def parse_args(arguments):
# prog = 'python wordcloud_cli.py'
parser = make_parser()
args = parser.parse_args(arguments)
if args.colormask and args.color:
raise ValueError('specify either a color mask or a color function')
args = vars(args)
with args.pop('text') as f:
text = f.read()
if args['stopwords']:
with args.pop('stopwords') as f:
args['stopwords'] = set(map(lambda l: l.strip(), f.readlines()))
if args['mask']:
mask = args.pop('mask')
args['mask'] = np.array(Image.open(mask))
color_func = wc.random_color_func
colormask = args.pop('colormask')
color = args.pop('color')
if colormask:
image = np.array(Image.open(colormask))
color_func = wc.ImageColorGenerator(image)
if color:
color_func = wc.get_single_color_func(color)
args['color_func'] = color_func
imagefile = args.pop('imagefile')
return args, text, imagefile
def __main__():
# 当前路径
d = os.path.dirname(__file__) if "__file__" in locals() else os.getcwd()
#读文件
with open(os.path.join(d, 'English.txt'), encoding='utf-8') as file:
text = file.read()
font_path = os.path.join(d, 'GABRWFFR.TTF')
pic = Image.open(os.path.join(d, 'fish.jpg'))
mask = np.array(pic)
# create coloring from image
pic_color = wordcloud.ImageColorGenerator(mask)
w = wordcloud.WordCloud(font_path=font_path,
background_color='white',
mask=mask,
contour_width=3,
contour_color="blue")
w.generate(text)
#recolor wordcloud
w.recolor(color_func=pic_color)
plt.figure()
plt.subplot(1, 2, 1)
plt.imshow(pic)
plt.subplot(1, 2, 2)
plt.imshow(w, interpolation="bilinear")
plt.show()
w.to_file(os.path.join(d, 'fish.png'))
def create_word_cloud():
# 设置词云形状图片,numpy+PIL方式读取图片
# 数据清洗词列表
stop_words = [
'就是', '不是', '但是', '还是', '只是', '这样', '这个', '一个', '什么', '电影', '没有'
]
# 设置词云的一些配置，如：字体，背景色，词云形状，大小,生成词云对象
wc = wordcloud.WordCloud(mask=imread('lianxi/background1.png'),
background_color=None,
stopwords=stop_words,
max_words=250,
scale=4,
mode='RGBA',
min_font_size=10,
max_font_size=70,
random_state=42,
font_path="C:\\Windows\\Fonts\\SimHei.TTF")
# 生成词云
wc.generate(cut_word())
img = imread('lianxi/color.jpg')
cloud_colors = wordcloud.ImageColorGenerator(np.array(img))
wc.recolor(color_func=cloud_colors)
plt.figure(figsize=(20, 20))
plt.rcParams['font.family'] = 'SimHei'
# 开始画图
plt.imshow(wc)
# 为云图去掉坐标轴
plt.axis("off")
plt.savefig('dataout/图7豆瓣电影词语云.png')
def show_cloud(self):
# 读取文件
fn = open('job.txt') # 打开文件
string_data = fn.read() # 读出整个文件
fn.close() # 关闭文件
# 文本预处理
pattern = re.compile(u'\t|\n|\.|-|:|;|\)|\(|\?|"') # 定义正则表达式匹配模式
string_data = re.sub(pattern, '', string_data) # 将符合模式的字符去除
# 文本分词
seg_list_exact = jieba.cut(string_data, cut_all=False) # 精确模式分词
