Python WordCloud.generate_from_frequencies方法代码示例

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def draw_tag_cloud(users_tokens):
    from PIL import Image
    import matplotlib.pyplot as plt
    from wordcloud import WordCloud, ImageColorGenerator

    trump_coloring = np.array(Image.open("pics/trump.png"))

    freqs = get_full_frequencies(users_tokens)
    freq_pairs = freqs.items()
    wc = WordCloud(max_words=2000, mask=trump_coloring,
                   max_font_size=40, random_state=42)
    wc.generate_from_frequencies(freq_pairs)

    image_colors = ImageColorGenerator(trump_coloring)

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

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def generate_word_cloud(img_bg_path,top_words_with_freq,font_path,to_save_img_path,background_color = 'white'):
    # 读取背景图形
    img_bg = imread(img_bg_path)
    
    # 创建词云对象
    wc = WordCloud(font_path = font_path,  # 设置字体
    background_color = background_color,  # 词云图片的背景颜色，默认为白色
    max_words = 500,  # 最大显示词数为1000
    mask = img_bg,  # 背景图片蒙版
    max_font_size = 50,  # 字体最大字号
    random_state = 30,  # 字体的最多模式
    width = 1000,  # 词云图片宽度
    margin = 5,  # 词与词之间的间距
    height = 700)  # 词云图片高度
    
    # 用top_words_with_freq生成词云内容
    wc.generate_from_frequencies(top_words_with_freq)
    
    # 用matplotlib绘出词云图片显示出来
    plt.imshow(wc)
    plt.axis('off')
    plt.show()
    
    # 如果背景图片颜色比较鲜明，可以用如下两行代码获取背景图片颜色函数，然后生成和背景图片颜色色调相似的词云
    #img_bg_colors = ImageColorGenerator(img_bg)
    #plt.imshow(wc.recolor(color_func = img_bg_colors))
    
    # 将词云图片保存成图片
    wc.to_file(to_save_img_path)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def generate_image(words, image):
    graph = np.array(image)
    wc = WordCloud(font_path=os.path.join(CUR_DIR, 'fonts/simhei.ttf'),
                   background_color='white', max_words=MAX_WORDS, mask=graph)
    wc.generate_from_frequencies(words)
    image_color = ImageColorGenerator(graph)
    return wc, image_color

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def make_word_cloud(product, sentiment):
    if sentiment == "all":
        pos, neg = get_top_five_phrases(product,sentiment)

        pos.index = range(0,len(pos))
        neg.index = range(0,len(neg))

        pos_words_array = []
        neg_words_array = []
        for i in range(0,len(pos)):
            pos_words_array.append((pos["vocab"][i].upper(), float(pos["count"][i])))

        for i in range(0,len(neg)):
            neg_words_array.append((neg["vocab"][i].upper(), float(neg["count"][i])))

        wc = WordCloud(background_color="white", max_words=2000,
               max_font_size=300, random_state=42)

        # generate word cloud for positive
        positive_name = '../app/static/img/pos_wordcloud.png'
        wc.generate_from_frequencies(pos_words_array)
        wc.recolor(color_func=pos_color_func, random_state=3)
        wc.to_file(positive_name)

        # generate word cloud for negative
        negative_name = '../app/static/img/neg_wordcloud.png'
        wc.generate_from_frequencies(neg_words_array)
        wc.recolor(color_func=neg_color_func, random_state=3)
        wc.to_file(negative_name)

        return positive_name, negative_name

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def wcloud(wf, color, save_as=None):
    """Create a word cloud based on word frequencies,
    `wf`, using a color function from `wc_colors.py`

    Parameters
    ----------
    wf : list
        (token, value) tuples
    color : function
        from `wc_colors.py`
    save_as : str
        filename

    Returns
    -------
    None
    """
    wc = WordCloud(background_color=None, mode='RGBA',
                   width=2400, height=1600, relative_scaling=0.5,
                   font_path='/Library/Fonts/Futura.ttc')
    wc.generate_from_frequencies(wf)
    plt.figure()
    plt.imshow(wc.recolor(color_func=color, random_state=42))
    plt.axis("off")
    if save_as:
        plt.savefig(save_as, dpi=300, transparent=True)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
    def cal_and_show_jd_hot_words(self, jd_dir='../spider/jd'):
        """
        calculate and show hot words of Job Description (JD)
        :param jd_dir:
        :return:
        """
        if not os.path.exists(jd_dir) or len(os.listdir(jd_dir)) == 0:
            print('Error! No valid content in {0}'.format(jd_dir))
            sys.exit(0)
        else:
            jd_and_dir = {_.split('.')[0]: os.path.join(jd_dir, _) for _ in os.listdir(jd_dir)}

