labels, labels)
return error
def mnist_procrustes(digits, num_points, num_avg):
proc_dist = lambda a, b: procrustes.procrustes(a, b)
k = len(digits)
a = []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points]*k,
digits)
l, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist)
accu = kmeans.accuracy(labels, l)
a.append(accu)
print accu
print
print "d_{P} = %f" % np.mean(a)
def mnist_euclidean(digits, num_points, num_avg):
eucl_dist = lambda a, b: np.linalg.norm(a-b)
k = len(digits)
a = []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points]*k,
digits)
l, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
accu = kmeans.accuracy(labels, l)
a.append(accu)
print accu
print
print "d_E = %f" % np.mean(a)
def mnist_procrustes(digits, num_points, num_avg):
proc_dist = lambda a, b: procrustes.procrustes(a, b)
k = len(digits)
a = []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points] * k,
digits)
l, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist)
accu = kmeans.accuracy(labels, l)
a.append(accu)
print accu
print
print "d_{P} = %f" % np.mean(a)
def mnist_euclidean(digits, num_points, num_avg):
eucl_dist = lambda a, b: np.linalg.norm(a - b)
k = len(digits)
a = []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points] * k,
digits)
l, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
accu = kmeans.accuracy(labels, l)
a.append(accu)
print accu
print
print "d_E = %f" % np.mean(a)
def mnist_procrustes_filling(digits, num_points, num_avg):
eucl_dist = lambda a, b: np.linalg.norm(a-b)
proc_dist = lambda a, b: procrustes.procrustes(a, b)
proc_dist_filling = lambda a, b: fill.procrustes_filling(a, b, N=40,
scale=200)
k = len(digits)
aa1 = []
aa2 = []
aa3 = []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points]*k,
digits)
l1, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
l2, _, _, _ = kmeans.kmeans_(k, ext_shapes, proc_dist)
l3, _, _, _ = kmeans.kmeans_(k, ext_shapes, proc_dist_filling)
a1 = kmeans.accuracy(labels, l1)
a2 = kmeans.accuracy(labels, l2)
a3 = kmeans.accuracy(labels, l3)
aa1.append(a1)
aa2.append(a2)
aa3.append(a3)
print "d_{E} = %f" % np.mean(aa1)
print "d_{P} = %f" % np.mean(aa2)
print "d_{F} = %f" % np.mean(aa3)
def mnist_procrustes_filling(digits, num_points, num_avg):
eucl_dist = lambda a, b: np.linalg.norm(a - b)
proc_dist = lambda a, b: procrustes.procrustes(a, b)
proc_dist_filling = lambda a, b: fill.procrustes_filling(
a, b, N=40, scale=200)
k = len(digits)
aa1 = []
aa2 = []
aa3 = []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points] * k,
digits)
l1, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
l2, _, _, _ = kmeans.kmeans_(k, ext_shapes, proc_dist)
l3, _, _, _ = kmeans.kmeans_(k, ext_shapes, proc_dist_filling)
a1 = kmeans.accuracy(labels, l1)
a2 = kmeans.accuracy(labels, l2)
a3 = kmeans.accuracy(labels, l3)
aa1.append(a1)
aa2.append(a2)
aa3.append(a3)
print "d_{E} = %f" % np.mean(aa1)
print "d_{P} = %f" % np.mean(aa2)
print "d_{F} = %f" % np.mean(aa3)
def mnist_alignment(digits, num_points, num_avg):
def dist_func(im1, im2):
d = fill.euclidean_alignment(im1, im2)
return d
k = len(digits)
a = []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points] * k,
digits)
l, _, _, _ = kmeans.kmeans_(k, originals, dist_func)
accu = kmeans.accuracy(labels, l)
a.append(accu)
print accu
print
print "d_A = %f" % np.mean(a)
def mnist_alignment(digits, num_points, num_avg):
def dist_func(im1, im2):
d = fill.euclidean_alignment(im1, im2)
return d
k = len(digits)
a = []
for i in range(num_avg):
originals, shapes, ext_shapes, labels = pick_data([num_points]*k,
digits)
l, _, _, _ = kmeans.kmeans_(k, originals, dist_func)
accu = kmeans.accuracy(labels, l)
a.append(accu)
print accu
print
print "d_A = %f" % np.mean(a)
def kmeans_euclidean(k, data, true_labels):
dist_func = distance.euclidean
labels, mus, obj, count = kmeans.kmeans_(k, data, dist_func, 30)
error = clusval.class_error(true_labels, labels)
return error
def mnist_standard_vs_procrustes(nrange, digits, num_sample, outfile):
"""Plot accuracy when clustering MNIST digits, using procrustes
and Euclidean distance.