object_list = []
# # 去除模式
# remove_words = [u'；', u'：', u'\xa0', u'有', u'数据', u'开发', u'经验', u'大',
# u'熟悉', u'/', u'。', u' ', u'、', u'技术', u'能力', u'了',u'的',
# u'和',u'1',u'2',u'3',u'4',u'5',u'6',u'7',u'8',u'9',u'0',
# u'等',u'相关',u'学习',u'或',u'了',u'进行',u'者',u'要求',u'描述',
# u'任职',u'以上',u'项目',u'应用',u'业务',u'平台',u'沟通',u'对',u'产品',
# u'设计',u'年',u'优先',u'，',u'’',u'‘',u'及',u'负责',u'工作',u'职位',
# u'具备',u'具有',u'系统',u'良好',u'团队',u'以上学历',u'使用',u'精通',u'公司',
# u'通常', u'如果', u'我们', u'需要'] # 自定义去除词库
#
# for word in seg_list_exact: # 循环读出每个分词
# if word not in remove_words: # 如果不在去除词库中
# object_list.append(word) # 分词追加到列表
filter_words = [
u'Hadoop', u'Spark', u'Hive', u'Flink', u'Hbase', u'hdfs',
u'Python'
] # 自定义需要统计的关键词
# 保留模式
for word in seg_list_exact: # 循环读出每个分词
if word in filter_words: # 如果不在去除词库中
object_list.append(word) # 分词追加到列表
# 词频统计
word_counts = collections.Counter(object_list) # 对分词做词频统计
word_counts_top10 = word_counts.most_common(30) # 获取前10最高频的词
print(word_counts_top10) # 输出检查
# 词频展示
mask = np.array(Image.open('./wordcloud_bg.jpg')) # 定义词频背景
wc = wordcloud.WordCloud(
font_path="./SourceHanSerifSC-Bold.otf", # 设置字体格式
mask=mask, # 设置背景图
max_words=30, # 最多显示词数
max_font_size=400 # 字体最大值
)
wc.generate_from_frequencies(word_counts) # 从字典生成词云
image_colors = wordcloud.ImageColorGenerator(mask) # 从背景图建立颜色方案
wc.recolor(color_func=image_colors) # 将词云颜色设置为背景图方案
plt.imshow(wc) # 显示词云
plt.axis('off') # 关闭坐标轴
plt.show() # 显示图像
plt.imsave("./out.jpg", wc)
def make_word_cloud(object_list):
# 词频展示
print('\n开始制作词云……') # 提示当前状态
word_counts = collections.Counter(object_list)
mask = numpy.array(Image.open(background)) # 定义词频背景
wc = wordcloud.WordCloud(
font_path='file/simfang.ttf', # 设置字体（这里选择“仿宋”）
background_color='white', # 背景颜色
mask=mask, # 文字颜色+形状（有mask参数再设定宽高是无效的）
max_words=number, # 显示词数
max_font_size=150 # 最大字号
)
wc.generate_from_frequencies(word_counts) # 从字典生成词云
wc.recolor(color_func=wordcloud.ImageColorGenerator(mask)) # 将词云颜色设置为背景图方案
plt.figure('词云') # 弹框名称与大小
plt.subplots_adjust(top=0.99,
bottom=0.01,
right=0.99,
left=0.01,
hspace=0,
wspace=0) # 调整边距
plt.imshow(wc, cmap=plt.cm.gray, interpolation='bilinear') # 处理词云
plt.axis('off') # 关闭坐标轴
print('制作完成！') # 提示当前状态
plt.show()
def show_cloud():
# Read all of comments.
total_comment_text = ""
for comment in database.get_comments():
total_comment_text += re.sub('<[^<]+?>', '', comment['text']).replace(
'\n', '').strip() # re用来去除html标签
# Cut sentences to short words.
wordlist = jieba.lcut(total_comment_text)
wordliststr = " ".join(wordlist)
font = os.path.join(os.path.dirname(__file__), "word_cloud_yahei.ttf")
