使用Python轻松实现绘制词云图项目(附详细源码)

import jieba  #结巴分词
from wordcloud import WordCloud  #词云展示库
from PIL import Image  #图像处理库
import numpy as np  #支持多维数组和矩阵运算
import matplotlib.pyplot as plt  #图像展示库

# 读取文本内容
with open('HL.txt','r',encoding="UTF-8") as f:
    file = f.read()  #将文本读取为整个字符串，readlines可以按行读取

#进行分词
data_cut =jieba.cut(file,cut_all = False) #精确模式分词

stop_words = ["，","。",";","、","我们","你们"]  #自定义停词列表

stop_words = [] #创建空列表
with open("stopwords.txt", 'r', encoding='utf-8') as f:
    for line in f:
        if len(line)>0:
            stop_words.append(line.strip())  #把停词追加到stop_words列表中

data_result = [i for i in data_cut if i not in stop_words] #获取需要的词

text = " ".join(data_result).replace("\n","") #连接成字符串
print(text)

wc = WordCloud(
    #设置字体，不指定就会出现乱码,这个字体文件需要下载
    font_path = "演示悠然小楷.ttf",
    background_color = "black",
    max_words = 5000,
)

# 生成词云图
wc.generate(text)

# 保存词云图
wc.to_file("IMJG.jpg") #保存图片

# 展示
plt.imshow(wc) #对图片进行处理，并显示其格式
plt.axis("off") #关闭坐标轴
plt.show() #将图片显示出来

#用Image方法打开图片
images = np.array(Image.open("JG.png"))

wc = WordCloud(
    #设置字体，不指定就会出现乱码,这个字体文件需要下载
    font_path = "演示悠然小楷.ttf",
    background_color = "black",
    max_words = 5000,
    mask=images
)

#-*- coding = uft-8 -*-
#@Time : 2020/5/23 10:30 上午
#@Author : 我是J哥
#@File : my_wordcloud.py

#给定词频制作词云图
from matplotlib import pyplot as plt   #绘图，数据可视化
from wordcloud import WordCloud   #词云
from PIL import Image  #图片处理
import numpy as np   #矩阵运算
import pymysql   #数据库
import pandas as pd  #数据处理


#准备词云所需文字（词）
conn = pymysql.connect(host="localhost", user="你的", passwd="你的", db="test", port=3306, charset="utf8")
cur = conn.cursor()
sql = "select brand as name,round(sum(jine)/10000,0) as value from Sc_month4 group by name order by value desc limit 100;"
df = pd.read_sql(sql, conn)
print(df)
name = list(df.name)  #词
value = df.value  # 词的频率
dic = dict(zip(name, value))  # 词频以字典形式存储
#print(dic)
cur.close()
conn.close()

img = Image.open("tree.png")
img_arry = np.array(img)
wc = WordCloud(
    background_color="white",
    mask=img_arry,
    max_words=1000,
    max_font_size=500,
    #font_path="演示悠然小楷.ttf"
    #font_path="有字库龙藏体.ttf"
    font_path="演示悠然小楷.ttf"
)

wc.generate_from_frequencies(dic)  #以词频生成词云

#绘制图片
fig = plt.figure(1)
plt.imshow(wc)
plt.axis("off")
plt.show()

#输出词云图片到文件
plt.savefig("JGJG.jpg",dpi=400)