python+jieba+wordcloud实现超酷的词云_jieba分词后如何使用jupyter输出

环境准备
pip 安装jieba库,wordcloud库与scipy库
资料准备

• 用于分词的文本:词频统计_AIjob.csv
• 禁止统计词库:stopwords.txt
• 自定义分词库:人工智能词汇.txt
• 掩膜用的形状图片:mask.jpg

不废话,直接上码

1.用结巴分词,生成字典对象

import jieba
from collections import Counter
import wordcloud
# 读取文件
with open("词频统计_AIjob.csv", "r", encoding="utf-8") as f:
    desc = f.read()

# 加载停用词列表
stop_words = []
with open("stopwords.txt", "r",encoding='utf-8') as f:
    for line in f:
        stop_words.append(line.strip())

jieba.load_userdict("人工智能词汇.txt")
# 分词
words = jieba.cut(desc, cut_all=False)
# 过滤停用词
filtered_words = []
for word in words:
    if word not in stop_words and len(word) > 1:
        filtered_words.append(word)

# 统计词频
word_counts = Counter(filtered_words)

w100=word_counts.most_common(500)
# 使用字典推导将列表转换为字典  
dict_result = {key: value for key, value in w100} 
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
28

用wordcloud 生成词云

from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
from scipy.ndimage import gaussian_gradient_magnitude
from wordcloud import WordCloud, ImageColorGenerator
def pic_wordcloud(dict_result,img_path,out_path):

    
    # img_path=r"E:\jupyter\spyder\bosszhipin\词频统计\pic\T1.jpg"
    
    parrot_color = np.array(Image.open(img_path))
    
    parrot_color = parrot_color[::3, ::3]
    
    # create mask  white is "masked out"
    parrot_mask = parrot_color.copy()
    parrot_mask[parrot_mask.sum(axis=2) == 0] = 255
    
    
    edges = np.mean([gaussian_gradient_magnitude(parrot_color[:, :, i] / 255., 2) for i in range(3)], axis=0)
    parrot_mask[edges > .08] = 255
    
    
    # acurately but it makes a better picture
    wc = WordCloud(max_words=1000, mask=parrot_mask, max_font_size=40, random_state=42, font_path=r"C:\Users\10921\AppData\Local\Microsoft\Windows\Fonts\方正正准黑简体.ttf",relative_scaling=0,
                   #width=1920, height=1080
                   )
    
    # generate word cloud
    wc.generate_from_frequencies(dict_result)
    # plt.imshow(wc)
    
    # create coloring from image
    image_colors = ImageColorGenerator(parrot_color)
    wc.recolor(color_func=image_colors)
    # plt.figure(figsize=(10, 10))
    # plt.imshow(wc, interpolation="bilinear")
    # wc.to_file("parrot_new.png")
    wc.to_file(out_path)
img_path="mask.jpg"
out_path='output.png'
pic_wordcloud(dict_result,img_path,out_path)
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
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42