def test_moments(self):
"""
Test the moments of categorical nodes.
"""
# Simple test
X = Categorical([0.7, 0.2, 0.1])
u = X._message_to_child()
self.assertEqual(len(u), 1)
self.assertAllClose(u[0], [0.7, 0.2, 0.1])
# Test plates in p
p = np.random.dirichlet([1, 1], size=3)
X = Categorical(p)
u = X._message_to_child()
self.assertAllClose(u[0], p)
# Test with Dirichlet prior
P = Dirichlet([7, 3])
logp = P._message_to_child()[0]
p0 = np.exp(logp[0]) / (np.exp(logp[0]) + np.exp(logp[1]))
p1 = np.exp(logp[1]) / (np.exp(logp[0]) + np.exp(logp[1]))
X = Categorical(P)
u = X._message_to_child()
p = np.array([p0, p1])
self.assertAllClose(u[0], p)
# Test with broadcasted plates
P = Dirichlet([7, 3], plates=(10, ))
X = Categorical(P)
u = X._message_to_child()
self.assertAllClose(u[0] * np.ones(X.get_shape(0)), p * np.ones(
(10, 1)))
pass
def test_moments(self):
"""
Test the moments of multinomial nodes.
"""
# Simple test
X = Multinomial(1, [0.7, 0.2, 0.1])
u = X._message_to_child()
self.assertEqual(len(u), 1)
self.assertAllClose(u[0], [0.7, 0.2, 0.1])
# Test n
X = Multinomial(10, [0.7, 0.2, 0.1])
u = X._message_to_child()
self.assertAllClose(u[0], [7, 2, 1])
# Test plates in p
n = np.random.randint(1, 10)
p = np.random.dirichlet([1, 1], size=3)
X = Multinomial(n, p)
u = X._message_to_child()
self.assertAllClose(u[0], p * n)
# Test plates in n
n = np.random.randint(1, 10, size=(3, ))
p = np.random.dirichlet([1, 1, 1, 1])
X = Multinomial(n, p)
u = X._message_to_child()
self.assertAllClose(u[0], p * n[:, None])
# Test plates in p and n
n = np.random.randint(1, 10, size=(4, 1))
p = np.random.dirichlet([1, 1], size=3)
X = Multinomial(n, p)
u = X._message_to_child()
self.assertAllClose(u[0], p * n[..., None])
# Test with Dirichlet prior
P = Dirichlet([7, 3])
logp = P._message_to_child()[0]
p0 = np.exp(logp[0]) / (np.exp(logp[0]) + np.exp(logp[1]))
p1 = np.exp(logp[1]) / (np.exp(logp[0]) + np.exp(logp[1]))
X = Multinomial(1, P)
u = X._message_to_child()
p = np.array([p0, p1])
self.assertAllClose(u[0], p)
# Test with broadcasted plates
P = Dirichlet([7, 3], plates=(10, ))
X = Multinomial(5, P)
u = X._message_to_child()
self.assertAllClose(u[0] * np.ones(X.get_shape(0)), 5 * p * np.ones(
(10, 1)))
pass
def test_moments(self):
"""
Test the moments of Dirichlet nodes.
"""
p = Dirichlet([2, 3, 4])
u = p._message_to_child()
self.assertAllClose(u[0],
special.psi([2,3,4]) - special.psi(2+3+4))
pass
def test_constant(self):
"""
Test the constant moments of Dirichlet nodes.
"""
p = Dirichlet([1, 1, 1])
p.initialize_from_value([0.5, 0.4, 0.1])
u = p._message_to_child()
self.assertAllClose(u[0], np.log([0.5, 0.4, 0.1]))
pass
def test_moments(self):
"""
Test the moments of Dirichlet nodes.
"""
p = Dirichlet([2, 3, 4])
u = p._message_to_child()
self.assertAllClose(u[0],
special.psi([2, 3, 4]) - special.psi(2 + 3 + 4))
pass
def test_constant(self):
"""
Test the constant moments of Dirichlet nodes.
