##Use the code by comment ##
关于该程序的使用,你可以直接读注释在数分钟内学会如何使用它
# - * - coding: utf - 8 -*-
from os import path
from scipy.misc import imread
import matplotlib.pyplot as plt
import jieba
# jieba.load_userdict("txt\userdict.txt")
# 添加用户词库为主词典,原词典变为非主词典
from wordcloud import WordCloud, ImageColorGenerator
# 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__)
stopwords = {}
isCN = 1 #默认启用中文分词
back_coloring_path = "img/lz1.jpg" # 设置背景图片路径
text_path = 'txt/lz.txt' #设置要分析的文本路径
font_path = 'D:\Fonts\simkai.ttf' # 为matplotlib设置中文字体路径没
stopwords_path = 'stopwords\stopwords1893.txt' # 停用词词表
imgname1 = "WordCloudDefautColors.png" # 保存的图片名字1(只按照背景图片形状)
imgname2 = "WordCloudColorsByImg.png"# 保存的图片名字2(颜色按照背景图片颜色布局生成)
my_words_list = ['路明非'] # 在结巴的词库中添加新词
back_coloring = imread(path.join(d, back_coloring_path))# 设置背景图片
# 设置词云属性
wc = WordCloud(font_path=font_path,  # 设置字体
               background_color="white",  # 背景颜色
               max_words=2000,  # 词云显示的最大词数
               mask=back_coloring,  # 设置背景图片
               max_font_size=100,  # 字体最大值
               random_state=42,
               width=1000, height=860, margin=2,# 设置图片默认的大小,但是如果使用背景图片的话,那么保存的图片大小将会按照其大小保存,margin为词语边缘距离
               )
# 添加自己的词库分词
def add_word(list):
    for items in list:
        jieba.add_word(items)
add_word(my_words_list)
text = open(path.join(d, text_path)).read()
def jiebaclearText(text):
    mywordlist = []
    seg_list = jieba.cut(text, cut_all=False)
    liststr="/ ".join(seg_list)
    f_stop = open(stopwords_path)
    try:
        f_stop_text = f_stop.read( )
        f_stop_text=unicode(f_stop_text,'utf-8')
    finally:
        f_stop.close( )
    f_stop_seg_list=f_stop_text.split('\n')
    for myword in liststr.split('/'):
        if not(myword.strip() in f_stop_seg_list) and len(myword.strip())>1:
            mywordlist.append(myword)
    return ''.join(mywordlist)
if isCN:
    text = jiebaclearText(text)
# 生成词云, 可以用generate输入全部文本(wordcloud对中文分词支持不好,建议启用中文分词),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, imgname1))
image_colors = ImageColorGenerator(back_coloring)
plt.imshow(wc.recolor(color_func=image_colors))
plt.axis("off")
# 绘制背景图片为颜色的图片
plt.figure()
plt.imshow(back_coloring, cmap=plt.cm.gray)
plt.axis("off")
plt.show()
# 保存图片
wc.to_file(path.join(d, imgname2))

from wordcloud import WordCloud
f = open(u'txt/AliceEN.txt','r').read()
wordcloud = WordCloud(background_color="white",width=1000, height=860, margin=2).generate(f)
# width,height,margin可以设置图片属性
# generate 可以对全部文本进行自动分词,但是他对中文支持不好,对中文的分词处理请看我的下一篇文章
#wordcloud = WordCloud(font_path = r'D:\Fonts\simkai.ttf').generate(f)
# 你可以通过font_path参数来设置字体集
#background_color参数为设置背景颜色,默认颜色为黑色
import matplotlib.pyplot as plt
plt.imshow(wordcloud)
plt.axis("off")
plt.show()
wordcloud.to_file('test.png')

