Commit 6473bd2b49191a183b240905442ecb9b7eafd0dd - poetry - (('Mo Repos',), {'htdigest_file': None, 'use_smarthttp': 0, 'require_browser_auth': 0, 'disable_push': 0, 'unauthenticated_push': 0, 'ctags

yangsaisai 7 years ago

3 changed file(s) with 39 addition(s) and 4 deletion(s). Raw diff Collapse all Expand all

+35

-0

.ipynb_checkpoints/rhyme_helper-checkpoint.py less more

	0
	1	class RhymeWords():
	2	rhyme_list = []
	3
	4	@staticmethod
	5	def read_rhyme_words(infile):
	6	with open(infile,'r',encoding='utf-8',errors='ignore') as fr:
	7	for line in fr:
	8	words = set(line.split())
	9	RhymeWords.rhyme_list.append(words)
	10
	11	@staticmethod
	12	def get_rhyme_words(w):
	13	for words in RhymeWords.rhyme_list:
	14	if w in words:
	15	return words
	16	return None
	17
	18	@staticmethod
	19	def print_stats():
	20	count = 0
	21	for words in RhymeWords.rhyme_list:
	22	count += len(words)
	23	print(words)
	24
	25	for w in words:
	26	if len(w) > 1:
	27	print(w)
	28
	29	print('count = ',count)
	30
	31	if __name__ == '__main__':
	32	infile = './data/poem/rhyme_words.txt'
	33	RhymeWords.read_rhyme_words(infile)
	34	RhymeWords.print_stats()⏎

-2

.ipynb_checkpoints/word2vec_helper-checkpoint.py less more

28	28
29	29
30	30	if __name__ == '__main__':
31		# w2vpath = './corpus/vectors_xhj_shj.bin' #分字
32		w2vpath = './corpus/vectors_qa_word.bin' #分词
	31	# w2vpath = './corpus/vectors_xhj_shj.bin' # 分字
	32	w2vpath = './corpus/vectors_qa_word.bin' # 分词
33	33
34	34	w2v = Word2Vec(w2vpath)
35	35	with open( './corpus/vocab_word.txt','w',encoding='utf-8') as fw:

-2

word2vec_helper.py less more

28	28
29	29
30	30	if __name__ == '__main__':
31		# w2vpath = './corpus/vectors_xhj_shj.bin' #分字
32		w2vpath = './corpus/vectors_qa_word.bin' #分词
	31	# w2vpath = './corpus/vectors_xhj_shj.bin' # 分字
	32	w2vpath = './corpus/vectors_qa_word.bin' # 分词
33	33
34	34	w2v = Word2Vec(w2vpath)
35	35	with open( './corpus/vocab_word.txt','w',encoding='utf-8') as fw: