Word cloud graph, word frequency graph, specially statistics the word cloud word frequency of some keywords

# 1. Read the text , And use jieba In the library cut() Function for word segmentation 
import jieba
import random
report = open('1.txt','r').read()
words = jieba.cut(report)

# 2. adopt for Loop statement extract list words The middle length is greater than or equal to 4 A word 
report_words = []
for word in words: # Make the length greater than or equal to 4 Put words in the list 
    if len(word) >= 2 and word in [' autonomous ',' Rule of virtue ',' The rule of law ', ' Three treatments ', ' data ', ' Rural revitalization ', ' a farmer ', ' rural ' ,' Agriculture ', ' Governance ',  ' rural ' ,' urban and rural ' ,' Numbers ',' Governance system ']:
        report_words.append(word)
for i in range(0,report.count(' Rural revitalization ')):
    report_words.append(' Rural revitalization ')
for i in range(0,report.count(' Governance ')):
    report_words.append(' Governance ')
for i in range(0,report.count(' Governance system ')):
    report_words.append(' Governance system ')
random.shuffle(report_words)
#print(report_words)

# # 3. Get the number of occurrences of high-frequency words printed out 
# from collections import Counter
# result = Counter(report_words).most_common(50) # Take the most 50 Group 
# #print(result)

# 4. Draw a cloud of words 
from wordcloud import WordCloud # Import related libraries 
content = ' '.join(report_words) # Convert list to string 
wc = WordCloud(
                background_color='pink',
                
                font_path=r"C:\\Windows\\Fonts\\msyh.ttc"
                ).generate(content)
image_produce = wc.to_image()
# # # wordcloud.to_file("new_wordcloud.jpg")
# # image_produce.show()

# # wc.to_file(' Clouds of words .png') # Export to PNG Format picture （ Using relative paths ）

import jieba
import pandas as pd
import numpy as np
import PIL.Image as image
from wordcloud import WordCloud
import matplotlib.pyplot as plt
with open("1.txt", "r",encoding='gbk') as f:  #  Open file 
    texts = f.read()  #  Read the file 
    
print(texts)
texts=texts.replace(' the people ','').replace(' socialist ','').replace(' social ','').replace(' Country ','')
# Clouds of words 
content=[]
words=jieba.lcut(texts)
for word in words:
    if len(word)>1:
        content.append(word)

contents=" ".join(content)
wordcloud = WordCloud(
background_color='pink',
font_path=r"C:\\Windows\\Fonts\\msyh.ttc"
).generate(contents)
image_produce = wordcloud.to_image()
# wordcloud.to_file("new_wordcloud.jpg")
image_produce.show()
plt.imshow(wordcloud)

# Top ten keywords with the highest frequency 
import jieba.analyse
content_str=contents
print(" ".join(jieba.analyse.extract_tags(content_str,topK=20,withWeight=(False))))#topK Number of keywords 

import jieba
content = open('2.txt', 'r', encoding='gbk').read()
#txt It is a text file for statistical word cloud 

# content=content.replace(' the people ','').replace(' socialist ','').replace(' social ','').replace(' Country ','').replace(' China ','').replace(' In our country ','')

# words = jieba.lcut(content)
# counts = {}
# for word in words:
# if len(word) == 1: #  Exclude word segmentation results of single words 
# continue
# else:
# counts[word] = counts.get(word, 0) + 1 # dict usage 
# hist = list(counts.items()) #  Form a list 
# hist.sort(key=lambda x: x[1], reverse=True)
# words=[]
# counts=[]
# for i in range(20): #  Output high frequency front 20 Word 
# word, count = hist[i]
# words.append(word)
# counts.append(count)
# print(counts)
# print(words)
import random

import jieba
import pandas as pd
import numpy as np
import PIL.Image as image
from wordcloud import WordCloud
import matplotlib.pyplot as plt
words=[' autonomous ',' Rule of virtue ',' The rule of law ', ' Three treatments ', ' data ', ' Rural revitalization ', ' a farmer ', ' rural ' ,' Agriculture ', ' Governance ',  ' rural ' ,' urban and rural ' ,' Numbers ',' Governance system ']
counts=[]
for i in words:
    num=content.count(i)
    counts.append(num)
print(counts)
x_data = words
y_data = counts

contents=" ".join(words)
wordcloud = WordCloud(
background_color='pink',
font_path=r"C:\\Windows\\Fonts\\msyh.ttc"
).generate(contents)
image_produce = wordcloud.to_image()
# import matplotlib.pyplot as plt
 
# plt.rcParams["font.sans-serif"]=['SimHei']
# plt.rcParams["axes.unicode_minus"]=False
 
# for i in range(len(x_data)):
# plt.bar(x_data[i],y_data[i])
 
# plt.title(" Word frequency display ")
# plt.xlabel(" Word frequency ")
# plt.ylabel(" Number ")
 
# plt.show()