如何将特定的停用词字典(excel表格)导入Python,并将其附加到nltk停用词列表中?目前我的停用词部分看起来像这样:
# filter out stop words
from nltk.corpus import stopwords
stop_words = set(stopwords.words('english'))
words = [w for w in words if not w in stop_words]
提前感谢!
发布于 2018-06-13 07:43:59
您可以使用pandas
库导入excel工作表。此示例假设您的停用字位于第一列,每行一个字。然后,创建nltk
停用词和您自己的停用词的联合:
import pandas as pd
from nltk.corpus import stopwords
stop_words = set(stopwords.words('english'))
# check pandas docs for more info on usage of read_excel
custom_words = pd.read_excel('your_file.xlsx', header=None, names=['mywords'])
# union of two sets
stop_words = stop_words | set(custom_words['mywords'])
words = [w for w in words if not w in stop_words]
https://stackoverflow.com/questions/50794820
复制相似问题