python 生成詞雲

#/usr/bin/env python
# *-*coding:utf-8 *-*


#模塊介紹https://amueller.github.io/word_cloud/
#python 3.5.2


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




filepath = '~/Download/Janeeyre.txt'
picturepath = '~/Download/anne.png'
fontpath = '~/Download/simfang.ttf'


text = open(filepath, 'r').read()


back_picture = imread(picturepath)


#設置 字體 字體間距 背景色 最多詞彙數量 詞雲形狀 最大號字體 計算和圖片之間的縮放
wc = WordCloud(font_path = fontpath,
font_step = 3,
background_color = 'black',
max_words = 200,
mask = back_picture,
max_font_size = 100,
random_state = 42,
scale = 5
)


#生成詞雲
wc.generate(text)


#運行後顯示圖片
plt.figure()
plt.imshow(wc)
plt.axis('off')
plt.show()
#保存圖片
wc.to_file( "Janeeyre.jpg")


'''-----------------------------------------------------------------------------------'''
#/usr/bin/env python
# *-*coding:utf-8 *-*




from scipy.misc import imread
import matplotlib.pyplot as plt
from wordcloud import WordCloud
import jieba
from collections import Counter


#讀入文本


text = open('~/Download/西遊記.txt').read()


#使用jieba# 分詞
text_jieba = list(jieba.cut(text))
#使用 counter 做詞頻統計 選取出頻率前100的詞彙
c = Counter(text_jieba)
common_c = c.most_common(100)
#讀取圖片
bg_pic = imread('~/Download/anne.png')
#配置詞雲參數
wc = WordCloud(
font_path = '~/Download/李旭科書法.ttf',
#font_path = '/home/asu/py2/simfang.ttf',
background_color = 'white',
max_words = 2000,
mask = bg_pic,
max_font_size = 200,
)


#生成詞雲
wc.generate_from_frequencies(dict(common_c))
#生成圖片顯示
plt.figure()
plt.imshow(wc)
plt.axis('off')
plt.show()


wc.to_file('xi youji.jpg')