问LDA模型中“好”/“坏”-Cases的规定(在Python中使用gensim )

EN

import os, csv

#create list with text blocks in rows, based on csv file
list=[]

with open('Testfile.csv', 'r') as csvfile:
    emails = csv.reader(csvfile)
    for row in emails:
         list.append(row)

#create doc_set
doc_set=[]

for row in list:
    doc_set.append(row[0])

#import plugins - need to install gensim and stop_words manually for fresh python install
from nltk.tokenize import RegexpTokenizer
from stop_words import get_stop_words
from nltk.stem.porter import PorterStemmer
from gensim import corpora, models
import gensim

tokenizer = RegexpTokenizer(r'\w+')

# create English stop words list
en_stop = get_stop_words('en')

# Create p_stemmer of class PorterStemmer
p_stemmer = PorterStemmer()


# list for tokenized documents in loop
texts = []

# loop through document list
for i in doc_set:

    # clean and tokenize document string
    raw = i.lower()
    tokens = tokenizer.tokenize(raw)

    # remove stop words from tokens
    stopped_tokens = [i for i in tokens if not i in en_stop]

    # stem tokens
    stemmed_tokens = [p_stemmer.stem(i) for i in stopped_tokens]

    # add tokens to list
    texts.append(stemmed_tokens)


# turn our tokenized documents into a id <-> term dictionary
dictionary = corpora.Dictionary(texts)

# convert tokenized documents into a document-term matrix
corpus = [dictionary.doc2bow(text) for text in texts]

# generate LDA model
ldamodel = gensim.models.ldamodel.LdaModel(corpus, num_topics=5, id2word = dictionary, passes=10)

print(ldamodel.print_topics(num_topics=5, num_words=5))

# map topics to documents
doc_lda=ldamodel[corpus]

with open('doc_lda.csv', 'w') as outfile:
    writer = csv.writer(outfile)
    for row in doc_lda:
        writer.writerow(row)