Python wordcloud.WordCloud() Examples

def generate_wordcloud(df, save_cfg=cfg.saving_config):
    brain_mask = np.array(Image.open("./img/brain_stencil.png"))

    def transform_format(val):
        if val == 0:
            return 255
        else:
            return val

    text = (df['Title']).to_string()

    stopwords = set(STOPWORDS)
    stopwords.add("using")
    stopwords.add("based")

    wc = WordCloud(
        background_color="white", max_words=2000, max_font_size=50, mask=brain_mask,
        stopwords=stopwords, contour_width=1, contour_color='steelblue')
    wc.generate(text)

    # store to file
    if save_cfg is not None:
        fname = os.path.join(save_cfg['savepath'], 'DL-EEG_WordCloud')
        wc.to_file(fname + '.' + save_cfg['format']) #, **save_cfg) 

def generate_word_cloud():
    """
    生成词云
    :return:
    """
    with open(filename, 'r') as f:
        word_content = f.read()

        # 使用jieba去分割
        wordlist = jieba.cut(word_content, cut_all=True)

        wl_space_split = " ".join(wordlist)

        font = r'/Users/xingag/Library/Fonts/SimHei.ttf'

        wordcloud = WordCloud(font_path=font, width=1080, height=1920, margin=2).generate(wl_space_split)

        # 显示图片
        plt.imshow(wordcloud)
        plt.axis("off")

        # 按照设置保存到本地文件夹
        wordcloud.to_file("./output.png") 

def main():
    seg = Seg()
    doc = '''自然语言处理: 是人工智能和语言学领域的分支学科。
            在这此领域中探讨如何处理及运用自然语言；自然语言认知则是指让电脑“懂”人类的语言。 
            自然语言生成系统把计算机数据转化为自然语言。自然语言理解系统把自然语言转化为计算机程序更易于处理的形式。'''
    # res = seg.seg_from_doc(doc)
    datalist = seg.get_data_from_mysql(1000, 0)
    keywords = dict(seg.get_keyword_from_datalist(datalist))

    font_path = root_path + '/data/simfang.ttf'
    bg_path = root_path + '/data/bg.jpg'
    #back_color = np.array(Image.open(bg_path))
    back_color = imread(bg_path)
    image_colors = ImageColorGenerator(back_color)
    wordcloud = WordCloud(font_path=font_path, background_color="white", mask=back_color,
                          max_words=2000, max_font_size=100, random_state=48, width=1000, height=800, margin=2)
    wordcloud.generate_from_frequencies(keywords)
    plt.figure()
    plt.imshow(wordcloud.recolor(color_func=image_colors))
    plt.axis("off")
    plt.show()
    wordcloud.to_file(root_path + '/data/pic2.png') 

def show_wordCloud(word_freq):
    """
    词云显示
    """
    font = r'C:\Windows\Fonts\msyh.ttc'  # 指定字体，不指定会报错
    color_mask = imread("resource/timg.jpg")  # 读取背景图片
    wcloud = WordCloud(
        font_path=font,
        # 背景颜色
        background_color="white",
        # 词云形状
        mask=color_mask,
        # 允许最大词汇
        max_words=2000,
        # 最大号字体
        max_font_size=80)

    wcloud.generate_from_frequencies(dict(word_freq))
    # 以下代码显示图片
    plt.imshow(wcloud)
    plt.axis("off")
    plt.show()
    wcloud.to_file("data/wcimage/三体词云_3.png") 

def show_wordCloud(word_freq):
    """
    词云显示
    """
    font = r'C:\Windows\Fonts\msyh.ttc'  # 指定字体，不指定会报错  
    color_mask = imread("resource/timg.jpg")  # 读取背景图片
    wcloud = WordCloud(
        font_path=font,
        # 背景颜色
        background_color="white",
        # 词云形状
        mask=color_mask,
        # 允许最大词汇
        max_words=2000,
        # 最大号字体
        max_font_size=80)

