Python:如何繪製文字雲? from wordcloud import WordCloud

# -*- coding: utf-8 -*-
"""
Created on Mon Jan 15 06:30:23 2024

@author: SavingKing
"""

import os
import json
import jieba
import numpy as np

folder = r"D:\Python code\240107_爬蟲"
fname = "my_lis_msg_backup.json"

fpath = os.path.join(folder,fname)
#'D:\\Python code\\240107_爬蟲\\my_lis_msg.json'

with open(fpath,"r",encoding="UTF-8") as f:
    dic = json.load(f)

k0 = list(dic.keys())[0]

lis = dic[k0]
lis2D = []
for strr in lis:
    lis_jieba = jieba.lcut(strr)
    lis2D.append(lis_jieba)

lenN = len( lis2D )
#951

lis2D_flatten = []
for ele in lis2D:
    lis2D_flatten.extend(ele)
#len = 9051
rm = [ '，', '。', '、', '；', '：', '“', '”', '？', '！', '（', '）', '《', '》', '...', 
    '的', '是', '在', '有', '和', '也', '了', '不', '人', '我', '他', '之', '為', '與', 
    '大', '來', '到', '上', '就', '很', '個', '去', '而', '要', '會', '可以', '你', 
    '對', '着', '還', '但', '年', '這', '那', '得', '着', '中', '一個',' ', '/', '\n','.'
    '都','元','喔','說','沒',"1","2","4","7","(",")", "?","=", "+", ",",",","...","吧","才"
    # 可以繼續添加更多的詞
    ]

for strr in rm:
    if strr in lis2D_flatten:
        while strr in lis2D_flatten:
            lis2D_flatten.remove(strr)

dic_term_freq = {}

for term in lis2D_flatten:
    if term in dic_term_freq:
        dic_term_freq[term] += 1/len(lis2D_flatten)
    else:
        dic_term_freq[term] = 1/len(lis2D_flatten)

print("dic_term_freq:",dic_term_freq)
#出現最多的是那些詞? 詞頻多少?
max_count = max(dic_term_freq.values())

lis_max_count=[]
for k in dic_term_freq:
    if dic_term_freq[k] == max_count:
        lis_max_count.append(k)
print("max_count:",max_count)
print("lis_max_count:",lis_max_count)
#若沒有事先去掉不重要的詞
#lis_max_count: ['，']
#詞頻最高的是 不重要的標點符號
#使用IDF過濾

set_lis2D_flatten  = set(lis2D_flatten )
#去掉重複的詞,節省for迴圈次數

dic_IDF = {}
for strr in set_lis2D_flatten:
    cnt= 0 
    for i in range(lenN):
        if strr in lis2D[i]:
            cnt+=1
    
    idf = np.log(lenN/cnt)
    dic_tmp = {strr:idf}
    dic_IDF.update(dic_tmp)
    
max_IDF = max(dic_IDF.values())
lis_max_IDF = []
for word in dic_IDF:
    if dic_IDF[word] == max_IDF:
        lis_max_IDF.append(word)

# =============================================================================
# print("max_IDF:",max_IDF)
# print("lis_max_IDF:",lis_max_IDF)
# =============================================================================
    
dic_TFxIDF = {}
for word in dic_IDF.keys():
    tf = dic_term_freq [word]
    idf = dic_IDF [word]
    dic_tmp = {word:tf*idf}
    dic_TFxIDF.update(dic_tmp)
    
max_TFxIDF = max(dic_TFxIDF.values())
lis_max_TFxIDF = []
for word in dic_TFxIDF:
    if dic_TFxIDF[word] == max_TFxIDF:
        lis_max_TFxIDF.append(word)

print("max_TFxIDF:",max_TFxIDF)

#生成文字雲
from wordcloud import WordCloud
import matplotlib.pyplot as plt

# 創建一個文字雲實例
wordcloud = WordCloud(
    width = 800,  # 宽度
    height = 800,  # 高度
    background_color ='white',  # 背景颜色
    min_font_size = 10,  # 最小字體大小
    font_path='C:\\Windows\\Fonts\\kaiu.ttf' #標楷體
) #type: wordcloud.wordcloud.WordCloud

# 生成文字雲
wordcloud.generate_from_frequencies(dic_TFxIDF)

# 可視化顯示
plt.figure(figsize = (8, 8), facecolor = None)
#8 inchs = 8*2.54cm = 20.32 cm
plt.imshow(wordcloud)
plt.axis("off")  # 關閉座標軸
# plt.tight_layout(pad = 0)
plt.show()