# @Time : 2021/3/11 15:20
# @Author : chao
# -*- coding: utf-8 -*-
import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.decomposition import LatentDirichletAllocation
def txt_to_df(txt):
cntVector = CountVectorizer()
cntTf = cntVector.fit_transform(txt)
lda = LatentDirichletAllocation(n_components=TOPIC_NUM,
learning_offset=50.,
random_state=0)
lda.fit_transform(cntTf)
lda_topics = lda.components_ / lda.components_.sum(axis=1)[:, np.newaxis]
topics = []
for topic_idx, topic in enumerate(lda_topics):
t = []
ll = list(map(lambda i : (cntVector.get_feature_names()[i], topic[i]), list(topic.argsort()[:-11:-1])))
for pair in ll:
t.append(pair[0] + ' ' + str(float('%.8f' % pair[1])))
topics.append(t)
df = pd.DataFrame(topics)
return df
###########################################################
FILE_TXT = r'C:\Users\\代码\数据\预处理后数据\baishi_data.txt'
FILE_WRITE = r'C:\Users\代码\主题提取\数据\baishi_lda.xlsx'
TOPIC_NUM = 1
with open(FILE_TXT, encoding='ANSI') as f:
text = f.readlines()
t = txt_to_df(np.array(text))
t.to_excel(FILE_WRITE)
(四)文本挖掘——LDA主题提取
最新推荐文章于 2024-06-05 10:16:39 发布