    wcloud.generate_from_frequencies(dict(word_freq))
    # 以下代码显示图片
    plt.imshow(wcloud)
    plt.axis("off")
    plt.show()
    wcloud.to_file("data/wcimage/三体词云_3.png") 

def show_wordCloud(word_freq):
    """
    词云显示
    """
    font = r'C:\Windows\Fonts\msyh.ttc'  # 指定字体，不指定会报错
    color_mask = imread("resource/timg.jpg")  # 读取背景图片
    wcloud = WordCloud(
        font_path=font,
        # 背景颜色
        background_color="white",
        # 词云形状
        mask=color_mask,
        # 允许最大词汇
        max_words=2000,
        # 最大号字体
        max_font_size=80)

    wcloud.generate_from_frequencies(dict(word_freq))
    # 以下代码显示图片
    plt.imshow(wcloud)
    plt.axis("off")
    plt.show()
    wcloud.to_file("data/wcimage/雪中_1.png") 

def gen_img(texts, img_file):
    data = ' '.join(text for text in texts)
    image_coloring = imread(img_file)
    wc = WordCloud(
        background_color='white',
        mask=image_coloring,
        font_path='/Library/Fonts/STHeiti Light.ttc'
    )
    wc.generate(data)

    # plt.figure()
    # plt.imshow(wc, interpolation="bilinear")
    # plt.axis("off")
    # plt.show()

    wc.to_file(img_file.split('.')[0] + '_wc.png') 

def PrintWorfCloud(self,documents,backgroundImgPath,fontPath):
        '''Print out the word cloud of all news(articles/documents).

        # Arguments:
            documents: Overall raw documents.
            backgroundImgPath: Background image path.
            fontPath: The path of windows fonts that used to create the word-cloud.
        '''
        from scipy.misc import imread
        import matplotlib.pyplot as plt
        from wordcloud import WordCloud
        corpora_documents = self.jieba_tokenize(documents) #分词
        for k in range(len(corpora_documents)):
            corpora_documents[k] = ' '.join(corpora_documents[k])
        corpora_documents = ' '.join(corpora_documents)
        color_mask = imread(backgroundImgPath) #"C:\\Users\\lenovo\\Desktop\\Text_Mining\\3.jpg"
        cloud = WordCloud(font_path=fontPath,mask=color_mask,background_color='white',\
                          max_words=2000,max_font_size=40) #"C:\\Windows\\Fonts\\simhei.ttf"
        word_cloud = cloud.generate(corpora_documents) 
        plt.imshow(word_cloud, interpolation='bilinear')
        plt.axis("off") 

def create_wordcloud(content,image='weibo.jpg',max_words=5000,max_font_size=50):

    cut_text = " ".join(content)
    cloud = WordCloud(
        # 设置字体，不指定就会出现乱码
        font_path="HYQiHei-25J.ttf",
        # 允许最大词汇
        max_words=max_words,
        # 设置背景色
        # background_color='white',
        # 最大号字体
        max_font_size=max_font_size
    )
    word_cloud = cloud.generate(cut_text)
    word_cloud.to_file(image)

# 分词并去除停用词 

def run(db, args):
    if platform.system() == "Darwin":
        mpl.use("TkAgg")

    import matplotlib.pyplot as plt

    title = "Top reused passwords for {}".format(args.domain)
    passwords = db.all_passwords

    wc = WordCloud(background_color="black", width=1280, height=800, margin=5, max_words=1000, color_func=__get_password_color(passwords))
    wc.generate(" ".join([password for password, score in passwords]))

    plt.title(title)
    plt.imshow(wc, interpolation="nearest", aspect="equal")
    plt.axis("off")
    plt.show() 

def lyrics():
    with open('lyrics.json', 'r', encoding='utf-8') as f:
        data = json.load(f)
    tokens = list()
    for v in data.values():
        # 斷詞後的結果, 若非空白且長度為 2 以上, 則列入詞庫
        tokens += [seg for seg in jieba.cut(v) if seg.split() and len(seg) > 1]

