python | 数据可视化 词云

python | 数据可视化 词云

直接丢代码：

import matplotlib.pyplot as plt
import matplotlib.colors as colors  # 处理图片相关内容
from wordcloud import WordCloud
import jieba
from PIL import Image
import numpy as np 
import sqlite3

# 读文件
# text_from_file_with_apath = open('数字爱情故事.md', encoding='utf-8').read()

text_from_file_with_apath = ''
conn = sqlite3.connect('msg.db')
c = conn.cursor()
cursor = c.execute("SELECT * from mz_msg;")
for row in cursor:
	text_from_file_with_apath += row[1]
conn.close()

# print(text_from_file_with_apath)

image = np.array(Image.open('1.jpg'))  # 词云形状

# 自定义文字颜色
# colormaps = colors.ListedColormap(['#FF0000','#FF7F50','#FFE4C4'])  # 红色系
colormaps = colors.ListedColormap(['#0010FF','#00E5FF','#BF46FF'])   # 蓝色系

wordlist_after_jieba = jieba.lcut(text_from_file_with_apath, cut_all = True)

# 整理成字符串
wl_space_split = ''
for i in wordlist_after_jieba:
	if len(i) > 1:
		wl_space_split += i
		wl_space_split += " "



# print(wordlist_after_jieba) # 分词字典
# wl_space_split = " ".join(wordlist_after_jieba) # 整理词成字符串
# print(wl_space_split)

# 生成
my_wordcloud = WordCloud(
	font_path="a.ttf", 
	mask=image,
	background_color='white',  # 指定背景颜色，默认黑色
	colormap=colormaps,  # 指定文字颜色
	width=800,  # 指定宽度
	height=600,  # 指定高度
	font_step=4, #字号步长
	min_font_size=8,max_font_size=250, #字号
).generate(wl_space_split)

# 显示
plt.imshow(my_wordcloud)
plt.axis("off")
plt.show()


my_wordcloud.to_file('词云1.png')  # 生成词云图片