python实战===老司机奇技淫巧系列之字符转换成图…

#coding:utf-8
#author  http://blog.csdn.net/fyuanfena/article/details/52038984

from os import path
from scipy.misc import imread
import matplotlib.pyplot as plt
import jieba

from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator



stopwords = {}
def importStopword(filename=''):
    global stopwords
    f = open(filename, 'r', encoding='utf-8')
    line = f.readline().rstrip()

    while line:
        stopwords.setdefault(line, 0)
        stopwords[line] = 1
        line = f.readline().rstrip()

    f.close()

def processChinese(text):
    seg_generator = jieba.cut(text)  # 使用jieba分词，也可以不使用

    seg_list = [i for i in seg_generator if i not in stopwords]

    seg_list = [i for i in seg_list if i != u' ']

    seg_list = r' '.join(seg_list)

    return seg_list

importStopword(filename='./stopwords.txt')


# 获取当前文件路径
# __file__ 为当前文件, 在ide中运行此行会报错,可改为
# d = path.dirname('.')
d = path.dirname(__file__)

text = open(path.join(d, u'love.txt'),encoding ='utf-8').read()

#如果是中文
text = processChinese(text)#中文不好分词，使用Jieba分词进行

# read the mask / color image
# 设置背景图片
back_coloring = imread(path.join(d, "./image/love.jpg"))

wc = WordCloud( font_path='./font/cabin-sketch.bold.ttf ',                      #设置字体 要是使用汉字就用simhei.ttf
                background_color="white", #背景颜色
                max_words=1000,# 词云显示的最大词数
                mask=back_coloring,#设置背景图片
                max_font_size=80, #字体最大值
                random_state=10,   #42
                )
# 生成词云, 可以用generate输入全部文本(中文不好分词),也可以我们计算好词频后使用generate_from_frequencies函数
wc.generate(text)
# wc.generate_from_frequencies(txt_freq)
# txt_freq例子为[('词a', 100),('词b', 90),('词c', 80)]
# 从背景图片生成颜色值
image_colors = ImageColorGenerator(back_coloring)

plt.figure()
# 以下代码显示图片
plt.imshow(wc)
plt.axis("off")
plt.show()
# 绘制词云

# 保存图片
wc.to_file(path.join(d, "名1称.png"))

#!/usr/bin/env python
"""
Image-colored wordcloud
=======================

You can color a word-cloud by using an image-based coloring strategy
implemented in ImageColorGenerator. It uses the average color of the region
occupied by the word in a source image. You can combine this with masking -
pure-white will be interpreted as 'don't occupy' by the WordCloud object when
passed as mask.
If you want white as a legal color, you can just pass a different image to
"mask", but make sure the image shapes line up.
"""

from os import path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt

from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator

d = path.dirname(__file__)

# Read the whole text.
text = open(path.join(d, 'alice.txt')).read()

# read the mask / color image taken from
# http://jirkavinse.deviantart.com/art/quot-Real-Life-quot-Alice-282261010
alice_coloring = np.array(Image.open(path.join(d, "alice_color.png")))
stopwords = set(STOPWORDS)
stopwords.add("said")

wc = WordCloud(background_color="white", max_words=2000, mask=alice_coloring,
               stopwords=stopwords, max_font_size=40, random_state=42)
# generate word cloud
wc.generate(text)

# create coloring from image
image_colors = ImageColorGenerator(alice_coloring)

# show
plt.imshow(wc, interpolation="bilinear")
plt.axis("off")
plt.figure()
# recolor wordcloud and show
# we could also give color_func=image_colors directly in the constructor
plt.imshow(wc.recolor(color_func=image_colors), interpolation="bilinear")
plt.axis("off")
plt.figure()
plt.imshow(alice_coloring, cmap=plt.cm.gray, interpolation="bilinear")
plt.axis("off")
plt.show()