"""
eucl_dist = lambda a, b: np.linalg.norm(a-b)
proc_dist1 = lambda a, b: procrustes.procrustes(a, b)
proc_dist2 = lambda a, b: procrustes.procrustes2(a, b)
proc_dist3 = lambda a, b: procrustes.procrustes3(a, b, 50)
k = len(digits)
a1, a2, a3, a4, a5 = [], [], [], [], []
for n in nrange:
print "Doing %i of %i"%(n, nrange[-1])
ns = [n]*k
for m in range(num_sample):
originals, shapes, ext_shapes, labels = pick_data(ns, digits)
l1, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
l2, _, _, _ = kmeans.kmeans_(k, ext_shapes, proc_dist1)
l3, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist3)
l4, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist1)
l5, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist2)
ac1 = kmeans.accuracy(labels, l1)
ac2 = kmeans.accuracy(labels, l2)
ac3 = kmeans.accuracy(labels, l3)
ac4 = kmeans.accuracy(labels, l4)
ac5 = kmeans.accuracy(labels, l5)
a1.append([n, ac1])
a2.append([n, ac2])
a3.append([n, ac3])
a4.append([n, ac4])
a5.append([n, ac5])
print ' ', ac1, ac2, ac3, ac4, ac5
a1 = np.array(a1)
a2 = np.array(a2)
a3 = np.array(a3)
a4 = np.array(a4)
a5 = np.array(a5)
# plotting results
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(a1[:,0], a1[:,1], 'o', color='b', alpha=.5, label=r'$d_E$')
ax.plot(a2[:,0], a2[:,1], 'o', color='r', alpha=.5, label=r'$d_{P_0}$')
ax.plot(a3[:,0], a3[:,1], 'o', color='g', alpha=.5, label=r'$d_{P_3}$')
ax.plot(a4[:,0], a4[:,1], 'o', color='c', alpha=.5, label=r'$d_{P}$')
ax.plot(a5[:,0], a5[:,1], 'o', color='m', alpha=.5, label=r'$d_{P_l}$')
a1_avg, a2_avg, a3_avg, a4_avg, a5_avg = [], [], [], [], []
for n in nrange:
mu1 = a1[np.where(a1[:,0]==n)][:,1].mean()
mu2 = a2[np.where(a2[:,0]==n)][:,1].mean()
mu3 = a3[np.where(a3[:,0]==n)][:,1].mean()
mu4 = a4[np.where(a4[:,0]==n)][:,1].mean()
mu5 = a5[np.where(a5[:,0]==n)][:,1].mean()
a1_avg.append([n, mu1])
a2_avg.append([n, mu2])
a3_avg.append([n, mu3])
a4_avg.append([n, mu4])
a5_avg.append([n, mu5])
a1_avg = np.array(a1_avg)
a2_avg = np.array(a2_avg)
a3_avg = np.array(a3_avg)
a4_avg = np.array(a4_avg)
a5_avg = np.array(a5_avg)
ax.plot(a1_avg[:,0], a1_avg[:,1], '-', color='b')
ax.plot(a2_avg[:,0], a2_avg[:,1], '-', color='r')
ax.plot(a3_avg[:,0], a3_avg[:,1], '-', color='g')
ax.plot(a4_avg[:,0], a4_avg[:,1], '-', color='c')
ax.plot(a5_avg[:,0], a5_avg[:,1], '-', color='m')
ax.set_xlabel(r'$N_i$')
ax.set_ylabel(r'$A$')
leg = ax.legend(loc=0)
leg.get_frame().set_alpha(0.6)
ax.set_title(r'$\{%s\}$'%(','.join([str(d) for d in digits])))
fig.savefig(outfile)
def kmeans_euclidean(k, data, true_labels):
dist_func = distance.euclidean
labels, mus, obj, count = kmeans.kmeans_(k, data, dist_func, 30)
error = clusval.class_error(true_labels, labels)
return error
def mnist_standard_vs_procrustes(nrange, digits, num_sample, outfile):
"""Plot accuracy when clustering MNIST digits, using procrustes
and Euclidean distance.
