else: unknown_vec = w2v_model.seeded_vector(token) unknown_words[token] = unknown_vec test_vectors.append(unknown_vec) # Train GMM print 'Starting GMM training' words = w2v_model.vocab.keys() word_vectors = w2v_model.syn0 gmm_model = GMM(n_components=num_topics, n_iter=num_gmm_iterations, covariance_type='diag') gmm_model.fit(word_vectors) # joblib.dump(gmm_model, gmm_output_file) print 'Done GMM training' # Get the likelihood of each word vector under each Gaussian component scores = gmm_model.score(test_vectors) print scores ll = sum(scores) print "LL: "+str(ll) # Print topics if desired if print_topics: log_probs = log_multivariate_normal_density(word_vectors, gmm_model.means_, gmm_model.covars_, gmm_model.covariance_type) print np.min(log_probs) _, num_col = log_probs.shape for col in xrange(num_col): top_n = 10 log_component_probs = (log_probs[:,col]).T sorted_indexes = np.argsort(log_component_probs)[::-1][:top_n] ordered_word_probs = [(w2v_model.index2word[idx], log_component_probs[idx]) for idx in sorted_indexes]
unknown_words[token] = unknown_vec
test_vectors.append(unknown_vec)
# Train GMM
print 'Starting GMM training'
words = w2v_model.vocab.keys()
word_vectors = w2v_model.syn0
gmm_model = GMM(n_components=num_topics,
n_iter=num_gmm_iterations,
covariance_type='diag')
gmm_model.fit(word_vectors)
# joblib.dump(gmm_model, gmm_output_file)
print 'Done GMM training'
# Get the likelihood of each word vector under each Gaussian component
scores = gmm_model.score(test_vectors)
print scores
ll = sum(scores)
print "LL: " + str(ll)
# Print topics if desired
if print_topics:
log_probs = log_multivariate_normal_density(
word_vectors, gmm_model.means_, gmm_model.covars_,
gmm_model.covariance_type)
print np.min(log_probs)
_, num_col = log_probs.shape
for col in xrange(num_col):
top_n = 10
log_component_probs = (log_probs[:, col]).T
sorted_indexes = np.argsort(
