wordcloud词云库

生成的词云默认长 400，高200

 

新时代中国特色社会主义词云：

###词库默认不支持中文，要设置字体

import jieba
import wordcloud
from scipy.misc import imread

#读取文本内容
f = open('新时代中国特色社会主义.txt','rb')
txt = f.read()
f.close()

#处理成一个个词汇
ls = jieba.lcut(txt)
txt = ' '.join(ls)

#词云生成
mask = imread("11.ico")
w = wordcloud.WordCloud(background_color = 'white',
                        width = 1000,height = 700,
                        font_path = 'msyh.ttc',
                        mask = mask,max_words = 15)
w.generate(txt)
w.to_file('china.png')

 

词云颜色为灰色

import jieba
import wordcloud
from scipy.misc import imread
import pandas as pd

import random
def grey_color_func(word, font_size, position, orientation, random_state=None,
                    **kwargs):
    return "hsl(30, 0%%, %d%%)" % random.randint(90, 160)

 
#读取 csv 内容
df = pd.read_csv('jd_生日礼物男.csv',encoding='utf-8')
names_txt = list(df['商品名'])
txt = ''.join(names_txt)

 
#处理成一个个词汇
ls = jieba.lcut(txt)
txt = ' '.join(ls)
 
#词云生成
mask = imread("gift.jpg")
w = wordcloud.WordCloud(background_color = 'white',
                        width = 1000,height = 700,
                        font_path = 'msyh.ttc',mask=mask,
                       )
w.generate(txt)

import matplotlib.pyplot as plt
plt.imshow(w.recolor(color_func=grey_color_func, random_state=3),
           interpolation="bilinear")

w.to_file('gift_girl.png')

 

importError: cannot import name 'imread' from 'scipy.misc'

https://blog.csdn.net/AndyTsui/article/details/90759927

 

次数数量统计类型为 Series

import matplotlib.pyplot as plt
from wordcloud import WordCloud

frequencies = result.groupby(by = ['word'])['word'].count()
frequencies = frequencies.sort_values(ascending = False)
backgroud_Image=plt.imread('../data/pl.jpg')
wordcloud = WordCloud(font_path="msyh.ttc",
                      max_words=100,
                      background_color='white',
                      mask=backgroud_Image)
my_wordcloud = wordcloud.fit_words(frequencies)
plt.imshow(my_wordcloud)
plt.axis('off')
plt.show()

# 将结果写出
my_wordcloud.to_file('../tem/wordcloud.png')
result.to_csv("../tem/word.csv", index = False, encoding = 'utf-8')