    # 計算 tokens 內各詞彙的出現次數
    counter = Counter(tokens)
    print(counter.most_common(10))

    # 文字雲, 要顯示中文需附上字型檔
    wcloud = WordCloud(font_path='NotoSansMonoCJKtc-Regular.otf').generate(' '.join(tokens))
    plt.imshow(wcloud)
    plt.axis('off')
    plt.show() 

def test_write_wordclouds_to_folder(tmpdir):
    try:
        import lda
        import PIL
        from wordcloud import WordCloud
    except ImportError:
        pytest.skip('at least one of lda, Pillow, wordcloud not installed')

    path = tmpdir.mkdir('wordclouds').dirname

    data = model_io.load_ldamodel_from_pickle('tests/data/tiny_model_reuters_5_topics.pickle')
    model = data['model']
    vocab = data['vocab']

    phi = model.topic_word_
    assert phi.shape == (5, len(vocab))

    topic_word_clouds = visualize.generate_wordclouds_for_topic_words(phi, vocab, 10)

    visualize.write_wordclouds_to_folder(topic_word_clouds, path, 'cloud_{label}.png')

    for label in topic_word_clouds.keys():
        assert os.path.exists(os.path.join(path, 'cloud_{label}.png'.format(label=label))) 

def draw_word_cloud(content):
    d = os.path.dirname(__file__)
    img = Image.open(os.path.join(d, "toutiao.jpg"))
    width = img.width / 80
    height = img.height / 80
    alice_coloring = np.array(img)
    my_wordcloud = WordCloud(background_color="white",
                             max_words=500, mask=alice_coloring,
                             max_font_size=200, random_state=42,
                             font_path=(os.path.join(d, "../common/font/PingFang.ttc")))
    my_wordcloud = my_wordcloud.generate_from_frequencies(content)

    image_colors = ImageColorGenerator(alice_coloring)
    plt.figure(figsize=(width, height))
    plt.imshow(my_wordcloud.recolor(color_func=image_colors))
    plt.imshow(my_wordcloud)
    plt.axis("off")
    # 通过设置subplots_adjust来控制画面外边框
    plt.subplots_adjust(bottom=.01, top=.99, left=.01, right=.99)
    plt.savefig("toutiao_wordcloud.png")
    plt.show() 

def draw_word_cloud(content):
    d = os.path.dirname(__file__)
    img = Image.open(os.path.join(d, "changzuoren.jpg"))
    width = img.width / 80
    height = img.height / 80
    alice_coloring = np.array(img)
    my_wordcloud = WordCloud(background_color="white",
                             max_words=500, mask=alice_coloring,
                             max_font_size=200, random_state=42,
                             font_path=(os.path.join(d, "../common/font/PingFang.ttc")))
    my_wordcloud = my_wordcloud.generate_from_frequencies(content)

    image_colors = ImageColorGenerator(alice_coloring)
    plt.figure(figsize=(width, height))
    plt.imshow(my_wordcloud.recolor(color_func=image_colors))
    plt.imshow(my_wordcloud)
    plt.axis("off")
    # 通过设置subplots_adjust来控制画面外边框
    plt.subplots_adjust(bottom=.01, top=.99, left=.01, right=.99)
    plt.savefig("changzuoren_wordcloud.png")
    plt.show() 

def generate_wordclouds_for_topic_words(topic_word_distrib, vocab, top_n, topic_labels='topic_{i1}', which_topics=None,
                                        return_images=True, **wordcloud_kwargs):
    """
    Generate wordclouds for the top `top_n` words of each topic in `topic_word_distrib`.

