Python STOPWORDS.add方法代码示例

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def wordcloud(datafile):

    #remove stop words, the most common words in a language
    vectorizer=CountVectorizer(stop_words='english')

    for word in vectorizer.get_stop_words():
        STOPWORDS.add(word)
    STOPWORDS.add("said")

    pony_mask = np.array(Image.open("../pinkyB.jpg"))
    wc = WordCloud(background_color="black", max_words=2000, mask=pony_mask, stopwords=STOPWORDS)

    #init dictionary with the five categories
    categoriesSet = set(datafile["Category"])
    categoriesDict = dict.fromkeys(categoriesSet,"")

    #Conditional Selection
    # business = datafile.ix[datafile["Category"]=="Business"]
    # print business["Content"].size

    #fill index with data from cv
    for index, row in datafile.iterrows():
        categoriesDict[row["Category"]] += str(row["Content"])

    for category, text in categoriesDict.iteritems():
        wc.generate(text)
        image = wc.to_image()
        image.save("../wordcloud/wordcloud_" + category + ".jpg")
    return

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [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 STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def generateWordCloud(text, stop):
    d = path.dirname(outputdir)

    for w in stop:
        STOPWORDS.add(w)

    # Generate the wordcloud without the stop words    
    wordcloud = WordCloud(stopwords=STOPWORDS).generate(text)

    # Draw the positioned words to a PNG file.
    wordcloud.to_file(path.join(d, 'diabetes-wordcloud.png'))

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def cloudplot(person):

    person = re.sub(r'\+', ' ', person)

    text = GetTextRange(Emails, person)
    text = rmBoring(rmNonAlpha(text)).decode('ascii', 'ignore')

    plt.clf()

    d = path.dirname(path.abspath(__file__))

    hilcolor = np.array(Image.open(path.join(d, "static/img/hillarylogo.jpg")))

    wc = WordCloud(background_color="white", max_words=150, mask=hilcolor,
               stopwords=STOPWORDS.add("said"),
               max_font_size=80, random_state=42,
               relative_scaling = 0.5)


    wc.generate(text)
    image_colors = ImageColorGenerator(hilcolor)

    plt.imshow(wc.recolor(color_func=image_colors))
    plt.axis("off")

    fig = plt.gcf()
    img = StringIO.StringIO()
    fig.savefig(img)
    img.seek(0)

    return send_file(img, mimetype='image/png')

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def create_wordcloud(posts):
	wordcloud_str=' '.join(post['message'] for post in posts) #join all posts together
	aces_mask=imread("aces.png") #add aces mask
	wc=WordCloud(background_color="BLACK", mask=aces_mask, stopwords=STOPWORDS.add("will")) #don't include the word "will" in the wordcloud
																							#(not an interesting word and took up a large chunk of the wordcloud)
	wc.generate(wordcloud_str)
	plt.axis("off")
	plt.imshow(wc)
	plt.show()
	wc.to_file("aces_wordcloud.png")

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def generate_wc(content):
    path = r'fzzqhj.TTF'
    bg_pic = imread('mo.png')  # 读取一张图片文件
    image_colors = ImageColorGenerator(bg_pic)  # 从背景图片生成颜色值
    wc = WordCloud(font_path=path, background_color="white",
                   mask=bg_pic,
                   stopwords=STOPWORDS.add("said"),
                   max_font_size=40,
                   color_func=image_colors,
                   random_state=42)
    wc = wc.generate(content)
    wc.to_file(c.outputs_pictures_path + 'result.jpg')

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def make_word_cloud(data):
  text = ''
  for d in data:
    text = text + d[0] + ' '

  # Generate a word cloud image
  wordcloud = WordCloud(stopwords=STOPWORDS.add('watson')).generate(text)

  # Display the generated image:
  # the matplotlib way:
  import matplotlib.pyplot as plt
  plt.imshow(wordcloud)
  plt.axis("off")
  plt.show()

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def mainProcess(usernames):
	print "Processing "+str(len(usernames)-1)+" usernames"
	words4=""
	loginFacebook(driver)
	timeread=time.time()
 	time0=time.clock()

	for username in usernames:
		if len(username) is not 0: 
			username=username.strip()
			time1=time.clock() 
			count, words3 =produce3(username) 
			module.Database.edit2(username, count, conn)
			time2=time.clock()
			words4=words4+" "+words3

 	
 	time3=time.clock()
 	timeread=time.time()-timeread
 	print "TOTAL TIME"
 	print time3-time0
 	print timeread
 	more_stopwords =["ja", "aga", "kui", "siis", "tongue", "nii", "ka", "et", "see", "ma","oma","oli", "emoticon", "ei","ning", "seda", "või", "smile", "grin", "Kas", "kes", "veel"]
 	for more in more_stopwords: 
 		STOPWORDS.add(more)
 	utf=["Translation", "nüüd", "või", "ära", "Kas"]
  	for u in utf: 
  		words4=words4.replace(u, "")
 	wordcloud = WordCloud(stopwords=STOPWORDS).generate(words4)
	image = wordcloud.to_image()
	image.save("words.png","PNG")
	driver.close() 
 	driver.quit 
 	conn.commit()
 	conn.close() 
	print "Done"

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def create_cloud(word, img, out_path):