mask = np.array(Image.open(
'word_cloud_mask.png')) # background and shape of the word cloud
# Get the word cloud.
wd = wordcloud.WordCloud(scale=8,
width=1920,
height=1080,
font_path=font,
mask=mask,
max_font_size=100,
min_font_size=12,
background_color="white",
stopwords=get_stop_words()).generate(wordliststr)
image_colors = wordcloud.ImageColorGenerator(mask)
wd.recolor(color_func=image_colors) # color is from the background image
plt.figure()
plt.imshow(wd)
plt.axis("off")
plt.show()
def cloudplot():
# 设置模板图像的路径
target_coloring = imread(r'C:\Users\ctrl\Desktop\heart.jpg')
# 以词频和背景模板为依据生成词云对象
word_cloud = WordCloud(font_path=r'C:\Windows\Fonts\simhei.ttf',
background_color="white",
max_words=2000,
mask=target_coloring).generate_from_frequencies(
AnalyzeData())
# 生成颜色分布
image_color = wordcloud.ImageColorGenerator(target_coloring)
# image_color =
import matplotlib.pyplot as plt
# 仅按照词频、边界、默认颜色生成词云图像
plt.imshow(word_cloud)
plt.axis("off")
plt.figure()
# 重新上色，按照图像色彩分布生成
plt.imshow(word_cloud.recolor(color_func=image_color))
plt.axis("off")
plt.figure()
# 绘制原始图像
plt.imshow(target_coloring, cmap=plt.cm.gray)
plt.axis("off")
plt.show()
word_cloud.to_file(filename + '.png')
def get_wordcloud(): # 词云生成
words_str = ""
with open("jd_comment.txt") as f:
for line in f:
line = re.sub(
u"[0-9\s+.!/,$%^*()?;；:-【】\"\']+|[+—！，;:。？、~@#￥%…&*（）＞＜-]+",
"", line) # 去掉多余字符
if line == "": continue
line = line.replace("\n", "") # 去掉换行符
seg_list = jieba.cut(line, cut_all=False)
words_str += (" ".join(seg_list))
stopwords = stopwordslist()
words = [
word for word in words_str.split(" ")
if word not in stopwords and len(word) > 1
]
word_counts = Counter() # 词频统计
for x in words:
word_counts[x] += 1
mask = np.array(PIL.Image.open(r'./background.jpg'))
wc = WordCloud(font_path=r'C:\Windows\Fonts\SimHei.TTF',
max_words=2000,
mask=mask,
repeat=False)
wc.generate_from_frequencies(word_counts)
image_colors = wordcloud.ImageColorGenerator(
mask) # 可以去掉 # 基于彩色图像生成相应彩色 文字颜色跟随背景图颜色
wc.recolor(color_func=image_colors)
wc.to_file("词云.jpg")
def question_41():
data_name = '汽车之家论坛'
text = open('{}_cut.txt'.format(data_name), 'r', encoding='utf-8').read()
alice_coloring = imread("bk.jpg")
wc = wordcloud.WordCloud(background_color="white",
width=800,
height=600,
mask=alice_coloring,
max_font_size=20,
random_state=1,
max_words=100,
font_path='C:\\Windows\\msyh.ttf')
wc.generate(text)
image_colors = wordcloud.ImageColorGenerator(alice_coloring)
plt.axis("off")
plt.figure()
plt.imshow(wc.recolor(color_func=image_colors))
plt.axis("off")
plt.figure(dpi=300)
plt.axis("off")
wc.to_file('{}_word_cloud.png'.format(data_name))
def create_word_cloud(self, text):
"""
:param word_list: 经过去除标点符号、分词、去停用词后的词列表
:return:
"""
word_list = self.tokenization(text)
word_counts = collections.Counter(word_list) # 对分词做词频统计
word_counts_topK = word_counts.most_common(self.topK) # 获取前K最高频的词
# print(word_counts_topK)
# 词频展示
mask = np.array(Image.open(self.wc_background)) # 定义词频背景
wc = wordcloud.WordCloud(
font_path=self.font_path, # 设置字体格式
mask=mask, # 设置背景图
max_words=self.max_words, # 最多显示词数
max_font_size=self.max_font_size # 字体最大值
)
wc.generate_from_frequencies(word_counts) # 从字典生成词云
image_colors = wordcloud.ImageColorGenerator(mask) # 从背景图建立颜色方案
wc.recolor(color_func=image_colors) # 将词云颜色设置为背景图方案
