[python基础] python生成wordcloud并保存

1.核心包

#jieba、pandas用来处理数据，数据源以xls格式存储的，这里用pandas进行处理
import jieba
from jieba import analyse
import pandas as pd
#scipy、wordcloud创建词云
from scipy.misc import imread
from wordcloud import WordCloud
from wordcloud import ImageColorGenerator
#matpoltlib展示、保存生成的词云图
import matplotlib.pyplot as plt

2.过程

import jieba
from jieba import analyse
import pandas as pd

import sys
reload(sys)
sys.setdefaultencoding('utf-8')

# 1.stopwords
def stop_words():
    stop_dict = set()
    with open(u'./百度停用词列表.txt', 'r')as  f:
        words = f.readlines()
        for word in words:
            stop_dict.add(word.strip().decode('utf-8'))
    return stop_dict

# 2.分词并去停用词
# save chinese only,remove english words,emoji
def remove_stopwords(stop_words):
    source_data = pd.read_excel('./11.xls')
    all_content = []
    content = source_data[u'内容']
    f = open('./weibo.txt', 'w')
    for line in content:
        cut_list = [c for c in jieba.cut(line)]
        ret_set = set(cut_list) - stop_words
        ret_list = list(ret_set)
        f.writelines([str(line) for line in ret_list])
        f.writelines('\n')
        all_content.extend(ret_list)
    f.close()

#3.统计词频
def get_frequency_words(file):
    with open(file, 'r') as f:
        texts = f.read()
　　　　　# 统计词频
        top_words = analyse.textrank(texts, topK=400, withWeight=True)
        ret_words = {}
        for word in top_words:
            ret_words[word[0]] = word[1]
    return ret_words

from scipy.misc import imread
from wordcloud import WordCloud
from wordcloud import ImageColorGenerator
import matplotlib.pyplot as plt

# 4.生成词云图并保存
def generate_word_cloud(dict):
    color_mask = imread('./background.jpg')
    cloud = WordCloud(
        # 设置字体，不指定就会出现乱码，文件名不支持中文
        font_path="./static/chinese.msyh.ttf",
        # font_path=path.join(d,'simsun.ttc'),
        # 设置背景色，默认为黑，可根据需要自定义为颜色
        background_color='white',
        # 词云形状，
        mask=color_mask,
        # 允许最大词汇
        max_words=400,
        # 最大号字体，如果不指定则为图像高度
        max_font_size=150,
        # 画布宽度和高度，如果设置了mask则不会生效
        # 词语水平摆放的频率，默认为0.9.即竖直摆放的频率为0.1
        prefer_horizontal=0.8
    )
    cloud.generate_from_frequencies(frequencies=dict)
    cloud.to_file('word_cloud.jpg')
    # plt.imshow(cloud)
    # 不现实坐标轴
    plt.axis('off')
    # 绘制词云
    # plt.figure(dpi = 600)
    image_colors = ImageColorGenerator(color_mask)
# 重新上色
    plt.imshow(cloud.recolor(color_func=image_colors))
　　# 保存图片
    plt.savefig('./result2.png')
    # plt.show()

if __name__ == '__main__':
    stop_words = stop_words()
    remove_stopwords(stop_words=stop_words)
    words_frequency = get_frequency_words('./weibo.txt')
    generate_word_cloud(words_frequency)