Python WordCloud.to_file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 to_file [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 to_file [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 to_file [as 别名]
def generateWordCloud(node, contribs, wordsToShow=None, normalize=True, normMin=0, normMax=1):
    contrib = contribs[node]
    
    if (normalize):
        contrib = normalizeContrib(contrib, normMin, normMax)
    
    # generate text
    text = generateText(contrib, wordsToShow)
    
    # load mask
    d = path.dirname(__file__)
    circle_mask = imread(path.join(d, "black_circle_mask_whitebg.png"))
    
    # gen word cloud
    wc = WordCloud(background_color="white", max_words=2000, mask=circle_mask)
    wc.generate(text)

    # store to file
    wc.to_file(path.join(d, "node.png"))

    # show
    useColorFunc = False #normalize
    if (useColorFunc):
        plt.imshow(wc.recolor( color_func=pos_neg_color_func ))
    else:
        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 to_file [as 别名]
    def generate_wc(self, background_color='#ffffff'):
        """generate wordcloud and save to file"""
        # fig_kw = dict(figsize=(self.width/self.dpi, self.height/self.dpi),
        #               dpi=self.dpi)
        self.get_exclude_words()
        try:
            imgpath = os.path.join(self.curdir, self.wordcloud_mask)
            arr = np.array(Image.open(imgpath))
            # Other masks can be extracted from
            # Font-Awesome (http://minimaxir.com/2016/05/wordclouds/)

            # Download font or use the default one
            font_path = get_font(self.font_name)
            if self.allow_font_change:
                logger.info('Using {} font'.format(font_path))
            # print(font_path)

            wc = WordCloud(width=self.width, height=self.height,
                           font_path=font_path, colormap=self.cmap,
                           stopwords=self.exclude_words,
                           background_color=background_color, mode='RGBA',
                           mask=arr).generate(self.text)

            self.make_img_file()
            wc.to_file(self.img_file)
            self.error_in_wordcloud_gen = None

            self.font_name = None  # reset to default

        except Exception as e:
            self.error_in_wordcloud_gen = e

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
def run():
    f = open(u'words2.txt', 'r').read()
    words = list(jieba.cut(f))
    a = []
    for w in words:
        if len(w) > 1:
            a.append(w)
    text = r' '.join(a)
    
    bg = np.array(Image.open('bg.jpg'))
    wordcloud = WordCloud(
            background_color = 'white',
            #width = 1500,
            #height = 960,
            #margin = 10,
            mask = bg,
            font_path='C:/Windows/Fonts/simkai.ttf',
            ).generate(text)

    image_colors=ImageColorGenerator(bg)

    plt.imshow(wordcloud.recolor(color_func=image_colors))
    plt.axis('off')
    plt.show()
    wordcloud.to_file('words_result3.png')
    return

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
def wordCloud(text_array,name,keyword=""):
	new_text_arr=[]
	if keyword is not "":
		keyword=keyword.split(" ")[1]
	for text in text_array:
		if keyword in text:
			new_text_arr.append(text)

	text_array=new_text_arr

	cloud_text=""
	for text in text_array:
		cloud_text+=text+" "

	m_stopwords=['police','traffic','sir']

	for word in m_stopwords:
		STOPWORDS.add(word)

	image_mask = os.path.join(BASE_DIR, 'static/tool/img/nebula.png')
	coloring = imread(image_mask)
	
	wordcloud = WordCloud(stopwords=STOPWORDS,background_color="white",mask=coloring,ranks_only=True,max_words=50).generate(cloud_text)
	filename=os.path.join(BASE_DIR, 'static/tool/img/'+name+'.png')

	image_colors = ImageColorGenerator(coloring)
	wordcloud.recolor(color_func=image_colors)
	wordcloud.to_file(filename)
	data_uri = open(filename, 'rb').read().encode('base64').replace('\n', '')

	img_tag = '<img src="data:image/png;base64,{0}" style="height:400px;">'.format(data_uri)
	
	layout=wordcloud.layout_
	words_colours={}
	count=1
	for lo in layout:
		entry={}
		entry['word']=lo[0][0]
		color=lo[len(lo)-1]
		color=color[4:]
		color=color[:-1]
		color_split=color.split(',')
		color_num=[int(x) for x in color_split]
		color_hex='#%02x%02x%02x' % tuple(color_num)
		# print color_num
		entry['color']=color_hex
		words_colours[count]=entry
		count+=1

