def vi(self, i, ids, cts, words_no, expElogbetad, no_iter=1000):
alpha = self.G_0.G_0 * self.m_gamma
gamma = np.ones(len(alpha))
expElogtheta = np.exp(dirichlet_expectation(gamma))
phinorm = np.dot(expElogtheta, expElogbetad) + 1e-100
counts = np.array(cts)
for _ in range(no_iter):
lastgamma = gamma
gamma = alpha + expElogtheta * np.dot(cts / phinorm,
expElogbetad.T)
expElogtheta = np.exp(dirichlet_expectation(gamma))
phinorm = np.dot(expElogtheta, expElogbetad) + 1e-100
meanchange = mean_absolute_difference(gamma, lastgamma)
if meanchange < meanchangethresh:
break
pro_mat = np.outer(expElogtheta.T, 1 / phinorm) * expElogbetad
mat_z = my_multinomial(pro_mat)
self.mat_z[i][self.effe_list] = mat_z
self.mat_z_sum[i][self.effe_list] = np.dot(mat_z, cts)
def testMeanAbsoluteDifference(self):
# test mean_absolute_difference
rs = self.random_state
for dtype in [np.float16, np.float32, np.float64]:
for i in range(self.num_runs):
input1 = rs.uniform(-10000, 10000, size=(self.num_topics,))
input2 = rs.uniform(-10000, 10000, size=(self.num_topics,))
known_good = mean_absolute_difference(input1, input2)
test_values = matutils.mean_absolute_difference(input1, input2)
msg = "mean_absolute_difference failed for dtype={}".format(dtype)
self.assertTrue(np.allclose(known_good, test_values), msg)
def lda_e_step(doc_word_ids, doc_word_counts, alpha, beta, max_iter=100):
r"""Performs EM-iteration on a single document for calculation of likelihood for a maximum iteration of `max_iter`.
Parameters
----------
doc_word_ids : int
Id of corresponding words in a document.
doc_word_counts : int
Count of words in a single document.
alpha : numpy.ndarray
Lda equivalent value of alpha.
beta : numpy.ndarray
Lda equivalent value of beta.
max_iter : int, optional
Maximum number of times the expectation will be maximised.
Returns
-------
(numpy.ndarray, numpy.ndarray)
Computed (:math:`likelihood`, :math:`\gamma`).
"""
gamma = np.ones(len(alpha))
expElogtheta = np.exp(dirichlet_expectation(gamma))
betad = beta[:, doc_word_ids]
phinorm = np.dot(expElogtheta, betad) + 1e-100
counts = np.array(doc_word_counts)
for _ in range(max_iter):
lastgamma = gamma
gamma = alpha + expElogtheta * np.dot(counts / phinorm, betad.T)
Elogtheta = dirichlet_expectation(gamma)
expElogtheta = np.exp(Elogtheta)
phinorm = np.dot(expElogtheta, betad) + 1e-100
meanchange = mean_absolute_difference(gamma, lastgamma)
if meanchange < meanchangethresh:
break
likelihood = np.sum(counts * np.log(phinorm))
likelihood += np.sum((alpha - gamma) * Elogtheta)
likelihood += np.sum(gammaln(gamma) - gammaln(alpha))
likelihood += gammaln(np.sum(alpha)) - gammaln(np.sum(gamma))
return likelihood, gamma
def lda_e_step(ids, cts, alpha, expElogbetad, max_iter=1000):
"""
the function to update global parameters
"""
gamma = np.ones(len(alpha))
expElogtheta = np.exp(dirichlet_expectation(gamma))
phinorm = np.dot(expElogtheta, expElogbetad) + 1e-100
counts = np.array(cts)
for _ in range(max_iter):
lastgamma = gamma
gamma = alpha + expElogtheta * np.dot(cts / phinorm, expElogbetad.T)
expElogtheta = np.exp(dirichlet_expectation(gamma))
phinorm = np.dot(expElogtheta, expElogbetad) + 1e-100
meanchange = mean_absolute_difference(gamma, lastgamma)
if meanchange < meanchangethresh:
break
return gamma / np.sum(gamma)
def update_doc(self, i, max_iter=500):
self.mat_z[i] = np.zeros(((self.max_K + 1), self.chunk_doc_word_no[i]))
self.mat_z_avrg[i] = np.copy(self.mat_z[i])
self.mat_z_sum[i] = np.zeros((self.max_K + 1))
ids = self.chunk_doc_word_ids_list[i]
cts = self.chunk_doc_word_counts_list[i]
words_no = self.chunk_doc_word_no[i]
expElogbetad = self.m_dir_exp_lambda[np.ix_(self.effe_list, ids)]
self.vi(i, ids, cts, words_no, expElogbetad, no_iter=1000)
self.gibbs_samplings(i, ids, cts, words_no, expElogbetad, max_iter=10)
iter = 2
aver_sum = np.copy(self.mat_z_sum[i])
aver_phi = digamma(self.G_0.G_0 * self.m_gamma +
self.mat_z_sum[i][self.effe_list])
while iter < max_iter:
last_aver_sum = np.copy(aver_sum)
self.gibbs_samplings(i,
ids,
cts,
words_no,
expElogbetad,
max_iter=1)
self.mat_z_avrg[i] -= 1 / iter * (self.mat_z_avrg[i] -
self.mat_z[i])
aver_sum -= 1 / iter * (last_aver_sum - self.mat_z_sum[i])
aver_phi -= 1 / iter * (aver_phi -
digamma(self.G_0.G_0 * self.m_gamma +
self.mat_z_sum[i][self.effe_list]))
iter += 1
meanchange = mean_absolute_difference(
aver_sum[self.effe_list],
last_aver_sum[self.effe_list]) / np.sum(cts)
if meanchange < meanchangethresh:
break
self.mat_phi[self.effe_list,
i] = aver_phi - digamma(self.G_0.G_0 * self.m_gamma)
if np.sum(self.mat_z_avrg[i][0]) > 0:
add_vector = self.mat_z_sum[i][0]
add_no = 1
add_list = ids
self.m_K += add_no
new_k = find_gap_in_np_array(self.effe_list, add_no)
self.effe_list = np.sort(self.effe_list.tolist() + new_k)
self.mat_z_avrg[i][new_k] = self.mat_z_avrg[i][0]
self.mat_z_avrg[i][0] = np.zeros_like(self.mat_z_avrg[i][0])
self.mat_z[i][new_k] = self.mat_z[i][0]
self.mat_z[i][0] = np.zeros_like(self.mat_z[i][0])
self.mat_phi[new_k, i] = self.mat_phi[0, i]
self.mat_phi[0, i] = np.zeros_like(self.mat_phi[0, i])
self.G_0.add_new(add_no)
self.m_lambda[np.ix_(new_k, add_list)] += self.rhot * self.m_D / self.chunksize * np.array(cts) * \
self.mat_z_avrg[i][new_k]
self.m_dir_exp_lambda[new_k] = np.exp(
dirichlet_expectation(self.m_lambda[new_k] + self.m_beta))