plt.imshow(wc) # 显示词云
plt.axis('off') # 关闭坐标轴
plt.savefig(os.path.join(self.save_path, self.wc_name))
plt.show() # 显示图像
def title():
import jieba
import jieba.analyse
title = []
jieba.load_userdict('dict.txt')
jieba.analyse.set_stop_words('stop_words.txt')
records5 = collection1.find({})
for record5 in records5:
title.append(record5['title'])
words = "".join(title)
wordlist = jieba.cut(words, cut_all=True)
word_space_split = " ".join(wordlist)
stopwords = set()
mask2 = np.array(Image.open('CR.jpg')) # 定义词频背景
wc2 = wordcloud.WordCloud(
background_color="white",
font_path="fonts/simkai.ttf",
stopwords=stopwords,
mask=mask2, # 设置背景图
max_words=200, # 最多显示词数
max_font_size=100 # 字体最大值
)
wc2.generate(word_space_split) # 从字典生成词云
image_colors = wordcloud.ImageColorGenerator(mask2) # 从背景图建立颜色方案
wc2.recolor(color_func=image_colors) # 将词云颜色设置为背景图方案
plt.imshow(wc2) # 显示词云
plt.axis('off') # 关闭坐标轴
plt.show() # 显示图像
def word_cloud(segment, title):
"""
生成词云
:param bullets: 弹幕列表
:return: 图片url和排名前10的词
"""
word_counts = collections.Counter(segment)
word_counts_top10 = word_counts.most_common(10)
print(word_counts_top10)
# mask = np.array(Image.open(url_for('static',filename='background.jpg'))) # 定义词频背景
# mask = np.array(Image.open('D:/Python Projects/BilibiliRank/app/static/background.jpg')) # 定义词频背景
root_dir = current_app.config['ROOT_DIR']
mask = np.array(Image.open(root_dir + '/static/background.jpg')) # 定义词频背景
wc = wordcloud.WordCloud(
font_path=root_dir+'/static/STFQLBYTJW.ttf', # 设置字体格式
mask=mask, # 设置背景图
max_words=200, # 最多显示词数
max_font_size=100 # 字体最大值
)
wc.generate_from_frequencies(word_counts) # 从字典生成词云
image_colors = wordcloud.ImageColorGenerator(mask) # 从背景图建立颜色方案
wc.recolor(color_func=image_colors) # 将词云颜色设置为背景图方案
# wc.to_file(url_for('static',filename='wordcloud/wordcloud.png'))
r_img_url = '/static/wordcloud/wordcloud' + str(time()) + '.png'
wc.to_file(root_dir + r_img_url)
print('图片生成成功！')
# plt.imshow(wc) # 显示词云
# plt.axis('off') # 关闭坐标轴
# plt.show() # 显示图像
return r_img_url, word_counts_top10
def words_cloud(self, chin_list: list, eng_list: list, rm_words=None):
if rm_words is None:
rm_words = [
'', 'and', 'to', 'the', 'a', 'for', 'our', 'we', 'with', 'in',
'of', 'We', '的', 'be', 'that', 'their', 'as', 'on', 'an', 'is',
'和', 'have', 'are', 'by', 'most', '-', 'where', 'its'
]
words_list = []
remove_words = rm_words
all_list = chin_list + eng_list
for word in all_list:
if word not in remove_words:
words_list.append(word)
word_counts = collections.Counter(words_list)
mask = np.array(Image.open('./wordcloud.jpg'))
wc = wordcloud.WordCloud(
font_path='/r2/dockerfile/py2/fonts/simhei.ttf', # 设置字体格式
mask=mask,
scale=4,
background_color='white',
max_words=2000,
max_font_size=100)
wc.generate_from_frequencies(word_counts)
image_colors = wordcloud.ImageColorGenerator(mask)
wc.recolor(color_func=image_colors)
plt.imshow(wc.recolor(color_func=image_colors),
interpolation="bilinear")
plt.axis('off')
wc.to_file(f'{self.path}/word_cloud.jpg')
def main():
base_logo_path = "../../assets/publiccompany/logos/%s.png"
base_transcript_path = "../../assets/publiccompany/transcripts/%s.txt"
ticker = "gm"
img = Image.open(base_logo_path % ticker)
img = img.resize((1280, 1080))
img_color = np.array(img)
img_color_gen = wordcloud.ImageColorGenerator(img_color)
