Created
February 20, 2019 07:04
-
-
Save huhuhang/0b4b3de032e51217fc72fb931c751707 to your computer and use it in GitHub Desktop.
文本预处理依次返回:字到序号映射字典、序号到字映射字典、数据集中全部单字、数据集全文。
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# *-* coding:utf-8 *-* | |
''' | |
modifed by ioiogoo | |
''' | |
def preprocess_file(path): | |
# 语料文本内容 | |
files_content = '' | |
with open(path, 'r',encoding='UTF-8') as f: | |
for line in f: | |
x = line.strip() + "]" | |
x = x.split(":")[1] | |
if len(x) <= 5 : | |
continue | |
if x[5] == ',': | |
files_content += x | |
words = sorted(list(files_content)) | |
counted_words = {} | |
for word in words: | |
if word in counted_words: | |
counted_words[word] += 1 | |
else: | |
counted_words[word] = 1 | |
# 去掉低频的字 | |
erase = [] | |
for key in counted_words: | |
if counted_words[key] <= 2: | |
erase.append(key) | |
for key in erase: | |
del counted_words[key] | |
wordPairs = sorted(counted_words.items(), key=lambda x: -x[1]) | |
words, _ = zip(*wordPairs) | |
words += (" ",) | |
# word到id的映射 | |
word2num = dict((c, i) for i, c in enumerate(words)) | |
num2word = dict((i, c) for i, c in enumerate(words)) | |
return word2num, num2word, words, files_content |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment