python绘制词云图（已知词频以及未知词频）_python 词频图

1.词云图（已知词频）

1.1不加背景图层

1.1.1原始数据

1.1.2程序

import pandas as pd
from wordcloud import WordCloud
from matplotlib import pyplot as plt

pd.set_option('display.float_format', lambda x: '%.4f' % x) # 取消科学计数法
data=pd.read_excel('./GDP.xlsx',sheet_name='2021',usecols=['国家/地区','GDP总量(人民币核算)'])
print(data.head())
list_country=data['国家/地区'].tolist()
list_gdp=data['GDP总量(人民币核算)'].tolist()
dic=dict(zip(list_country,list_gdp))
print(dic)

font=r'C:\Windows\Fonts\simhei.ttf'
wordcloud=WordCloud(background_color='black',width=800,height=800,margin=1,font_path=font).generate_from_frequencies(dic)
plt.imshow(wordcloud)
plt.axis('off')
plt.show()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17

1.1.3效果

1.2加背景图层

1.2.1原始数据

1.2.2程序

import pandas as pd
import numpy as np
from wordcloud import WordCloud
from matplotlib import pyplot as plt
from PIL import Image

pd.set_option('display.float_format', lambda x: '%.4f' % x) # 取消科学计数法
data=pd.read_excel('./GDP.xlsx',sheet_name='2021',usecols=['国家/地区','GDP总量(人民币核算)'])
print(data.head())
list_country=data['国家/地区'].tolist()
list_gdp=data['GDP总量(人民币核算)'].tolist()
dic=dict(zip(list_country,list_gdp))
print(dic)

font=r'C:\Windows\Fonts\simhei.ttf'
MASK=np.array(Image.open('./rmb.jpg'))
wordcloud=WordCloud(background_color='white',scale=1,max_words=500,max_font_size=100,font_path=font,mask=MASK,repeat=False,mode='RGB',colormap='winter').generate_from_frequencies(dic)
plt.imshow(wordcloud,interpolation='bilinear')
plt.axis('off')
plt.show()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20

1.2.3效果

2.词云图(未知词频)

2.1不加背景图层

2.1.1原始数据

2.1.2程序

import re
import jieba
import pandas as pd
from wordcloud import WordCloud
from matplotlib import pyplot as plt

text=pd.read_csv('zfgzbg.txt',index_col=0)
print(text)
text2=str(text)
# 去除特殊字符、数字和字母，只保留汉字
text3=re.sub("[a-zA-Z0-9'!""#$%&\'()*+,-./:;<=>?@，。?★、…【】《》：？“”‘'！[\\]^_`{|}~\s]+","",text2)
print(text3)
text4=jieba.lcut(text3)
print(text4)
text5=' '.join(text4)
print(text5)

# 暂时列举以下停用词，可根据实际需要进行补充删改
stopwords=['我','和','你','的','地','得','了','都','对','向','在','可','能','为','要','再','是','等','一','二','三','四','五','六','七','八','九','十','各位','代表','一年','请予']
font=r'C:\Windows\Fonts\simhei.ttf'
wordcloud=WordCloud(background_color='white',scale=1,max_words=500,max_font_size=100,font_path=font,stopwords=stopwords).generate_from_text(text5)
plt.imshow(wordcloud,interpolation='bilinear')
plt.axis('off')
plt.show()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

2.1.3效果

2.2加背景图层

2.2.1原始数据

2.2.2程序

import re
import jieba
import pandas as pd
import numpy as np
from PIL import Image
from wordcloud import WordCloud
from matplotlib import pyplot as plt

text=pd.read_csv('zfgzbg.txt',index_col=0)
print(text)
text2=str(text)
# 去除特殊字符、数字和字母，只保留汉字
text3=re.sub("[a-zA-Z0-9'!""#$%&\'()*+,-./:;<=>?@，。?★、…【】《》：？“”‘'！[\\]^_`{|}~\s]+","",text2)
print(text3)
text4=jieba.lcut(text3)
print(text4)
text5=' '.join(text4)
print(text5)

# 暂时列举以下停用词，可根据实际需要进行补充删改
stopwords=['我','和','你','的','地','得','了','都','对','向','在','可','能','为','要','再','是','等','一','二','三','四','五','六','七','八','九','十','各位','代表','一年','请予']
font=r'C:\Windows\Fonts\simhei.ttf'
MASK=np.array(Image.open('./map.jpg'))
wordcloud=WordCloud(background_color='white',scale=2,max_words=500,max_font_size=150,font_path=font,stopwords=stopwords,mask=MASK,colormap='brg').generate_from_text(text5)
plt.imshow(wordcloud,interpolation='bilinear')
plt.axis('off')
plt.show()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

2.2.3效果