from nltk.tokenize import RegexpTokenizer
#from stop_words import get_stop_words
from gensim import corpora, models
import gensim
import os
from os import path
from time import sleep
filename_2 = "buisness1.txt"
file1 = open(filename_2, encoding='utf-8')
Reader = file1.read()
tdm = []
# Tokenized the text to individual terms and created the stop list
tokens = Reader.split()
#insert stopwords files
stopwordfile = open("StopWords.txt", encoding='utf-8')
# Use this to read file content as a stream
readstopword = stopwordfile.read()
stop_words = readstopword.split()
for r in tokens:
if not r in stop_words:
#stopped_tokens = [i for i in tokens if not i in en_stop]
tdm.append(r)
dictionary = corpora.Dictionary(tdm)
corpus = [dictionary.doc2bow(i) for i in tdm]
sleep(3)
#Implemented the LdaModel
ldamodel = gensim.models.ldamodel.LdaModel(corpus, num_topics=10, id2word = dictionary)
print(ldamodel.print_topics(num_topics=1, num_words=1))
我正在尝试使用一个单独的包含停止字的txt文件来删除停止字。在我删除了停止词之后,我会添加文本文件中不在停止词中的单词。我在dictionary = corpora.Dictionary(tdm)
处得到错误doc2bow expects an array of unicode tokens on input, not a single string
。
有人能帮我更正我的代码吗
这几乎肯定是重复的,但请使用以下内容:
dictionary = corpora.Dictionary([tdm])