python jieba+wordcloud

pip install jieba
pip install wordcloud

#! -*- coding: utf-8 -*-
import jieba.posseg as pseg

stop_words = ["给", "被", "的", "最"]
text = "食堂的饭真的是很好吃呀,最喜欢食堂了"
word_dict = {}
# 分词并统计词频,flag表示词性
for word, flag in pseg.cut(text):
    if word not in stop_words:
        if word not in word_dict:
            word_dict[word] = 1
        else:
            word_dict[word] += 1
        print(word + "\t" + flag)
print("--------------")
# 按照词频做降序排列
word_dict_sort = sorted(word_dict.items(), key=lambda word_dict:word_dict[1], reverse=True)
for key, word in word_dict_sort:
    print(key + "\t" + str(word))

python jieba+wordcloud_第1张图片
python jieba+wordcloud_第2张图片

#! -*- coding: utf-8 -*-
import jieba
from wordcloud import WordCloud
from matplotlib import pyplot as plt


text = "我是一串新闻"
mytext = " ".join(jieba.cut(text))
font = r'simsun.ttf'
wordcloud = WordCloud(font_path=font, #如果是中文必须要添加这个,否则会显示成框框
               # background_color='white',
               # width=1000,
               # height=800,
               ).generate(mytext)

wordcloud.to_file('ss.png') #保存图片
plt.imshow(wordcloud)  #用plt显示图片
plt.axis('off') #不显示坐标轴
plt.show() #显示图片

你可能感兴趣的:(python,jieba,wordcloud)