    :param topic_word_distrib: topic-word distribution; shape KxM, where K is number of topics, M is vocabulary size
    :param vocab: vocabulary array of length M
    :param top_n: number of top values to take from each row of `distrib`
    :param topic_labels: labels used for each row; determine keys in in result dict; either single format string with
                         placeholders ``"{i0}"`` (zero-based topic index) or ``"{i1}"`` (one-based topic index), or
                         list of topic label strings
    :param which_topics: if not None, a sequence of indices into rows of `topic_word_distrib` to select only these
                         topics to generate wordclouds from
    :param return_images: if True, store image objects instead of :class:`wordcloud.WordCloud` objects in the result
                          dict
    :param wordcloud_kwargs: pass additional options to :class:`wordcloud.WordCloud`; updates options in
           :data:`~tmtoolkit.topicmod.visualize.DEFAULT_WORDCLOUD_KWARGS`
    :return: dict mapping row labels to wordcloud images or instances generated from each topic
    """
    return generate_wordclouds_from_distribution(topic_word_distrib, row_labels=topic_labels, val_labels=vocab,
                                                 top_n=top_n, which_rows=which_topics, return_images=return_images,
                                                 **wordcloud_kwargs) 

def draw_imgae(counter):
    font_path = "C:/Users/96363/Desktop/markdown/font/HYBeiKeHeiW.ttf"
    # background_image = numpy.array(Image.open("C:\\Users\\96363\\Downloads\\british-library-FQph76jy1mo-unsplash.jpg"))
    wd = WordCloud(
        font_path=font_path,
        height=400,
        width=800,
        background_color="black",
        #  mask=background_image
    ).generate_from_frequencies(counter)
    wd.to_file("world.png")
    # 词图显示
    image = Image.open("world.png")
    image.show() 

def AddFigure(filteredDictionary, plotnum, title):
	wordcloud = WordCloud().generate_from_frequencies(filteredDictionary)
	plt.subplot(plotnum)
	plt.imshow(wordcloud, interpolation='bilinear')
	plt.title(title)
	plt.axis("off")

#Search term used for this tweet
#We want to filter this out! 

def wordCloud():
  logging.info("Generating wordCloud from text, cnt = %d", msgCnt)
  wordcloud = WordCloud(stopwords=STOPWORDS, width=800, height=400, background_color="white", max_words=1000).generate(wordText)
  logging.debug("wc freq %s: ", wordcloud.words_)
  wordcloud.to_file(mountPath + "/wordcloud.png") 

def update_wordcloud_abbr():
    """ Update the figure wordcloud_category.jpg """

    data = pd.read_csv('AllGAN-r2.tsv',delimiter='\t', encoding='utf-8')

    wordcloud = WordCloud(stopwords=STOPWORDS,relative_scaling = 0.2, random_state=3,
                max_words=2000, background_color='white').generate(' '.join(data['Abbr.']))

    plt.figure(figsize=(12,12))
    plt.imshow(wordcloud, interpolation="bilinear")
    plt.axis("off")
    #plt.show()
    #plt.savefig('wordcloud_title.png')
    wordcloud.to_file('wordcloud_abbr.png')
    wordcloud.to_file('docs/png/wordcloud_abbr.png') 

def update_wordcloud_category():
    """ Update the figure wordcloud_category.jpg """

    data = pd.read_csv('AllGAN-r2.tsv',delimiter='\t', encoding='utf-8')

    wordcloud = WordCloud(stopwords=STOPWORDS,relative_scaling = 0.2, random_state=3,
                max_words=2000, background_color='white').generate(' '.join(data['Category']))

    plt.figure(figsize=(12,12))
    plt.imshow(wordcloud, interpolation="bilinear")
    plt.axis("off")
    #plt.show()
    #plt.savefig('wordcloud_title.png')
    wordcloud.to_file('wordcloud_category.png')
    wordcloud.to_file('docs/png/wordcloud_category.png') 

def update_wordcloud_title():
    """ Update the figure wordcloud_title.jpg """

    data = pd.read_csv('AllGAN-r2.tsv',delimiter='\t', encoding='utf-8')