            for k, v in jd_and_dir.items():
                text = "".join(pd.read_excel(v)['详情描述'])
                jieba.analyse.set_stop_words(STOPWORDS_PATH)
                jieba.load_userdict(USER_CORPUS)
                hot_words_with_weights = jieba.analyse.extract_tags(text, topK=30, withWeight=True, allowPOS=())

                frequencies = {_[0]: _[1] for _ in hot_words_with_weights}

                print(frequencies)

                x, y = np.ogrid[:300, :300]
                mask = (x - 150) ** 2 + (y - 150) ** 2 > 130 ** 2
                mask = 255 * mask.astype(int)

                wordcloud = WordCloud(font_path='./msyh.ttf', width=600, height=300, background_color="white",
                                      repeat=False,
                                      mask=mask)
                wordcloud.generate_from_frequencies(frequencies)

                import matplotlib.pyplot as plt
                plt.imshow(wordcloud, interpolation='bilinear')
                plt.axis("off")
                plt.show()

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def generate_image(files, src_image):
    content = get_content(files)
    graph = np.array(Image.open(src_image))
    wc = WordCloud(font_path=os.path.join(CUR_DIR, 'fonts/simhei.ttf'),
                   background_color='white', max_words=MAX_WORDS, mask=graph)
    words = process_text(content)
    wc.generate_from_frequencies(words)
    image_color = ImageColorGenerator(graph)
    return wc, image_color

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
 def create_Cloud(self, data):
     print ('creating wordpair graph...')
     self.twitter_mask = np.array(Image.open(path.join(path.dirname(__file__), 'MASK/twitter_mask.png')))
     for word in data:
         wordcloud = WordCloud(font_path=path.join(path.dirname(__file__), 'FONT/CabinSketch-Bold.ttf'), relative_scaling=.5, width=1800, height=1400, stopwords=None, mask=self.twitter_mask)
         wordcloud.generate_from_frequencies(list(data[word].items()))
         wordcloud.to_file(path.join(path.dirname(__file__), 'WORDPAIRS/'+word+'.png'))            
     
     return

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def create_wordcloud(wordcloud_data):
    mask = imread(MASK_PATH)
    wordcloud = WordCloud(max_words=1000, mask=mask, stopwords=None, margin=10, random_state=1,
                          font_path=FONT_PATH, prefer_horizontal=1.0, width=WORD_CLOUD_WIDTH,
                          height = WORD_CLOUD_HEIGHT, background_color='black', mode='RGBA')
    word_importance_list = [(dct['word'], dct['importance']) for dct in wordcloud_data['words']]
    partisanship_list = [dct['partisanship'] for dct in wordcloud_data['words']]
    kwargs = {'word_partisanship': partisanship_list}
    wordcloud.generate_from_frequencies(word_importance_list, **kwargs)
    return wordcloud

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def makeImage(text):
    alice_mask = np.array(Image.open("alice_mask.png"))

    wc = WordCloud(background_color="white", max_words=1000, mask=alice_mask)
    # generate word cloud
    wc.generate_from_frequencies(text)

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

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def generateWordCloud():
    words_old = [  #some words to visualize
        { 
            'word': 'this', 
            'size': 55,
            'color': COLOR_RED,
            'font': '\'Indie Flower\', cursive',
            'angle': '45'
        },
        { 
            'word': 'Test', 
            'size': 73,
            'color': COLOR_BLUE,
            'font': '\'Open Sans\', sans-serif',
            'angle': '-30'
        },
        { 
            'word': 'kinDA', 
            'size': 153,
            'color': COLOR_GREEN,
            'font': '\'Indie Flower\', cursive',
            'angle': '-150'
        },
        { 
            'word': 'WERKS', 
            'size': 33,
            'color': COLOR_PURPLE,
            'font': '\'Open Sans\', sans-serif',
            'angle': '90'
        }
    ]