"""
eucl_dist = lambda a, b: np.linalg.norm(a - b)
proc_dist1 = lambda a, b: procrustes.procrustes(a, b)
proc_dist2 = lambda a, b: procrustes.procrustes2(a, b)
proc_dist3 = lambda a, b: procrustes.procrustes3(a, b, 50)
k = len(digits)
a1, a2, a3, a4, a5 = [], [], [], [], []
for n in nrange:
print "Doing %i of %i" % (n, nrange[-1])
ns = [n] * k
for m in range(num_sample):
originals, shapes, ext_shapes, labels = pick_data(ns, digits)
l1, _, _, _ = kmeans.kmeans_(k, originals, eucl_dist)
l2, _, _, _ = kmeans.kmeans_(k, ext_shapes, proc_dist1)
l3, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist3)
l4, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist1)
l5, _, _, _ = kmeans.kmeans_(k, shapes, proc_dist2)
ac1 = kmeans.accuracy(labels, l1)
ac2 = kmeans.accuracy(labels, l2)
ac3 = kmeans.accuracy(labels, l3)
ac4 = kmeans.accuracy(labels, l4)
ac5 = kmeans.accuracy(labels, l5)
a1.append([n, ac1])
a2.append([n, ac2])
a3.append([n, ac3])
a4.append([n, ac4])
a5.append([n, ac5])
print ' ', ac1, ac2, ac3, ac4, ac5
a1 = np.array(a1)
a2 = np.array(a2)
a3 = np.array(a3)
a4 = np.array(a4)
a5 = np.array(a5)
# plotting results
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(a1[:, 0], a1[:, 1], 'o', color='b', alpha=.5, label=r'$d_E$')
ax.plot(a2[:, 0], a2[:, 1], 'o', color='r', alpha=.5, label=r'$d_{P_0}$')
ax.plot(a3[:, 0], a3[:, 1], 'o', color='g', alpha=.5, label=r'$d_{P_3}$')
ax.plot(a4[:, 0], a4[:, 1], 'o', color='c', alpha=.5, label=r'$d_{P}$')
ax.plot(a5[:, 0], a5[:, 1], 'o', color='m', alpha=.5, label=r'$d_{P_l}$')
a1_avg, a2_avg, a3_avg, a4_avg, a5_avg = [], [], [], [], []
for n in nrange:
mu1 = a1[np.where(a1[:, 0] == n)][:, 1].mean()
mu2 = a2[np.where(a2[:, 0] == n)][:, 1].mean()
mu3 = a3[np.where(a3[:, 0] == n)][:, 1].mean()
mu4 = a4[np.where(a4[:, 0] == n)][:, 1].mean()
mu5 = a5[np.where(a5[:, 0] == n)][:, 1].mean()
a1_avg.append([n, mu1])
a2_avg.append([n, mu2])
a3_avg.append([n, mu3])
a4_avg.append([n, mu4])
a5_avg.append([n, mu5])
a1_avg = np.array(a1_avg)
a2_avg = np.array(a2_avg)
a3_avg = np.array(a3_avg)
a4_avg = np.array(a4_avg)
a5_avg = np.array(a5_avg)
ax.plot(a1_avg[:, 0], a1_avg[:, 1], '-', color='b')
ax.plot(a2_avg[:, 0], a2_avg[:, 1], '-', color='r')
ax.plot(a3_avg[:, 0], a3_avg[:, 1], '-', color='g')
ax.plot(a4_avg[:, 0], a4_avg[:, 1], '-', color='c')
ax.plot(a5_avg[:, 0], a5_avg[:, 1], '-', color='m')
ax.set_xlabel(r'$N_i$')
ax.set_ylabel(r'$A$')
leg = ax.legend(loc=0)
leg.get_frame().set_alpha(0.6)
ax.set_title(r'$\{%s\}$' % (','.join([str(d) for d in digits])))
fig.savefig(outfile)