#    tmp_data = data['Title'].split(" ") for x in data

#    count_list = list([list(x) for x in data['Title'].value_counts().reset_index().values])

#    wordcloud = WordCloud(stopwords=STOPWORDS,relative_scaling = 0.2,
#                        max_words=2000, background_color='white').generate_from_frequencies(tmp_data)
    stopwords = set(STOPWORDS)
    #ganstop = ['Generative','Adversarial', 'Networks', 'Network', 'GAN', 'GANs', 'using', 'Learning', 'Training', 'Generation',
    #        'Neural', 'Net', 'Model', 'Nets', 'Deep', 'Based', 'Via', 'Conditional', 'Models', 'Examples']
    #stopwords.add(ganstop)

    stopwords.add('Generative')
    stopwords.add('Adversarial')
    stopwords.add('Networks')
    stopwords.add('Network')
    stopwords.add('GAN')
    stopwords.add('GANs')
    stopwords.add('using')
    stopwords.add('Learning')
    stopwords.add('Training')
    stopwords.add('Generation')
    stopwords.add('Neural')
    stopwords.add('Net')
    stopwords.add('Model')
    stopwords.add('Nets')
    stopwords.add('Deep')
    stopwords.add('Based')
    stopwords.add('Via')
    stopwords.add('Conditional')
    stopwords.add('Models')
    stopwords.add('Examples')

    wordcloud = WordCloud(stopwords=stopwords,relative_scaling = 0.2, random_state=3,
                    max_words=2000, background_color='white').generate(' '.join(data['Title']))

    plt.figure(figsize=(12,12))
    plt.imshow(wordcloud, interpolation="bilinear")
    plt.axis("off")
    #plt.show()
    #plt.savefig('wordcloud_title.png')
    wordcloud.to_file('wordcloud_title.png')
    wordcloud.to_file('docs/png/wordcloud_title.png') 

def wordCloud2():
  logging.info("Generating wordCloud from freq, cnt = %d", msgCnt)
  wordcloud = WordCloud(stopwords=STOPWORDS, width=800, height=400, background_color="white", max_words=1000).generate_from_frequencies(wordCounter)
  wordcloud.to_file(mountPath + "/wordcloud2.png") 

def seg_answer():
    answer_content = open(question_id + ".txt",'r',encoding='utf-8').read()
    print("segging answers...")
    answer_seg = jieba.cut(answer_content)
    stopwords = open("chineseStopWords.txt",'r',encoding='GBK').read()
    new_answer_seg = []
    for text in answer_seg:
        if text not in stopwords:
            new_answer_seg.append(text)
    string = ' '.join(new_answer_seg)
    print("making wordcloud...")
    wc = WordCloud(font_path='C:/Windows/Fonts/simkai.ttf',background_color='white',width=1000,height=800).generate(string)
    wc.to_file(question[0]+'.png') 

def generate_wordcloud(tup):
    wordcloud = WordCloud(
        background_color="white", max_words=50, max_font_size=40, random_state=42
    ).generate(str(tup))
    return wordcloud 

def genwordcloud(texts,mask=None,font_path=None,background_color='white'):
    '''生成词云
    parameter
    ----------
    mask: RGBA模式数组，最后一个分量是alpha通道, 默认会生成一个900*1200的椭圆
    font_path: 采用的字体，建议采用安卓默认字体DroidSansFallback.ttf
    
    return
    -------
    img:可以直接img.save('test.png')
    '''
    from PIL import Image
    try:
        from wordcloud import WordCloud
    except:
        #raise Exception('wordcloud need install wordcloud package.')
        print('wordcloud need install wordcloud package.')
        return None
    if mask is None:
        tmp=np.zeros((900,1200),dtype=np.uint8)
        for i in range(tmp.shape[0]):
            for j in range(tmp.shape[1]):
                if (i-449.5)**2/(430**2)+(j-599.5)**2/(580**2)>1:
                    tmp[i,j]=255
        mask=np.zeros((900,1200,4),dtype=np.uint8)
        mask[:,:,0]=tmp
        mask[:,:,1]=tmp
        mask[:,:,2]=tmp
        mask[:,:,3]=255
    else:
        mask=np.array(Image.open(mask))
    wordcloud = WordCloud(background_color = background_color,font_path=font_path, mask = mask)
    wordcloud.generate(texts)
    img=wordcloud.to_image()
    return img 

