代码拉取完成,页面将自动刷新
'''
英语单词词性还原
修改自https://github.com/rocketk/wordcounter
'''
'''
Copyright [rocketk]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
'''
import sys,re,collections,nltk
from nltk.stem.wordnet import WordNetLemmatizer
from nltk.tokenize import word_tokenize
from utils import costCount
# patterns that used to find or/and replace particular chars or words
# to find chars that are not a letter, a blank or a quotation
pat_letter = re.compile(r'[^a-zA-Z \']+')
# to find the 's following the pronouns. re.I is refers to ignore case
pat_is = re.compile("(it|he|she|that|this|there|here)(\'s)", re.I)
# to find the 's following the letters
pat_s = re.compile("(?<=[a-zA-Z])\'s")
# to find the ' following the words ending by s
pat_s2 = re.compile("(?<=s)\'s?")
# to find the abbreviation of not
pat_not = re.compile("(?<=[a-zA-Z])n\'t")
# to find the abbreviation of would
pat_would = re.compile("(?<=[a-zA-Z])\'d")
# to find the abbreviation of will
pat_will = re.compile("(?<=[a-zA-Z])\'ll")
# to find the abbreviation of am
pat_am = re.compile("(?<=[I|i])\'m")
# to find the abbreviation of are
pat_are = re.compile("(?<=[a-zA-Z])\'re")
# to find the abbreviation of have
pat_ve = re.compile("(?<=[a-zA-Z])\'ve")
lmtzr = WordNetLemmatizer()
@costCount
def standardizedWords(text):
'''
将单词转换为标准化的形式
'''
words_box=[]
words_box.extend(merge(replace_abbreviations(text).split()))
return ' '.join(words_box)
@costCount
def merge(words):
new_words = []
for word in words:
if word:
tag = nltk.pos_tag(word_tokenize(word)) # tag is like [('bigger', 'JJR')]
pos = get_wordnet_pos(tag[0][1])
if pos:
lemmatized_word = lmtzr.lemmatize(word, pos)
new_words.append(lemmatized_word)
else:
new_words.append(word)
return new_words
@costCount
def get_wordnet_pos(treebank_tag):
if treebank_tag.startswith('J'):
return nltk.corpus.wordnet.ADJ
elif treebank_tag.startswith('V'):
return nltk.corpus.wordnet.VERB
elif treebank_tag.startswith('N'):
return nltk.corpus.wordnet.NOUN
elif treebank_tag.startswith('R'):
return nltk.corpus.wordnet.ADV
else:
return ''
@costCount
def replace_abbreviations(text):
new_text = text
new_text = pat_letter.sub(' ', text).strip().lower()
new_text = pat_is.sub(r"\1 is", new_text)
new_text = pat_s.sub("", new_text)
new_text = pat_s2.sub("", new_text)
new_text = pat_not.sub(" not", new_text)
new_text = pat_would.sub(" would", new_text)
new_text = pat_will.sub(" will", new_text)
new_text = pat_am.sub(" am", new_text)
new_text = pat_are.sub(" are", new_text)
new_text = pat_ve.sub(" have", new_text)
new_text = new_text.replace('\'', ' ')
return new_text
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。