wordcloud的生成

最近整理学习Python时写过的一些代码，为了方便以后查看，将其作为笔记记录下来。。。

模块安装

安装Wordcloud包。

pip install wordcloud

安装Jieba分词工具。

pip install jieba

生成词云

# -*- coding: utf-8 -*-
import matplotlib.pyplot as plt
import pickle
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
import jieba
import codecs
import os

fin = codecs.open('诛仙.txt', 'r', encoding='utf-8')
print(len(fin.readlines()))

def wordCloud(stopwords):
    """
    第一次运行时将分好的词存入text文件中，然后加载并创建词云
    :param stopwords:
    :return:
    """
    text = ''
    with codecs.open('诛仙.txt', "r", encoding='utf-8') as fin:
        for i, line in enumerate(fin.readlines()):
            line = line.strip()
            text += segTool(line, stopwords)
            text += ' '
        # print(text)
        fout = open('text', 'wb')
        pickle.dump(text, fout)
        fout.close()
    # 直接从文件加载数据
    fr = open('text', 'rb')
    text = pickle.load(fr)
    fr.close()
    backgroud_Image = plt.imread('11.jpg')
    wc = WordCloud(background_color='white',    # 设置背景颜色
                mask=backgroud_Image,           # 设置背景图片
                max_words=100,                  # 设置最大现实的字数
                stopwords=STOPWORDS,            # 设置停用词
                font_path='qihei55.ttf',        # 设置字体格式，如不设置,显示不了中文
                max_font_size=100,              # 设置字体最大值
                random_state=30,                # 设置有多少种随机生成状态，即有多少种配色方案
                )
    wc.generate(text)
    # 改变字体颜色
    image_colors = ImageColorGenerator(backgroud_Image)
    # 字体颜色为背景图片的颜色
    wc.recolor(color_func=image_colors)
    # 绘制图片
    plt.imshow(wc)
    # 消除坐标抽
    plt.axis('off')
    # 显示图片
    plt.show()
    # 获得模块所在的路径的
    d = os.path.dirname(__file__)
    # d = os.getcwd()
    # 将多个路径组合后返回
    wc.to_file(os.path.join(d, "cy1.jpg"))

def segTool(line, stopwords):
    """ 结巴分词，并去掉停用词 """
    seg_list = jieba.cut(line, cut_all=False)
    segResult = ""
    for word in seg_list:
        if word not in stopwords and len(word) > 1:
            segResult += word
            segResult += " "
    return segResult.strip()

def stopwordslist(filepath):
    """ 创建停用词list """
    stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]
    return stopwords

if __name__ == "__main__":
    stopwords = stopwordslist('stopwords.txt')
    wordCloud(stopwords)

效果图