	# print words_colours
	list_html=""
	cap=51
	if cap>len(words_colours):
		cap=len(words_colours)

	for i in range(1,cap):
		list_html+='<li class="list-group-item" ><a class="cloud-key-'+name+'" href="#" style="color:'+words_colours[i]['color']+'">'
		list_html+="#"+str(i)+" "+words_colours[i]['word']+'</a></li>'

	return (img_tag,list_html)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
def generate_cloud():
    d = path.dirname(__file__)
    janice = open(path.join(d, 'messages.txt')).read()
    group_mask = misc.imread(path.join(d, "mask.png"), flatten=True)
    wc = WordCloud(background_color="white", max_words = 2000, mask=group_mask)
    wc.generate(text)
    wc.to_file(path.join(d, "masked.jpg"))

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
    def wordcloudplot_focus(self, yizhongzhazha=None, backimage=None):
        """Do wordcloud plots for contacts. need to run relationship()
        first to get self._relationship.
        Parameters
            yizhongzhazha: pandas object by loading the data
            backimage: background image file's directory

        Returns: basic word cloud plots saved in files
        """
        if yizhongzhazha is None:
            print("Need load message table first.")
            return
        if self._contacts_topN is None:
            print("need to run relationship() first.")
            return
        if backimage is not None:
            custompic = imread(backimage)
        else:
            custompic = None
        if not os.path.exists('./wordcloud'):
            os.makedirs('./wordcloud')
        wordcloud = WordCloud(background_color="white", mask=custompic,
                              max_words=2000,scale=3)
        for k in range(len(self._contacts_topN)):
            text=self._relationship.iloc[:,k]
            text_to_wordcloud=[]
            for i in range(len(text)):
                text_to_wordcloud.append((text.index.values[i]+' ')*text[i])
            text=''.join(text_to_wordcloud)
            wordcloud.generate(text)
            wordcloud.to_file("./wordcloud/"+self._relationship.columns[k]+'2.png')

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
def make_word_cloud(text, save_path, background_color='black'):
    # text expected to a string or a list of [(word, count), ...]
    from wordcloud import WordCloud
    import os

    def col_fun(word, *args, **kw):
        return '#333'

    if type(text) == str:
        big_string = text
    else:
        big_string = ''
        for word in text:
            big_string = big_string + ''.join((word[0]+' ') * word[1])

    # print 'trying to make cloud: %s' % save_path
    # print os.getcwd()
    wc = WordCloud(background_color=background_color,
                   color_func=col_fun,
                   max_words=10000,
                   height=200,
                   width=700,
                   font_path='app/static/fonts/NanumScript.ttc').generate(big_string)
    wc.generate(big_string)
    wc.to_file('app/%s' % save_path)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
def create_word_cloud(filename):
    # 读取文件内容
    text = open("{}.txt".format(filename), encoding='utf-8').read()

    # 注释部分采用结巴分词
    # wordlist = jieba.cut(text, cut_all=True)
    # wl = " ".join(wordlist)

    # 设置词云
    wc = WordCloud(
        # 设置背景颜色
        background_color="white",
        # 设置最大显示的词云数
        max_words=2000,
        # 这种字体都在电脑字体中，window在C:\Windows\Fonts\下，mac下可选/System/Library/Fonts/PingFang.ttc 字体
        font_path='C:\\Windows\\Fonts\\simfang.ttf',
        height=500,
        width=500,
        # 设置字体最大值
        max_font_size=60,
        # 设置有多少种随机生成状态，即有多少种配色方案
        random_state=30,
    )

    myword = wc.generate(text)  # 生成词云 如果用结巴分词的话，使用wl 取代 text， 生成词云图
    # 展示词云图
    plt.imshow(myword)
    plt.axis("off")
    plt.show()
    wc.to_file('signature.png')  # 把词云保存下

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
def txt2pic(txt_file, out_png, font_path, mask_file):
  text_address = path.abspath(txt_file)
  text = open(text_address).read()   #读取文本
  text_cut = jieba.cut(text)   #分词
  new_textlist = ' '.join(text_cut)   #组合
  pic_address = path.abspath(mask_file)
  pic = imread(pic_address)  #读取图片
  pic_color = ImageColorGenerator(pic)   #根据图片生成颜色函数
  wc = WordCloud(background_color='white',    #构造wordcloud类
    mask=pic,
    width = 750,
    height = 750,
    max_font_size = 80,
    random_state=30,
    font_path=font_path,
    max_words=500,
    min_font_size=2,
    color_func=pic_color
  )
  wc.generate(new_textlist)    #生成词云图
  plt.figure()    #画图
  plt.imshow(wc)
  plt.axis("off")
  plt.show()
  wc.to_file(out_png)   #保存图片

