NLP情感分析和可视化|python实现评论内容的文本清洗、语料库分词、去除停用词、建立TF-IDF矩阵、获取主题词和主题词团_评论文本清洗

1 文本数据准备

首先文本数据准备，爬取李佳琦下的评论，如下：

 2 提出文本数据、获得评论内容

#内容读取
import xlrd
import pandas as pd
 
wb=xlrd.open_workbook("评论数据.xlsx")
sh=wb.sheet_by_index(0)
col=sh.ncols
row=sh.nrows
Text=[]
for i in range(row):
    Text_Context=sh.row_values(i,1,2)[0]
    Text.append(Text_Context)
del Text[0]
print(Text)

2 进行结巴分词、去除停用词，得到词料

#结巴分词
import jieba
import gensim
#停用词处理
 
import spacy
from spacy.lang.zh.stop_words import STOP_WORDS
 
sent_words = []
for sent0 in Text:
    try:
        l=list(jieba.cut(sent0))
        # print(l)
        filtered_sentence = []
        for word in l:
            if word not in STOP_WORDS:
                filtered_sentence.append(word)
        sent_words.append(filtered_sentence)
        # print( filtered_sentence)
    except:
        pass
print(sent_words)
document = [" "

3 生成TF-IDF矩阵：获取逆文档高频词

from sklearn import feature_extraction
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
 
tfidf_model = TfidfVectorizer().fit(document)
# 得到语料库所有不重复的词
feature = tfidf_model.get_feature_names()
print(feature)
# 得到每个特征对应的id值：即上面数组的下标
print(tfidf_model.vocabulary_)
 
# 每一行中的指定特征的tf-idf值：
sparse_result = tfidf_model.transform(document)
 
# 每一个语料中包含的各个特征值的tf-idf值：
# 每一行代表一个预料，每一列代表这一行代表的语料中包含这个词的tf-idf值，不包含则为空
weight = sparse_result.toarray()
 
# 构建词与tf-idf的字典：
feature_TFIDF = {}
for i in range(len(weight)):
    for j in range(len(feature)):
        # print(feature[j], weight[i][j])
        if feature[j] not in feature_TFIDF:
            feature_TFIDF[feature[j]] = weight[i][j]
        else:
            feature_TFIDF[feature[j]] = max(feature_TFIDF[feature[j]], weight[i][j])
# print(feature_TFIDF)
 
# 按值排序：
print('TF-IDF 排名前十的(TF-IDF>1时)：')
featureList = sorted(feature_TFIDF.items(), key=lambda kv: (kv[1], kv[0]), reverse=True)
for i in range(10):
    print(featureList[i][0], featureList[i][1])
 
k=0
m=0
print('TF-IDF 排名前十的(TF-IDF<1时)：')
while k<=10:
    if featureList[m][1]<1:
        k+=1
        print(featureList[m][0], featureList[m][1])
    m+=1

4 结果：

5 画图

#!/usr/bin/python
# -*- coding:utf-8 -*-
 
from gensim import corpora
from gensim.models import LdaModel
from gensim.corpora import Dictionary
#内容读取
import xlrd
import pandas as pd
from gensim import corpora
from collections import defaultdict
import spacy
from spacy.lang.zh.stop_words import STOP_WORDS
#结巴分词
import jieba
import gensim
#停用词处理
 
wb=xlrd.open_workbook("评论数据.xlsx")
sh=wb.sheet_by_index(0)
col=sh.ncols
row=sh.nrows
Text=[]
for i in range(row):
    Text_Context=sh.row_values(i,1,2)[0]
    Text.append(Text_Context)
del Text[0]
print(Text)
 
file1 = open('结巴分词结果.txt','w')
 
sent_word = []
for sent0 in Text:
    try:
        l=list(jieba.cut(sent0))
        sent_word.append(l)
        # print( filtered_sentence)
    except:
        pass
 
for s in sent_word:
    try:
        for w in s:
            file1.write(str(w))
        file1.write('\n')
    except:
        pass
 
file1.close()
sent_words=[]
for l in sent_word:
    filtered_sentence=[]
    for word in l:
        if word not in STOP_WORDS:
            filtered_sentence.append(word)
    sent_words.append(filtered_sentence)
 
file2 = open('去除停用词后的结果.txt','w')
for s in sent_word:
    for w in s:
        file1.write(w)
    file2.write('\n')
file2.close()
 
dictionary = corpora.Dictionary(sent_words)
corpus = [dictionary.doc2bow(text) for text in sent_words]
lda = LdaModel(corpus=corpus, id2word=dictionary, num_topics=20, passes=60)
# num_topics：主题数目
# passes：训练伦次
# num_words：每个主题下输出的term的数目
 
file3=open("tf-idf值.txt",'w')
 
for topic in lda.print_topics(num_words = 20):
    try:
        termNumber = topic[0]
        print(topic[0], ':', sep='')
        file3.write(str(topic[0])+':'+''+'\n')
        listOfTerms = topic[1].split('+')
        for term in listOfTerms:
            listItems = term.split('*')
            print('  ', listItems[1], '(', listItems[0], ')', sep='')
            file3.write('  '+str(listItems[1])+ '('+str(listItems[0])+ ')',+''+ '\n')
    except:
        pass
import pyLDAvis.gensim
 
d=pyLDAvis.gensim.prepare(lda, corpus, dictionary)
 
'''
lda: 计算好的话题模型
corpus: 文档词频矩阵
dictionary: 词语空间
'''
 
pyLDAvis.save_html(d, 'lda_pass10.html')
# pyLDAvis.displace(d) #展示在notebook的output cell中
 

6 结果展示