    # Read the whole text.
    # text = open(word_path).read()
    text = word.read().decode('utf-8')
    # read the mask image
    # taken from
    # http://www.stencilry.org/stencils/movies/alice%20in%20wonderland/255fk.jpg
    alice_mask = np.array(Image.open(img))
    # alice_mask = np.array(img_path)
    wc = WordCloud(font_path = '华文黑体.ttf' ,background_color="white", max_words=2000, mask=alice_mask,
                   stopwords=STOPWORDS.add("said"), width=1000, height=2300, ranks_only=True, mode='RGBA')
    # generate word cloud
    wc.generate(text)
    # wc.generate_from_frequencies([()])
    # store to file
    wc.to_file(out_path)

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def WordCloudTopic( items , imagePath = None):
    # Generate a word cloud image
    
    if imagePath:
    	alice_coloring = np.array(Image.open(imagePath))

    	wc = WordCloud(background_color="white", max_words=200, mask=alice_coloring,
                   stopwords=STOPWORDS.add("said"),
                   max_font_size=300)
    	# generate word cloud
    	wc.generate_from_frequencies(items)
    	image_colors = ImageColorGenerator(alice_coloring)
    	plt.imshow(wc.recolor(color_func=image_colors))
    else:
    	wc = WordCloud(background_color="white", max_words=300,
        max_font_size=40, random_state=42)
    	wordcloud = wc.generate_from_frequencies(items)    
    	plt.imshow(wordcloud)
    plt.axis("off")
    plt.show()

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def generate_wc(text = "Hello World"):
    #if int(time.time()*10)%10 in [0]:
    d = path.dirname(__file__)


    # read the mask image
    alice_coloring = np.array(Image.open(path.join(d, '..','static','images',"heart.png")))

    wc = WordCloud(background_color="white", max_words=2000, mask=alice_coloring,
                   stopwords=STOPWORDS.add("said"),
                   max_font_size=40, random_state=42)
    # generate word cloud
    wc.generate(text)

    # generate word cloud image and save it 
    filename = "wordcloud.png"
    wc.to_file(path.join(d,'..','static','images',filename))
    del wc

    return filename

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def main():
    parser = argparse.ArgumentParser(description='Generate word cloud')
    parser.add_argument('artist', help='Artist to be searched')
    args = parser.parse_args()
    artist = string_to_url(args.artist)
    #artist = "Gaslight Anthem"

    api_url = "http://lyrics.wikia.com/api.php?func=getArtist&artist=%s&fmt=realjson" % (artist, )
    data = json.load(urllib2.urlopen(api_url))
    art_data = data['albums']

    songs_by_album = [album['songs'] for album in art_data]
    songs = sum(songs_by_album, [])
    lyrics = ""
    for song in songs:
        song = song.strip(bad_chars)
        lyrics += get_lyrics(string_to_url(song), artist)
        wc = WordCloud(background_color="white", max_words=2000,stopwords=STOPWORDS.add("said"))
        if not args.sum:
            wc.generate(lyrics)
            wc.to_file("%s_%s.png" %(artist,song,))

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def wordcloud(wordSource):
    #writes origional catagory list to text file
    d = os.path.dirname(__file__)
    file = open("catagory.txt", 'w')
    for item in wordSource:
        file.write("%s\n" % item)
    thefile = open(os.path.join(d, "catagory.txt")).read()

    #adds words to exclude list
    STOPWORDS.add("chronic")
    STOPWORDS.add("disease")
    STOPWORDS.add("obstructive")
    STOPWORDS.add("status")

    # generate word cloud
    wordcloud = WordCloud(stopwords=STOPWORDS,
        background_color="white",
        width = 650,
        height = 250).generate_from_text(thefile)

    #re-colers and saves wordcloud as png
    wordcloud.recolor(color_func=grey_color_func, random_state=3)
    wordcloud.to_file("wordcloud.png")

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def cloud_word_with_mask(file_name):
	text = open(file_name).read()
	# read the mask / color image
	# amazon_coloring = imread('amazon-logo_grey.png')

	wc = WordCloud(background_color="white", max_words=200, #mask=amazon_coloring,
	               stopwords=STOPWORDS.add("said"),
	               max_font_size=200, random_state=42, width=1800, height=1000)
	# generate word cloud
	wc.generate(text)

	# create coloring from image
	# image_colors = ImageColorGenerator(amazon_coloring)

	# recolor wordcloud and show
	# we could also give color_func=image_colors directly in the constructor
	# plt.imshow(wc.recolor(color_func=image_colors))
	plt.figure()
	plt.imshow(wc)
	plt.axis("off")
	# plt.show()
	plt.savefig(file_name.split('.')[0] + '.png')

# 需要导入模块: from wordcloud import STOPWORDS [as 别名]
# 或者: from wordcloud.STOPWORDS import add [as 别名]
def generateWordcloud(wordlist, outfile, title, nwords=100):
    """

    :param wordlist: words in a list
    :param outfile: name of the output file to which to store the figure
    :param title: title of the figure
    :param nwords: maximum number of words to plot

    :return: None
    """
    # generate word cloud
    wc = WordCloudSMN(background_color="white", max_words=nwords,
                      width=800, height=400,
                      stopwords=STOPWORDS.add("looking"),
                      max_font_size=80, random_state=42)
    wc.generate_SMN(wordlist)

    # generate the figure
    plt.figure(figsize=(16, 16))
    plt.title(title)
    plt.imshow(wc)
    plt.axis("off")
    plt.savefig(outfile)
    plt.close()