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
    def create_wordclouds(self, text, name_of_cloud, additional_stop_list, max_words, width, height, bigram = False):
        text_nopunc = self.remove_punctuation(text, "", "")
        text_lower = text_nopunc.lower()
        stop = self.stopwords
        stop.extend(additional_stop_list)
        text_nostop = self.remove_stopword(text_lower, stop)
        tokens = wt(text_nostop)
        text_lem = self.lemmatize(tokens)
        tokens_lem = wt(text_lem)
        my_bigrams = nltk.bigrams(tokens_lem)
        if bigram:
            bigram_merged=list()
            for line in my_bigrams:
                bigram_merged.append(line[0]+' ' + line[1])
            counts = collections.Counter(bigram_merged)
        else:
            counts = collections.Counter(tokens_lem)
        final = counts.most_common(max_words)
        max_count = max(final, key=operator.itemgetter(1))[1]
        final = [(name, count / float(max_count))for name, count in final]

        # tags = make_tags(final, maxsize=max_word_size)
        # create_tag_image(tags, name_of_cloud+'.png', size=(width, height), layout=3, fontname='Crimson Text', background = (255, 255, 255))

        # temp_cloud = " ".join(text for text, count in final)
        word_cloud = WordCloud(font_path="fonts/Georgia.ttf",
            width=width, height=height, max_words=max_words, stopwords=stop)
        word_cloud.fit_words(final)
        word_cloud.to_file(name_of_cloud + ".png")

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
def main(save_files = False, db_filename = '../output/database.sqlite'):
    conn = sqlite3.connect(db_filename)
    c = conn.cursor()

    # Retrieve papers
    c.execute('''SELECT *
                 FROM Papers''')

    paper_content = c.fetchall()
    conn.close()

    titles = ''

    for pc in paper_content:
        titles += pc[1]

    # A Marvin Minsky mask
    mask = np.array(Image.open("../files/minsky_mask.png"))

    wc = WordCloud(background_color="white", max_words=2000, mask=mask, stopwords=STOPWORDS.copy())
    # Generate word cloud
    wc.generate(titles)
    
    if (save_files):
        # Store to file
        wc.to_file("../files/title_cloud.png")
    
    # Show word cloud
    plt.imshow(wc)
    plt.axis("off")
    # Show mask
#    plt.figure()
#    plt.imshow(mask, 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 to_file [as 别名]
def makecloud(name):
    cnt = 0
    # file=open('age_over54_train/KABarron.txt')
    file = open('extracted_tweets/'+name + ".txt")
    demo_text = ""
    stop = stopwords.words('english')
    for line in file:
        if cnt < 2:
            cnt += 1
        elif cnt < 52:
            line = line.strip().replace("'", "").replace('"', '')
            if str(line).startswith("RT"):
                continue
            else:
                newline = [i for i in line.split() if i not in stop]
                finsent = ""
                for word in newline:
                    if "@" in word or "https" in word or ".co" in word or "http" in word:
                        continue
                    else:
                        finsent += word + " "

                demo_text += finsent + " "
            cnt += 1
        else:
            break
    filename = 'static/'+ name + '_cloud.png'
    wordcloud = WordCloud(max_font_size=500,width=900,height=600,background_color='white',prefer_horizontal=0.5,font_path="a_song_for_jennifer/a song for jennifer.ttf").generate(demo_text)
    wordcloud.to_file(filename)
    return str(name + '_cloud.png')

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import to_file [as 别名]
def create_word_cloud(filename):
    text = open('{}.txt'.format(filename),encoding='utf-8').read()
    print(type(text))
    # print(text)
    #结巴分词
    wordlist = jieba.cut(text,cut_all=False)
    wl = " ".join(wordlist)

    #设置词云
    wc = WordCloud(
        #设置背景颜色
        background_color='white',
        #设置最大的显示词云数
        max_words=2000,
        #字体
        font_path="../python_space/like.ttf",
        height=1200,
        width=1600,
        #设置有多少中随机生成状态,即有多少种配色方案
        random_state=30,
    )
    myword = wc.generate(wl)#生成词云
    #展示词云
    plt.imshow(myword)
    plt.axis("off")
    plt.show()
    wc.to_file('py_book.png')#把词云保存下来