#!/usr/bin/env python
"""
Colored by Group Example
========================
Generating a word cloud that assigns colors to words based on
a predefined mapping from colors to words
"""
from wordcloud import (WordCloud, get_single_color_func)
import matplotlib.pyplot as plt
class SimpleGroupedColorFunc(object):
    """Create a color function object which assigns EXACT colors
       to certain words based on the color to words mapping
       Parameters
       ----------
       color_to_words : dict(str -> list(str))
         A dictionary that maps a color to the list of words.
       default_color : str
         Color that will be assigned to a word that's not a member
         of any value from color_to_words.
    """
    def __init__(self, color_to_words, default_color):
        self.word_to_color = {word: color
                              for (color, words) in color_to_words.items()
                              for word in words}
        self.default_color = default_color
    def __call__(self, word, **kwargs):
        return self.word_to_color.get(word, self.default_color)
class GroupedColorFunc(object):
    """Create a color function object which assigns DIFFERENT SHADES of
       specified colors to certain words based on the color to words mapping.
       Uses wordcloud.get_single_color_func
       Parameters
       ----------
       color_to_words : dict(str -> list(str))
         A dictionary that maps a color to the list of words.
       default_color : str
         Color that will be assigned to a word that's not a member
         of any value from color_to_words.
    """
    def __init__(self, color_to_words, default_color):
        self.color_func_to_words = [
            (get_single_color_func(color), set(words))
            for (color, words) in color_to_words.items()]
        self.default_color_func = get_single_color_func(default_color)
    def get_color_func(self, word):
        """Returns a single_color_func associated with the word"""
        try:
            color_func = next(
                color_func for (color_func, words) in self.color_func_to_words
                if word in words)
        except StopIteration:
            color_func = self.default_color_func
        return color_func
    def __call__(self, word, **kwargs):
        return self.get_color_func(word)(word, **kwargs)
text = """The Zen of Python, by Tim Peters
Beautiful is better than ugly.
Explicit is better than implicit.
Simple is better than complex.
Complex is better than complicated.
Flat is better than nested.
Sparse is better than dense.
Readability counts.
Special cases aren't special enough to break the rules.
Although practicality beats purity.
Errors should never pass silently.
Unless explicitly silenced.
In the face of ambiguity, refuse the temptation to guess.
There should be one-- and preferably only one --obvious way to do it.
Although that way may not be obvious at first unless you're Dutch.
Now is better than never.
Although never is often better than *right* now.
If the implementation is hard to explain, it's a bad idea.
If the implementation is easy to explain, it may be a good idea.
Namespaces are one honking great idea -- let's do more of those!"""
# Since the text is small collocations are turned off and text is lower-cased
wc = WordCloud(collocations=False).generate(text.lower())
# 自定义所有单词的颜色
color_to_words = {
    # words below will be colored with a green single color function
    '#00ff00': ['beautiful', 'explicit', 'simple', 'sparse',
                'readability', 'rules', 'practicality',
                'explicitly', 'one', 'now', 'easy', 'obvious', 'better'],
    # will be colored with a red single color function
    'red': ['ugly', 'implicit', 'complex', 'complicated', 'nested',
            'dense', 'special', 'errors', 'silently', 'ambiguity',
            'guess', 'hard']
}
# Words that are not in any of the color_to_words values
# will be colored with a grey single color function
default_color = 'grey'
# Create a color function with single tone
# grouped_color_func = SimpleGroupedColorFunc(color_to_words, default_color)
# Create a color function with multiple tones
grouped_color_func = GroupedColorFunc(color_to_words, default_color)
# Apply our color function
# 如果你也可以将color_func的参数设置为图片,详细的说明请看 下一部分
wc.recolor(color_func=grouped_color_func)
# Plot
plt.figure()
plt.imshow(wc, interpolation="bilinear")
plt.axis("off")
plt.show()

#!/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")))
# 设置停用词
stopwords = set(STOPWORDS)
stopwords.add("said")
# 你可以通过 mask 参数 来设置词云形状
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
# 在只设置mask的情况下,你将会得到一个拥有图片形状的词云
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
# 我们还可以直接在构造函数中直接给颜色
# 通过这种方式词云将会按照给定的图片颜色布局生成字体颜色策略
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()