def make_wc(self, text, max):
		try:
			wc = WordCloud(background_color='black', width=1024, height=768, max_words=max).generate(' '.join(text))
			img = wc.to_image()
			b = BytesIO()
			img.save(b, 'png')
			b.seek(0)
			return b
		except Exception as e:
			return str(e) 

def make_wc_custom(self, mask, text, max):
		try:
			coloring = np.array(PIL.Image.open(mask))
			wc = WordCloud(width=1024, height=768, max_words=max, mask=coloring)
			wc = wc.generate(' '.join(text))
			image_colors = ImageColorGenerator(coloring)
			wc = wc.recolor(color_func=image_colors)
			img = wc.to_image()
			b = BytesIO()
			img.save(b, 'png')
			b.seek(0)
			return b
		except Exception as e:
			return str(e) 

def AddFigure(dictionary, plotnum, title):
	wordcloud = WordCloud().generate_from_frequencies(dictionary)
	plt.subplot(plotnum)
	plt.imshow(wordcloud, interpolation='bilinear')
	plt.title(title)
	plt.axis("off")


#Create a matplotlib figure 

def wordCloud(wordList):
    from wordcloud import WordCloud, ImageColorGenerator
    import matplotlib.pyplot as plt
    import numpy as np
    import PIL.Image as Image
    import os
    d = os.path.dirname(__file__)
    img = Image.open(os.path.join(d, "jupiter.png"))
    width = img.width/80
    height = img.height/80
    alice_coloring = np.array(img)
    my_wordcloud = WordCloud(background_color="white",
                             max_words=500, mask=alice_coloring,
                             max_font_size=200, random_state=42,
                             font_path=(os.path.join(d, "../font/PingFang.ttc")))
    my_wordcloud = my_wordcloud.generate_from_frequencies(wordList)

    image_colors = ImageColorGenerator(alice_coloring)
    plt.figure(figsize=(width, height))
    plt.imshow(my_wordcloud.recolor(color_func=image_colors))
    plt.imshow(my_wordcloud)
    plt.axis("off")
    # 通过设置subplots_adjust来控制画面外边框
    plt.subplots_adjust(bottom=.01, top=.99, left=.01, right=.99)
    plt.savefig("jupiter_wordcloud_1.png")
    plt.show() 

def generate_word_cloud(self, fonts, masks, name_prefix='some-wordcloud', bg_color='white'):
        """
          (obj, list, list, str) -> None

          Generating the word clouds with different masks and fonts and saving it as images.
        """

        if name_prefix is None:
            name_prefix = 'some-wordcloud'

        BASE_FOLDER = self.wc_helper.save_dir
        STOPWORDS = self.STOPWORDS
        print BASE_FOLDER

        from scipy.misc import imread

        for mask_name in masks:
            _mask_file = imread(masks[mask_name], flatten=True)
            _mask_width = len(_mask_file[0]) + 1
            _mask_height = len(_mask_file) + 1
            for font_name in fonts:
                _font_file = fonts[font_name]
                _img_name = '%s-%s-%s-%s' % (str(name_prefix),
                                             str(font_name), str(mask_name), str(bg_color))
                wordcloud = WordCloud(
                    font_path=_font_file,
                    stopwords=STOPWORDS,
                    background_color=bg_color,
                    width=_mask_width,
                    height=_mask_height,
                    mask=_mask_file
                ).generate(self.words)
                plt.imshow(wordcloud)
                plt.axis('off')
                plt.savefig(BASE_FOLDER + _img_name, dpi=300)
                print '[i] image %s.png was generated ' % _img_name