"""
p = Dirichlet([1, 1, 1])
p.initialize_from_value([0.5, 0.4, 0.1])
u = p._message_to_child()
self.assertAllClose(u[0],
np.log([0.5, 0.4, 0.1]))
pass
def _run(self, x, K=25, beta=0.5, alpha=0.00001, hinton_plot=False, end=False):
'''Only to be used when doing parameter optimization.'''
self.participant_list = x[0]
N = len(x[0]) #number of data points (i.e. WCS participants)
D = np.shape(x[1])[1] #number of features
#K = 20 #number of initial clusters
R = Dirichlet(K*[alpha],
name='R')
Z = Categorical(R,
plates=(N,1),
name='Z')
P = Beta([beta, beta],
plates=(D,K),
name='P')
X = Mixture(Z, Bernoulli, P)
Q = VB(Z, R, X, P)
P.initialize_from_random()
X.observe(x[1])
Q.update(repeat=1000)
log_likelihood = Q.L[Q.iter-1]
if hinton_plot:
bpplt.hinton(Z)
bpplt.pyplot.show()
bpplt.hinton(R)
bpplt.pyplot.show()
#Get the weight matrix stored in Z (weights determine which cluster data point belongs to)
z = Z._message_to_child()[0]
z = z * np.ones(Z.plates+(1,))
z = np.squeeze(z)
self.z = z
#Get the weights stored in R (proportional to the size of the clusters)
r = np.exp(R._message_to_child()[0])
r = r * np.ones(R.plates+(1,))
r = np.squeeze(r)
self.r = r
#Get the cluster assignment of each data point
self.c_assign = np.argmax(self.z, axis=1)
return log_likelihood
def test_moments(self):
"""
Test the moments of categorical nodes.
"""
# Simple test
X = Categorical([0.7,0.2,0.1])
u = X._message_to_child()
self.assertEqual(len(u), 1)
self.assertAllClose(u[0],
[0.7,0.2,0.1])
# Test plates in p
p = np.random.dirichlet([1,1], size=3)
X = Categorical(p)
u = X._message_to_child()
self.assertAllClose(u[0],
p)
# Test with Dirichlet prior
P = Dirichlet([7, 3])
logp = P._message_to_child()[0]
p0 = np.exp(logp[0]) / (np.exp(logp[0]) + np.exp(logp[1]))
p1 = np.exp(logp[1]) / (np.exp(logp[0]) + np.exp(logp[1]))
X = Categorical(P)
u = X._message_to_child()
p = np.array([p0, p1])
self.assertAllClose(u[0],
p)
# Test with broadcasted plates
P = Dirichlet([7, 3], plates=(10,))
X = Categorical(P)
u = X._message_to_child()
self.assertAllClose(u[0] * np.ones(X.get_shape(0)),
p*np.ones((10,1)))
pass
def test_moments(self):
"""
Test the moments of multinomial nodes.
"""
# Simple test
X = Multinomial(1, [0.7,0.2,0.1])
u = X._message_to_child()
self.assertEqual(len(u), 1)
self.assertAllClose(u[0],
[0.7,0.2,0.1])
# Test n
X = Multinomial(10, [0.7,0.2,0.1])
u = X._message_to_child()
self.assertAllClose(u[0],
[7,2,1])
# Test plates in p
n = np.random.randint(1, 10)
p = np.random.dirichlet([1,1], size=3)
X = Multinomial(n, p)
u = X._message_to_child()
self.assertAllClose(u[0],
p*n)
# Test plates in n
n = np.random.randint(1, 10, size=(3,))
p = np.random.dirichlet([1,1,1,1])
X = Multinomial(n, p)
u = X._message_to_child()
self.assertAllClose(u[0],
p*n[:,None])
# Test plates in p and n
n = np.random.randint(1, 10, size=(4,1))
p = np.random.dirichlet([1,1], size=3)
X = Multinomial(n, p)
u = X._message_to_child()
self.assertAllClose(u[0],
p*n[...,None])
# Test with Dirichlet prior
P = Dirichlet([7, 3])
logp = P._message_to_child()[0]
p0 = np.exp(logp[0]) / (np.exp(logp[0]) + np.exp(logp[1]))
p1 = np.exp(logp[1]) / (np.exp(logp[0]) + np.exp(logp[1]))
X = Multinomial(1, P)
u = X._message_to_child()
p = np.array([p0, p1])
self.assertAllClose(u[0],
p)
# Test with broadcasted plates
P = Dirichlet([7, 3], plates=(10,))
X = Multinomial(5, P)
u = X._message_to_child()
self.assertAllClose(u[0] * np.ones(X.get_shape(0)),
5*p*np.ones((10,1)))
pass
def run(self, K=25, beta=0.5, alpha=0.00001, foci_thresh=0, num_neigh=4, hinton_plot=False, end=False):
'''Performs one run of the BBDP according to the specified parameters.'''
