import pandas as pd
import numpy
import jieba
import os
#查看修改路径
os.getcwd()
os.chdir(r"C:\Users\zcfemail\0.Python\4.python课程学习\2.文本分析")
#导入原资料
df_txt=pd.read_table(r'C:\Users\zcfemail\Desktop\aaa.txt',names=['content'], encoding='utf-8')
#删除空值,并转化为列表
df_txt=df_txt.dropna() #删除空值
# df_content=df_txt["content"].tolist() # 所有内容转化为了列表
content=df_txt.content.values.tolist() #每行内容转化为列表
#进行初步分词
content_s=[]
for line in content:
current_segment=jieba.lcut(line)
if len(current_segment)>1 and current_segment!='\t\r\n':
content_s.append(current_segment)
#分词结果转化为 数据框
df_content=pd.DataFrame({'content_s':content_s})
df_content.head()
#导入停用词
stopwords=pd.read_table(r".\stopwords.txt",index_col=False,sep='\t',quoting=3,names=['stopword'], encoding='utf-8')
#自定义清理停用词函数
def drop_stopwords(contents,stopwords):
contents_clean=[]
all_words=[]
for line in contents:
line_clean=[]
for word in line:
if word in stopwords:
continue
line_clean.append(word)
all_words.append(str(word))
contents_clean.append(line_clean)
return contents_clean,all_words
#清理后的词频
contents=df_content.content_s.values.tolist()
stopwords = stopwords.stopword.values.tolist()
contents_clean,all_words = drop_stopwords(contents,stopwords)
# 清理后的词频列表和所有汇总词频转化为数据框
df_content_clean=pd.DataFrame({'contents_clean':contents_clean})
df_all_words=pd.DataFrame({'all_words':all_words})
### 画词云图,构建所有词频
words_count=df_all_words.groupby(by=['all_words'])['all_words'].agg({"count":numpy.size})
words_count=words_count.reset_index().sort_values(by=["count"],ascending=False)
# 词云图
from wordcloud import WordCloud
import matplotlib.pyplot as plt
%matplotlib inline
import matplotlib
matplotlib.rcParams['figure.figsize']=(10.0,5.0)
wordcloud=WordCloud(font_path="./data/simhei.ttf",background_color="white",max_font_size=80)
word_frequence = {x[0]:x[1] for x in words_count.head(300).values}
wordcloud=wordcloud.fit_words(word_frequence)
plt.imshow(wordcloud)
# 每一列提取主要关键词
import jieba.analyse
import numpy as np
#index = 0
for index in np.arange(6):
print (df_txt['content'][index])
content_S_str = "".join(content_s[index])
print (" ".join(jieba.analyse.extract_tags(content_S_str, topK=5, withWeight=False)))
print("\n")
#全篇文章提出关键词
content_new=[]
for index in np.arange(6):
content_new.append(df_txt['content'][index])
content_new=''.join(content_new)
print (" ".join(jieba.analyse.extract_tags(content_new, topK=10)))
print("\n")