stop_words = wordcloud.STOPWORDS
[
stop_words.add(word)
for word in ["quarter", "think", "customer", "growth", "Azure"]
]
#img_color_gen = wordcloud.ImageColorGenerator(np.array(Image.open("../../assets/publiccompany/logos/mcd.png")))
#img_mask = ImageOps.invert(img)
img_mask = img
#img_mask.save("nflx-mask.png")
img_mask = np.array(img_mask)
#src_text = open("../../assets/publiccompany/transcripts/nflx.txt").read()
src_text = open(base_transcript_path % ticker).read()
wc = wordcloud.WordCloud(width=1280,
height=720,
mask=img_mask,
stopwords=stop_words,
max_words=1000)
wc.generate(src_text)
wc.recolor(color_func=img_color_gen)
wc.to_file("wc.jpg")
def makewordcloud(self):
content = ''
with open('comment.csv', 'r') as f:
reader = csv.reader(f)
for row in reader:
content += row[1]
content = content + '\n'
jieba.analyse.set_stop_words('stop.txt')
tags = jieba.analyse.extract_tags(content, topK=100, withWeight=True)
word_freq = {}
for v, n in tags:
word_freq[v] = str(int(n * 10000))
word_freq[v] = int(n * 10000)
mask = np.array(Image.open('index.png')) # 定义词频背景
wc = wordcloud.WordCloud(
font_path='C:/Windows/Fonts/simhei.ttf', # 设置字体格式
mask=mask, # 设置背景图
max_words=2000, # 最多显示词数
max_font_size=120, # 字体最大值
background_color='white')
wc.generate_from_frequencies(word_freq) # 从字典生成词云
image_colors = wordcloud.ImageColorGenerator(mask) # 从背景图建立颜色方案
wc.recolor(color_func=image_colors) # 将词云颜色设置为背景图方案
plt.imshow(wc) # 显示词云
plt.axis('off') # 关闭坐标轴
plt.show() # 显示图像'''
def cloudplot():
# 设置词云整体形状
target_coloring = imageio.imread(r'data\alice.png')
# 以词频和背景模板为依据生成词云对象
word_cloud = WordCloud(font_path=r'C:\windows\Fonts\simhei.ttf',
background_color="white", max_words=2000, mask=target_coloring).generate_from_frequencies(AnalyzeData())
# 生成颜色分布
image_color = wordcloud.ImageColorGenerator(target_coloring)
# image_color =
# 仅按照词频、边界、默认颜色生成词云图像
plt.imshow(word_cloud)
plt.axis("off")
plt.figure()
# 重新上色，按照图像色彩分布生成
plt.imshow(word_cloud.recolor(color_func=image_color))
plt.axis("off")
plt.figure()
# 绘制原始图像
plt.imshow(target_coloring, cmap=plt.cm.gray)
plt.axis("off")
plt.show()
word_cloud.to_file(filename + '.png')
def get_wordcloud(self,imagePath,words_str,store_path=''):
background=plt.imread(imagePath) #设定云图背景图案，参数为图片路径，不设置的话云图默认为方形
img = Image.open(imagePath)
width = img.width
height = img.height
wc=wordcloud.WordCloud(mask=background,font_path=self.FONTPATH,background_color='white',width=width,height=height,max_font_size=400,min_font_size=5)
alice_coloring = np.array(img)
image_colors = wordcloud.ImageColorGenerator(alice_coloring)
#font_path是中文字体路径，因为wordcloud库本身只支持英文，需要下载中文字体；
# max_font_size和min_font_size分别设置云图最大词语的大小和最小词语的大
wc.generate(words_str)#生成词云
# show
fig, axes = plt.subplots(1, 3)
axes[0].imshow(wc, interpolation="bilinear")
# recolor wordcloud and show
# we could also give color_func=image_colors directly in the constructor
axes[1].imshow(wc.recolor(color_func=image_colors), interpolation="bilinear")
axes[2].imshow(alice_coloring, cmap=plt.cm.gray, interpolation="bilinear")
for ax in axes:
ax.set_axis_off()
plt.show()
wc.to_file(store_path or self.OUTPUTPATH)#将词云存储到指定路径
def main():
print("@@@@@@@@欢迎来到词云生成器@@@@@@@@")
file_name = input("请输入txt文档所在路径: ")
file_info = readFile(file_name)
print("文件内容读取成功")
