def __eval_lda_clustering(lda_model, mm_corpus, gold_labels):
# lda_model = gensim.models.ldamodel.LdaModel.load(model_file)
sys_labels = list()
for i, doc in enumerate(mm_corpus):
topic_dist = lda_model[doc]
# print topic_dist
cluster_idx = 0
max_dist = 0
for tup in topic_dist:
if tup[1] > max_dist:
cluster_idx = tup[0]
max_dist = tup[1]
sys_labels.append(cluster_idx)
if len(sys_labels) % 5000 == 0:
print len(sys_labels)
# if i > 10:
# break
# print len(sys_labels)
# print len(gold_labels)
nmi_score = normalized_mutual_info_score(gold_labels, sys_labels)
purity_score = purity(gold_labels, sys_labels)
ri_score = rand_index(gold_labels, sys_labels)
# print 'NMI: %f' % normalized_mutual_info_score(gold_labels, sys_labels)
# print 'Purity: %f' % purity(gold_labels, sys_labels)
# print 'Accuracy: %f' % cluster_accuracy(gold_labels, sys_labels)
print 'NMI: %f Purity: %f Rand index: %f' % (nmi_score, purity_score,
ri_score)
return nmi_score, purity_score, ri_score
def __eval_lda_clustering(lda_model, mm_corpus, gold_labels):
# lda_model = gensim.models.ldamodel.LdaModel.load(model_file)
sys_labels = list()
for i, doc in enumerate(mm_corpus):
topic_dist = lda_model[doc]
# print topic_dist
cluster_idx = 0
max_dist = 0
for tup in topic_dist:
if tup[1] > max_dist:
cluster_idx = tup[0]
max_dist = tup[1]
sys_labels.append(cluster_idx)
if len(sys_labels) % 5000 == 0:
print len(sys_labels)
# if i > 10:
# break
# print len(sys_labels)
# print len(gold_labels)
nmi_score = normalized_mutual_info_score(gold_labels, sys_labels)
purity_score = purity(gold_labels, sys_labels)
ri_score = rand_index(gold_labels, sys_labels)
# print 'NMI: %f' % normalized_mutual_info_score(gold_labels, sys_labels)
# print 'Purity: %f' % purity(gold_labels, sys_labels)
# print 'Accuracy: %f' % cluster_accuracy(gold_labels, sys_labels)
print 'NMI: %f Purity: %f Rand index: %f' % (nmi_score, purity_score, ri_score)
return nmi_score, purity_score, ri_score
def bow_kmeans(bow_vecs, gold_labels, num_clusters):
print 'performing kmeans ...'
model = KMeans(n_clusters=num_clusters, n_jobs=4, n_init=20)
model.fit(bow_vecs)
# print len(gold_labels), 'samples'
nmi_score = normalized_mutual_info_score(gold_labels, model.labels_)
purity_score = purity(gold_labels, model.labels_)
ri_score = rand_index(gold_labels, model.labels_)
# print 'NMI: %f' % normalized_mutual_info_score(gold_labels, model.labels_)
# print 'Purity: %f' % purity(gold_labels, model.labels_)
# print 'Accuracy: %f' % cluster_accuracy(gold_labels, model.labels_)
print 'NMI: %f Purity: %f Rand index: %f' % (nmi_score, purity_score, ri_score)
return nmi_score, purity_score, ri_score
def bow_kmeans(bow_vecs, gold_labels, num_clusters):
print 'performing kmeans ...'
model = KMeans(n_clusters=num_clusters, n_jobs=4, n_init=20)
model.fit(bow_vecs)
# print len(gold_labels), 'samples'
nmi_score = normalized_mutual_info_score(gold_labels, model.labels_)
purity_score = purity(gold_labels, model.labels_)
ri_score = 0
# ri_score = rand_index(gold_labels, model.labels_)
# print 'NMI: %f' % normalized_mutual_info_score(gold_labels, model.labels_)
# print 'Purity: %f' % purity(gold_labels, model.labels_)
# print 'Accuracy: %f' % cluster_accuracy(gold_labels, model.labels_)
print 'NMI: %f Purity: %f Rand index: %f' % (nmi_score, purity_score,
ri_score)
print '%f\t%f\t%f' % (nmi_score, purity_score, ri_score)
return nmi_score, purity_score, ri_score
def __lda_clustering():
num_topics = 20
min_occurrence = 30
# datadir = 'e:/data/emadr/20ng_bydate/'
# labels_file = os.path.join(datadir, 'bindata/test-labels.bin')
# topic_vecs_file = os.path.join(datadir, 'lda/test-vecs-%d-%d.bin' % (num_topics, min_occurrence))
datadir = 'e:/data/emadr/nyt-less-docs/world'
labels_file = os.path.join(datadir, 'bindata/test-labels.bin')
topic_vecs_file = os.path.join(
datadir, 'lda/test-vecs-%d-%d.bin' % (num_topics, min_occurrence))
topic_vecs = ioutils.load_vec_list_file(topic_vecs_file)
gold_labels = ioutils.load_labels_file(labels_file)
sys_labels = list()
for i, topic_vec in enumerate(topic_vecs):
cluster_idx = 0
max_dist = 0
for j, v in enumerate(topic_vec):
if v > max_dist:
cluster_idx = j
max_dist = v
# print cluster_idx, max_dist
sys_labels.append(cluster_idx)
if len(sys_labels) % 5000 == 0:
print len(sys_labels)
nmi_score = normalized_mutual_info_score(gold_labels, sys_labels)
purity_score = purity(gold_labels, sys_labels)
# ri_score = rand_index(gold_labels, sys_labels)
ri_score = 0
print 'NMI: %f Purity: %f Rand index: %f' % (nmi_score, purity_score,
ri_score)
# print 'Accuracy: %f' % cluster_accuracy(labels, model.labels_)
print '%f\t%f\t%f' % (nmi_score, purity_score, ri_score)