Python WordCloud.generate_from_text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_text [as 别名]
def word_cloud(csv_file, stopwords_path, pic_path):
    pic_name = csv_file+"_词云图.png"
    path = os.path.abspath(os.curdir)
    csv_file = path+ "\\" + csv_file + ".csv"
    csv_file = csv_file.replace('\\', '\\\\')
    d = pd.read_csv(csv_file, engine='python', encoding='utf-8')
    content = []
    for i in d['content']:
        try:
            i = translate(i)
        except AttributeError as e:
            continue
        else:
            content.append(i)
    comment_after_split = jieba.cut(str(content), cut_all=False)
    wl_space_split = " ".join(comment_after_split)
    backgroud_Image = plt.imread(pic_path)
    stopwords = STOPWORDS.copy()
    with open(stopwords_path, 'r', encoding='utf-8') as f:
        for i in f.readlines():
            stopwords.add(i.strip('\n'))
        f.close()

    wc = WordCloud(width=1024, height=768, background_color='white',
                   mask=backgroud_Image, font_path="C:\simhei.ttf",
                   stopwords=stopwords, max_font_size=400,
                   random_state=50)
    wc.generate_from_text(wl_space_split)
    img_colors = ImageColorGenerator(backgroud_Image)
    wc.recolor(color_func=img_colors)
    plt.imshow(wc)
    plt.axis('off')  
    plt.show() 
    wc.to_file(pic_name)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_text [as 别名]
def cloud_for_document(outfile=None, fulltext=None):
    """Create a wordcloud for the DOCUMENT and save the result in OUTFILE"""
    assert outfile != None
    assert fulltext != None
    wc = WordCloud(width=1024, height=640)
    wc.generate_from_text(fulltext)
    plt.imshow(wc)
    plt.axis("off")
    plt.savefig(outfile, dpi=300)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_text [as 别名]
def generate_wordcloud(text, bgcolor, width, height, max_words, mask):
    if mask is not None:
        mask = _load_mask(mask)
    wc = WordCloud(relative_scaling=.5, width=width, height=height,
                   background_color=bgcolor, mask=mask,
                   max_words=max_words)
    return wc.generate_from_text(text)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_text [as 别名]
def wordcloud_image(text, **kwargs):
    """ Build wordcloud from text """
    format = 'PNG'
    if kwargs.has_key('file_format'):
        format = kwargs.pop('file_format')

    args = default_settings
    args.update(kwargs)

    wc = WordCloud(**args)
    wc.generate_from_text(text)
    img = wc.to_image()
    del wc
    imgbuf = BytesIO()
    img.save(imgbuf, format)
    width, height = img.size
    imgbuf.seek(0)
    del img
    return imgbuf, (width, height)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_text [as 别名]
df = pd.read_csv('music_message.csv', header=None)

text = ''
for line in df[2]:
    text += ' '.join(jieba.cut(line, cut_all=False))
backgroud_Image = plt.imread('job.jpg')
stopwords = set('')
stopwords.update(['封面', 'none介绍', '介绍', '歌单', '歌曲', '我们', '自己', '没有', '就是', '可以', '知道', '一起', '不是', '因为', '什么', '时候', '还是', '如果', '不要', '那些', '那么', '那个', '所有', '一样', '一直', '不会', '现在', '他们', '这样', '最后', '这个', '只是', '有些', '其实', '开始', '曾经', '所以', '不能', '你们', '已经', '后来', '一切', '一定', '这些', '一些', '只有', '还有'])

wc = WordCloud(
    background_color='white',
    mask=backgroud_Image,
    font_path='C:\Windows\Fonts\STZHONGS.TTF',
    max_words=2000,
    max_font_size=150,
    random_state=30,
    stopwords=stopwords
)
wc.generate_from_text(text)
# 看看词频高的有哪些,把无用信息去除
process_word = WordCloud.process_text(wc, text)
sort = sorted(process_word.items(), key=lambda e:e[1], reverse=True)
print(sort[:50])
img_colors = ImageColorGenerator(backgroud_Image)
wc.recolor(color_func=img_colors)
plt.imshow(wc)
plt.axis('off')
wc.to_file("活着.jpg")
print('生成词云成功!')

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import generate_from_text [as 别名]
    stopwords.add('目前')
    stopwords.add('但是')
    stopwords.add('然后')
    stopwords.add('这样')
    stopwords.add('这种')
    stopwords.add('曲唑')
    stopwords.add('如果')
    stopwords.add('戈舍')

    # 导入背景图
    bg_image = plt.imread('/Users/youpeng/zhizhi/beastcancer/timg.jpg')

    # 设置词云参数，参数分别表示：画布宽高、背景颜色、背景图形状、字体、屏蔽词、最大词的字体大小
    wc = WordCloud(
                   scale=4,
                   background_color='white',
                   mask=bg_image,
                   font_path='/System/Library/Fonts/PingFang.ttc',
                   stopwords=stopwords,
                   max_font_size=400,
                   random_state=50,
                   collocations=False
                   )
    # 将分词后数据传入云图
    wc.generate_from_text(words)
    plt.imshow(wc)
    plt.axis('off')  # 不显示坐标轴
    plt.show()
    # 保存结果到本地
    wc.to_file('/Users/youpeng/zhizhi/beastcancer/endocrine.jpg')