print("Transforming WCS participant data into binary vectors...")
x = u.transform_data_all(self.langs, norm=False, end=end, foci=True, foci_thresh=foci_thresh, num_neigh=num_neigh)
print("Finished transforming participant data")
self.participant_list = x[0]
N = len(x[0]) #number of data points (i.e. WCS participants)
D = np.shape(x[1])[1] #number of features
#K = 20 #number of initial clusters
R = Dirichlet(K*[alpha],
name='R')
Z = Categorical(R,
plates=(N,1),
name='Z')
P = Beta([beta, beta],
plates=(D,K),
name='P')
X = Mixture(Z, Bernoulli, P)
Q = VB(Z, R, X, P)
P.initialize_from_random()
X.observe(x[1])
Q.update(repeat=1000)
if hinton_plot:
bpplt.hinton(Z)
bpplt.pyplot.show()
bpplt.hinton(R)
bpplt.pyplot.show()
#Get the weight matrix stored in Z (weights determine which cluster data point belongs to)
z = Z._message_to_child()[0]
z = z * np.ones(Z.plates+(1,))
z = np.squeeze(z)
self.z = z
#Get the weights stored in R (proportional to the size of the clusters)
r = np.exp(R._message_to_child()[0])
r = r * np.ones(R.plates+(1,))
r = np.squeeze(r)
self.r = r
#Get the cluster assignment of each data point
self.c_assign = np.argmax(self.z, axis=1)
#Write cluster results to a file
if self.write_to_file:
if end:
save_path = "cluster_results_end_K={}_B={}_a={}_t={}_nn={}".format(K, beta, alpha, foci_thresh, num_neigh)
else:
save_path = "cluster_results_K={}_B={}_a={}_t={}_nn={}".format(K, beta, alpha, foci_thresh, num_neigh)
while path.exists(save_path+".txt"):
#save_path already exists
try:
old_file_num = int(save_path[save_path.find('(')+1:-1])
new_file_num = old_file_num + 1
save_path = save_path[0:save_path.find('(')] + '(' + str(new_file_num) + ')'
except ValueError:
save_path = save_path + " (1)"
self.save_path = save_path
file = open(path.abspath(self.save_path+".txt"), 'w')
#Write cluster assignment matrix Z (gives the probability that observation i belongs to cluster j)
if 'Z' not in self.in_file:
for i in range(len(self.z)):
line = "\t".join([str(x) for x in self.z[i]]) + "\n"
file.write(line)
file.write('---Z\n')
self.in_file.append('Z')
#Write cluster weights matrix R (proportional to the size of the resulting clusters)
if 'R' not in self.in_file:
line = "\t".join([str(x) for x in self.r]) + "\n"
file.write(line)
file.write('---R\n')
self.in_file.append('R')
#Write deterministic cluster assignments with the corresponding participant key
if 'C' not in self.in_file:
line1 = "\t".join([str(x) for x in self.participant_list]) + "\n"
line2 = "\t".join([str(x) for x in self.c_assign]) + "\n"
file.write(line1)
file.write(line2)
file.write('---C\n')
self.in_file.append('C')
file.close()
return self.c_assign
# coding: utf-8 ## Gaussian mixture model # Do some stuff: # In[2]: from bayespy.nodes import Dirichlet alpha = Dirichlet([1e-3, 1e-3, 1e-3]) print(alpha._message_to_child()) # Nice!
