python绘图

一、绘制词云图并统计词频

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba
import csv
import matplotlib.colors as colors
with open(".\\data\\百度文库爬取内容01.txt","r",encoding="utf-8") as f:
    txt=f.read()#返回一个字符串
#自定义颜色
color=colors.ListedColormap(["#000000","#00FF00","#0000FF","#FF0000"])
wd = WordCloudloud(width=1000,#指定词云对象生成图片的宽度,默认400像素
    font_path="C:\Windows\Fonts\simkai.ttf",  #设置字体格式，不然会乱码
    background_color="black",  #设置背景颜色
    mask=plt.imread(".\\data\\background_image.jpeg "),#设置背景图,默认是矩形
              height=700, #指定词云图片的背景颜色，默认为黑色
               stopwords="I a",#指定词云的排除词列表，即不显示的单词列表
               #colormap=color
               )
wd.generate(" ".join(jieba.lcut(txt)))#以空格为分隔符将列表中的所有元素合并成一个新的字符串
print("".join(jieba.lcut(txt)))
#保存词云图
wd.to_file('.\\data\\zhu.png')
#显示词云图
plt.imshow(wd,interpolation="bilinear")
plt.axis("off")
plt.show()
#
# #####################################################
# 使用可以使用sklearn中的CountVectorizer统计词频
from sklearn.feature_extraction.text import CountVectorizer
# 使用CountVectorizer统计词频
cv = CountVectorizer()
contents_count = cv.fit_transform([" ".join(jieba.lcut(txt))])
# 词有哪些
list1 = cv.get_feature_names()
# 词的频率
list2 = contents_count.toarray().tolist()[0]
# 将词与频率一一对应
contents_dict = dict(zip(list1, list2))
# 输出csv文件,newline=""，解决输出的csv隔行问题
with open(".\\data\\caifu_output.csv", 'w', newline="") as f:
    writer = csv.writer(f)
    for key, value in contents_dict.items():
        writer.writerow([key, value])
#
# ###############################################################
# #统计单词出现的频率
import csv
import jieba
import re
with open(".\\data\\百度文库爬取内容01.txt","r",encoding="utf-8") as f:
    txt=f.readlines()
dic={}
for line in txt:
    txt=re.sub("[^\u4e00-\u9fa5^a-z^A-Z^0-9]","",line)
    words=jieba.lcut(line)
    for word in words:
        if word in dic.keys():
            dic[word]+=1
        else:
            dic[word]=1
with open(".\\data\\词频统计.csv","w",newline="",encoding='utf-8') as file:
    writer=csv.writer(file)
    for key,value in dic.items():
        writer.writerow([key,value])
##############################