txt = cutWords(file_info)
main_choice = getChoice("是否要改变词云形成形状？<1>是 <2>否 ", 1, 2)
color_mask = None
if main_choice == 1:
file_name = input("请输入形状图片所在路径: ")
color_mask = getImage(file_name)
print("获取形状图片信息成功")
image_colors = wordcloud.ImageColorGenerator(color_mask)
plt.ion()
while True:
plt.close(1)
back_color = input("请输入背景颜色的英文单词(red, black, white等): ")
scale = getChoice("请输入图片清晰度(1比较模糊, 4较为清晰) ", 1, 100)
choice = getChoice("是否使用默认字体<1>是 <2>否 ", 1, 2)
font_path = "msyh.ttc"
if choice == 2:
font_path = getFont()
repeat = False
choice = getChoice("是否允许词汇重复出现<1>是 <2>否 ", 1, 2)
if choice == 1:
repeat = True
max_words = getChoice("请输入最大出现词汇数量(默认200): ", 1, 99999)
print("正在生成词云，时间可能较长，请稍后。。。(P.S. 显示时图片可能较模糊，但保存后图片会很清晰)")
w = wordcloud.WordCloud(font_path=font_path,
background_color=back_color,
width=1000,
height=700,
mask=color_mask,
scale=scale,
repeat=repeat,
max_words=max_words)
w.generate(txt)
if main_choice == 1:
choice = getChoice("词云底色是否要与形状图片相同<1>是 <2>否 ", 1, 2)
if choice == 1:
w.recolor(color_func=image_colors)
print("生成图片中。。。")
plt.figure(1)
plt.imshow(w)
plt.axis('off')
plt.pause(0.001)
plt.show()
if getChoice("是否满意<1>是 <2>否 ", 1, 2) == 1:
break
name = input("请输入保存图片名: ")
print("图片保存中。。。")
w.to_file(name + ".png")
name = input("图片保存成功！")
def extract_two(self, file=None):
fn = codecs.open(file, 'r+', encoding='utf-8')
string_data = fn.read()
fn.close()
# 文本预处理
pattern = re.compile(
'[’!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~。“”、：？，【】！（）——↓0-9a-zA-Z\.\.\.\.\.\.]+'
)
# pattern = re.compile(u'\t|\n|\.|-|:|;|\)|\(|\?|"')
string_data = re.sub(pattern, '', string_data) # 将符合模式的字符去除
string_data = string_data.replace('\n', '')
string_data = string_data.replace('\u3000', '')
string_data = string_data.replace('\r', '')
string_data = string_data.replace(' ', '')
logging.info(string_data)
# 文本分词
seg_list_exact = jieba.cut(string_data, cut_all=False) # 精确模式分词
object_list = []
remove_words_custom = [
u'的', u'，', u'和', u'是', u'随着', u'对于', u'对', u'等', u'能', u'都', u'。',
u' ', u'、', u'中', u'在', u'了', u'通常', u'如果', u'我们', u'需要', u'月',
u'日'
] # 自定义去除词库
remove_words = self.parse_multiple_files(
['中文停用词表.txt', '哈工大停用词表.txt', '四川大学机器智能实验室停用词库.txt', '百度停用词表.txt'])
remove_words = remove_words_custom + remove_words
for word in seg_list_exact: # 循环读出每个分词
if word not in remove_words: # 如果不在去除词库中
logging.info('\n')
logging.info(word)
object_list.append(word) # 分词追加到列表
logging.info(object_list)
# 词频统计
word_counts = collections.Counter(object_list) # 对分词做词频统计
word_counts_top10 = word_counts.most_common(10) # 获取前10最高频的词
print(word_counts_top10) # 输出检查
# 词频展示
font_path = r'C:\Windows\Fonts\simfang.ttf'
mask = np.array(Image.open('background.jpg')) # 定义词频背景
wc = wordcloud.WordCloud(
background_color='white', # 设置背景颜色
font_path=font_path, # 设置字体格式
mask=mask, # 设置背景图
max_words=200, # 最多显示词数
max_font_size=200, # 字体最大值
scale=80 # 调整图片清晰度，值越大越清楚
)
wc.generate_from_frequencies(word_counts) # 从字典生成词云
image_colors = wordcloud.ImageColorGenerator(mask) # 从背景图建立颜色方案
wc.recolor(color_func=image_colors) # 将词云颜色设置为背景图方案
plt.figure()
plt.imshow(wc) # 显示词云
plt.axis('off') # 关闭坐标轴
plt.show() # 显示图像
wc.to_file("bb.jpg") # 将图片输出为文件
def parse_args(arguments):
prog = 'python wordcloud_cli.py'
description = ('A simple command line interface for wordcloud module.')
