def gen_sent_on_topic(idxvocab, vocabxid, start_symbol, end_symbol, cf):
output = codecs.open(args.gen_sent_on_topic, "wb", "utf-8")
topics, entropy = tm.get_topics(sess, topn=topn)
with tf.variable_scope("model", reuse=True, initializer=initializer):
mgen = LM(is_training=False, vocab_size=len(idxvocab), batch_size=1, num_steps=1, config=cf, \
reuse_conv_variables=True)
for t in range(cf.topic_number):
output.write("\n" + "=" * 100 + "\n")
output.write("Topic " + str(t) + ":\n")
output.write(" ".join([idxvocab[item] for item in topics[t]]) + "\n\n")
output.write("\nSentence generation (greedy; argmax):" + "\n")
s = mgen.generate_on_topic(sess, t, vocabxid[start_symbol], 0,
cf.lm_sent_len + 10, vocabxid[end_symbol])
output.write("[0] " + " ".join([idxvocab[item] for item in s]) + "\n")
for temp in gen_temps:
output.write("\nSentence generation (random; temperature = " +
str(temp) + "):\n")
for i in range(gen_num):
s = mgen.generate_on_topic(sess, t, vocabxid[start_symbol], temp, cf.lm_sent_len+10, \
vocabxid[end_symbol])
output.write("[" + str(i) + "] " +
" ".join([idxvocab[item] for item in s]) + "\n")
def gen_sent_on_doc(docs, tags, idxvocab, vocabxid, start_symbol, end_symbol, cf):
topics, _ = tm.get_topics(sess, topn=topn)
topics = [ " ".join([idxvocab[w] for w in t]) for t in topics ]
doc_text = [ item.replace("\t", "\n") for item in codecs.open(args.input_doc, "r", "utf-8").readlines() ]
output = codecs.open(args.gen_sent_on_doc, "w", "utf-8")
with tf.variable_scope("model", reuse=True, initializer=initializer):
mgen = LM(is_training=False, vocab_size=len(idxvocab), batch_size=1, num_steps=1, config=cf, \
reuse_conv_variables=True)
for d in range(len(docs)):
output.write("\n" + "="*100 + "\n")
output.write("Doc " + str(d) +":\n")
output.write(doc_text[d])
doc, _, _, t, _ = get_batch_doc(docs, None, tags, d, cf.doc_len, cf.tag_len, 1, vocabxid[pad_symbol])
best_topics, best_words = mgen.get_topics_on_doc(sess, doc, t, topn)
output.write("\nRepresentative topics:\n")
output.write("\n".join([ ("[%.3f] %s: %s" % (item[1],str(item[0]).zfill(3),topics[item[0]])) \
for item in best_topics ]) + "\n")
output.write("\nRepresentative words:\n")
output.write("\n".join([ ("[%.3f] %s" % (item[1], idxvocab[item[0]])) for item in best_words ]) + "\n")
output.write("\nSentence generation (greedy; argmax):" + "\n")
s = mgen.generate_on_doc(sess, doc, t, vocabxid[start_symbol], 0, cf.lm_sent_len+10, vocabxid[end_symbol])
output.write("[0] " + " ".join([ idxvocab[item] for item in s ]) + "\n")
for temp in gen_temps:
output.write("\nSentence generation (random; temperature = " + str(temp) + "):\n")
for i in xrange(gen_num):
s = mgen.generate_on_doc(sess, doc, t, vocabxid[start_symbol], temp, cf.lm_sent_len+10, \
vocabxid[end_symbol])
output.write("[" + str(i) + "] " + " ".join([ idxvocab[item] for item in s ]) + "\n")
print "Vocab size =", len(idxvocab)
if cf.num_classes > 0:
print "Class size (supervised) =", cf.num_classes
if cf.num_tags > 0:
print "Tag size =", cf.num_tags - 1
print_corpus_stats("Train corpus", train_sents, train_docs, train_stats)
print_corpus_stats("Valid corpus", valid_sents, valid_docs, valid_stats)
#train model
with tf.Graph().as_default(), tf.Session() as sess:
tf.set_random_seed(cf.seed)
initializer = tf.contrib.layers.xavier_initializer()
with tf.variable_scope("model", reuse=None, initializer=initializer):
tm_train = TM(is_training=True, vocab_size=len(idxvocab), batch_size=cf.batch_size, \
num_steps=cf.tm_sent_len, num_classes=num_classes, config=cf) if cf.topic_number > 0 else None
lm_train = LM(is_training=True, vocab_size=len(idxvocab), batch_size=cf.batch_size, \
num_steps=cf.lm_sent_len, config=cf, reuse_conv_variables=True) \
if cf.rnn_hidden_size > 0 else None
with tf.variable_scope("model", reuse=True, initializer=initializer):
tm_valid = TM(is_training=False, vocab_size=len(idxvocab), batch_size=cf.batch_size, \
num_steps=cf.tm_sent_len, num_classes=num_classes, config=cf) if cf.topic_number > 0 else None
lm_valid = LM(is_training=False, vocab_size=len(idxvocab), batch_size=cf.batch_size, \
num_steps=cf.lm_sent_len, config=cf) if cf.rnn_hidden_size > 0 else None
tf.initialize_all_variables().run()
#initialise word embedding
if cf.word_embedding_model:
word_emb = init_embedding(mword, idxvocab)
if cf.rnn_hidden_size > 0:
sess.run(lm_train.lstm_word_embedding.assign(word_emb))
if cf.topic_number > 0: