1463f45807433d3d7ca110ee0eed012bd58e1418,data.py,,create_words_file,#Any#Any#,7

Before Change

	words = []
	normalizer = Normalizer()
	stemmer = Stemmer(words_file=None)
	words_file = codecs.open(output, "w", "utf8")
	for line in codecs.open(dic_file, encoding="utf8"):
		word = line.split("\t")[0]
		words.append(normalizer.normalize(word))

	word_set = set(words + list(stemmer.tenses.values()))
	for word in words:
		stem = stemmer.stem(word)
		if stem == word or stem not in word_set:
			print(word, file=words_file)

	print(output, "created")


def create_verbs_file(valency_file="resources/valency.txt", output="data/verbs.dat"):

After Change

	

	dic_words = [line.split("\t")[0] for line in codecs.open(dic_file, encoding="utf8")]
	print(*dic_words, sep="\n", file=codecs.open(output, "w", "utf8"))
	print(output, "created")


def create_verbs_file(valency_file="resources/valency.txt", output="data/verbs.dat"):

Instances