parser = argparse.ArgumentParser(description=description)
parser.add_argument('--text', metavar='file', type=argparse.FileType(), default='-',
help='specify file of words to build the word cloud (default: stdin)')
parser.add_argument('--stopwords', metavar='file', type=argparse.FileType(),
help='specify file of stopwords (containing one word per line) to remove from the given text after parsing')
parser.add_argument('--imagefile', metavar='file', type=argparse.FileType('w'), default='-',
help='file the completed PNG image should be written to (default: stdout)')
parser.add_argument('--fontfile', metavar='path', dest='font_path',
help='path to font file you wish to use (default: DroidSansMono)')
parser.add_argument('--mask', metavar='file', type=argparse.FileType(),
help='mask to use for the image form')
parser.add_argument('--colormask', metavar='file', type=argparse.FileType(),
help='color mask to use for image coloring')
parser.add_argument('--relative_scaling', type=float, default=0,
metavar='rs', help=' scaling of words by frequency (0 - 1)')
parser.add_argument('--margin', type=int, default=2,
metavar='width', help='spacing to leave around words')
parser.add_argument('--width', type=int, default=400,
metavar='width', help='define output image width')
parser.add_argument('--height', type=int, default=200,
metavar='height', help='define output image height')
parser.add_argument('--color', metavar='color',
help='use given color as coloring for the image - accepts any value from PIL.ImageColor.getcolor')
parser.add_argument('--background', metavar='color', default='black', type=str, dest='background_color',
help='use given color as background color for the image - accepts any value from PIL.ImageColor.getcolor')
parser.add_argument('--no_collocations', action='store_true',
help='do not add collocations (bigrams) to word cloud (default: add unigrams and bigrams)')
args = parser.parse_args(arguments)
if args.colormask and args.color:
raise ValueError('specify either a color mask or a color function')
with args.text:
args.text = args.text.read()
if args.stopwords:
with args.stopwords:
args.stopwords = set(map(str.strip, args.stopwords.readlines()))
if args.mask:
args.mask = np.array(Image.open(args.mask))
color_func = wc.random_color_func
if args.colormask:
image = np.array(Image.open(args.colormask))
color_func = wc.ImageColorGenerator(image)
if args.color:
color_func = wc.get_single_color_func(args.color)
args.collocations = not args.no_collocations
args.color_func = color_func
return args
def wordCount(url):
fileName = url[url.rfind('/') + 1:url.rfind('.')]
it.contentInfo(url, True)
# 读取文件
fn = open('../../fileInfo/' + fileName + '.txt')
string_data = fn.read() # 读出整个文件
fn.close() # 关闭文件
# 文本预处理
pattern = re.compile(u'\t|\n|\.|-|:|;|\)|\(|\?|"') # 定义正则表达式匹配模式
string_data = re.sub(pattern, '', string_data) # 将符合模式的字符去除
# 文本分词
seg_list_exact = jieba.cut(string_data, cut_all=False) # 精确模式分词
object_list = []
# 自定义去除词库
remove_words = [
u'的', u'，', u'和', u'是', u'随着', u'对于', u'对', u'等', u'能', u'都', u'。',
u' ', u'、', u'中', u'在', u'了', u'通常', u'如果', u'我们', u'需要', u'…', u':',
u'“', u'”', u'：', u'但', u'型', u'被'
]
for word in seg_list_exact: # 循环读出每个分词
if word not in remove_words: # 如果不在去除词库中
object_list.append(word) # 分词追加到列表
# 词频统计
word_counts = collections.Counter(object_list) # 对分词做词频统计