    # Read the whole text.
    words = [('chipotle', 55), ('McDonalds', 15), ('burgerking', 12), ('wendies', 41), ('using', 1), ('font', 2), ('randomize', 1), ('yet', 1), ('HHBs', 1), ('knowledge', 1), ('generator', 1), ('everything', 3), ('implementation', 2), ('simple', 2), ('might', 1), ('pixel', 1), ('real', 1), ('designs', 1), ('good', 1), ('without', 1), ('checking', 1), ('trees', 2), ('famous', 1), ('boxes', 1), ('every', 1), ('optimal', 1), ('front', 1), ('integer', 1), ('bit', 2), ('now', 2), ('easily', 1), ('shape', 1), ('fs', 1), ('stuff', 1), ('found', 1), ('works', 1), ('view', 1), ('right', 1), ('force', 1), ('generation', 3), ('hard', 1), ('back', 1), ('second', 1), ('sure', 1), ('Hopefully', 1), ('portrait', 1), ('best', 1), ('really', 2), ('speed', 1), ('method', 2), ('dataset', 2), ('figuring', 1), ('modify', 1), ('understanding', 1), ('represented', 1), ('come', 1), ('generate', 2), ('last', 2), ('fit', 1), ('Tweak', 1), ('study', 1), ('studied', 1), ('turn', 1), ('place', 2), ('isn', 1), ('uses', 2), ('implement', 1), ('sprites', 1), ('adjustable', 1), ('render', 1), ('color', 2), ('one', 1), ('fashion', 1), ('fake', 1), ('cloud', 5), ('size', 2), ('guess', 1), ('working', 1), ('Separate', 1), ('sake', 1), ('placing', 1), ('brute', 1), ('least', 2), ('insider', 1), ('lot', 1), ('basic', 1), ('prototype', 1), ('start', 1), ('empty', 1), ('sort', 1), ('testing', 1), ('spiral', 1), ('overlapping', 1), ('else', 1), ('controller', 1), ('part', 2), ('somewhat', 1), ('varying', 1), ('MySQL', 1), ('quad', 2), ('copy', 1), ('also', 1), ('bundled', 1), ('word', 9), ('algorithm', 2), ('typography', 1), ('will', 1), ('fll', 1), ('following', 2), ('bet', 1), ('perfecting', 1), ('proved', 1), ('orientation', 2), ('wordle', 1), ('JavaScript', 1), ('collision', 2), ('reads', 1), ('want', 1), ('ready', 1), ('compressing', 1), ('apparently', 1), ('check', 1), ('inefficient', 1), ('preferably', 1), ('end', 2), ('thing', 2), ('efficient', 1), ('make', 3), ('note', 1), ('python', 3), ('need', 3), ('complex', 1), ('instead', 1), ('hierarchical', 1), ('used', 1), ('ft', 1), ('see', 1), ('though', 2), ('moving', 1), ('preliminary', 1), ('data', 1), ('fm', 1), ('Figure', 2), ('database', 1), ('author', 1), ('together', 1), ('think', 1), ('provide', 1), ('definitely', 1), ('time', 1), ('position', 2), ('model', 2), ('D3', 1)]
    
    alice_mask = np.array(Image.open(path.join(d,"alice_mask.png")))
    burrito_mask = np.array(Image.open(path.join(d,"burrito2.png")))

    print alice_mask.shape
    print burrito_mask.shape

    # Generate a word cloud image
    wordcloud = WordCloud(
        background_color="white",
        max_words = 1500,
        mask = burrito_mask)
    wordcloud.generate_from_frequencies(words)

    # The pil way (if you don't have matplotlib)
    image = wordcloud.to_image()
    #words = wordcloud.process_text(text)
    #image.show()

    return serveImg(image)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def _save_word_cloud_img(frequencies, file_path):
    """
    ワードクラウドの画像ファイルを指定されたファイルパスに保存する。
    参考：http://amueller.github.io/word_cloud/index.html
    :param frequencies: タブル(単語, 出現頻度)のリスト
    :param file_path: 画像ファイルのパス
    """
    # 日本語フォントのパスが正しく設定されている必要がある。
    font_path = config.JAPANESE_FONT_PATH
    wc = WordCloud(background_color='white', max_font_size=320, font_path=font_path, width=900, height=500)
    wc.generate_from_frequencies(frequencies)
    wc.to_file(file_path)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def create_word_cloud(df, mask_file, font_path):

    mask = np.array(Image.open(mask_file))

    wc = WordCloud(relative_scaling=0.5,
                        mask=mask,
                        prefer_horizontal=1.0,
                        background_color='white',
                        font_path=font_path)

    wc.generate_from_frequencies(df.values)

    return wc

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def word_cloud(dictionary,topic_index,topic_word):
    
    wd={}
    b_1 = np.argsort(topic_word[ipt,:])[::-1]
    cloud_word = [str(dictionary[i])+' ' for i in b_1]
    for j in b_1:
        wd[str(dictionary[j])] = topic_word[topic_index,j]/np.sum(topic_word[topic_index,:])

    huaji = imread('250px.png')
    wc = WordCloud(width=1920, height=1080,background_color="white")
    wc.generate_from_frequencies(wd.items())  
    plt.figure()
    plt.imshow(wc)
    plt.axis('off')
    plt.show()

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_frequencies [as 别名]
def test_generate_from_frequencies():
    # test that generate_from_frequencies() takes input argument dicts
    wc = WordCloud(max_words=50)
    words = wc.process_text(THIS)
    result = wc.generate_from_frequencies(words)

    assert_true(isinstance(result, WordCloud))