word_counts_top10 = word_counts.most_common(10) # 获取前10最高频的词
# 输出检查
for item in word_counts_top10:
print item[0], item[1]
# 词频展示
mask = np.array(Image.open('./timg.jpeg')) # 定义词频背景
wc = wordcloud.WordCloud(
font_path='simhei.ttf', # 设置字体格式
mask=mask, # 设置背景图
width=800,
height=600,
max_words=200, # 最多显示词数
max_font_size=100 # 字体最大值
)
# 从字典生成词云
wc.generate_from_frequencies(word_counts)
# 从背景图建立颜色方案
image_colors = wordcloud.ImageColorGenerator(mask)
# 将词云颜色设置为背景图方案
wc.recolor(color_func=image_colors)
# 保存图片
plt.imsave('../../fileInfo/' + fileName + '.png', wc)
# 显示词云
plt.imshow(wc)
# 关闭坐标轴
plt.axis('off')
def show_novel():
# 导入停用词，转换为列表格式
stop_list = []
with open('materials/停用词.txt', 'r') as f:
for line in f.readlines():
stop_list.append(line.strip())
# 导入小说原文
with open('materials/全职高手.txt', 'r', encoding='gbk') as f:
text = f.read()
# 导入词库字典，编码方式必须是utf-8
jieba.load_userdict('materials/词库字典.txt')
# 分词功能的函数，完成分词
def txt_cut(f):
return [w for w in jieba.cut(f) if w not in stop_list and len(w) > 1]
textcut = txt_cut(text)
# 对词频进行简单统计
word_count = pd.Series(textcut).value_counts().sort_values(
ascending=False)[0:20]
# 画出柱状图并保存
fig = plt.figure(figsize=(15, 8))
x = word_count.index.tolist()
y = word_count.values.tolist()
sns.barplot(x, y, palette='BuPu_r')
plt.title('词频Top20')
plt.ylabel('count')
sns.despine(bottom=True)
plt.savefig('词频统计.png', dpi=400)
plt.show()
# 实例化一个词云类，添加分词
fig_cloud = plt.figure(figsize=(15, 5))
# font_path导入中文字体，mask设置词云图案的形状
cloud = wordcloud.WordCloud(font_path='materials/simkai.ttf',
mask=imread('materials/test.jpg'),
mode='RGBA',
background_color=None).generate(
' '.join(textcut))
# 对词的颜色做美化
img = imread('materials/color.jpg')
cloud_colors = wordcloud.ImageColorGenerator(np.array(img))
cloud.recolor(color_func=cloud_colors)
# 调用matplotlib接口
plt.imshow(cloud)
plt.axis('off')
plt.savefig('wordcloud.png', dpi=400)
plt.show()
def plotWordColud(user_id):
user_text, friend_text = "", ""
with open("weibo.csv", 'r') as file:
reader = csv.reader(file)
weibos = list(reader)
with open("Edges.csv", 'r') as file:
reader = csv.reader(file)
edges = list(reader)
friends = []
for edge in edges:
if edge[0] == user_id:
if edge[1] not in friends:
friends.append(edge[1])
if edge[1] == user_id:
if edge[0] not in friends:
friends.append(edge[0])
for weibo in weibos:
if weibo[1] == user_id:
user_text += weibo[2]
if weibo[1] in friends:
friend_text += weibo[2]
user_text_list = segment(user_text)
friend_text_list = segment(friend_text)
user_ = ",".join(user_text_list)
friend_ = ",".join(friend_text_list)
#设定指定的背景
jpg = imread('logo.jpg')
mask = np.array(Image.open('logo.jpg'))
image_colors = wordcloud.ImageColorGenerator(mask)
#保存
wc = WordCloud(background_color="white",
max_words=200,
min_font_size=10,
max_font_size=35,
width=400,
font_path="/Users/wu/Downloads/msyh/msyh.ttf",
mask=mask,
color_func=image_colors)
wc.generate(user_)
file_path = "./wordCloud/user_.png"
wc.to_file(file_path)
wc.generate(friend_)
file_path = "./wordCloud/friend_.png"
wc.to_file(file_path)
def getKeyWords(self):
""" 根据微博文本内容统计关键词 """
text = ""
for weibo in self.weibos:
text += weibo['text']
segs = jieba.cut(text)
wcdict = {}
for word in segs:
if len(word) == 1:
continue
else:
wcdict[word] = wcdict.get(word, 0) + 1
wcls = list(wcdict.items())
wcls.sort(key=lambda x: x[1], reverse=True)
xx = [
'他们', '没有', '自己', '一个', '什么', '这样', '知道', '我们', '这个', '这些', '不过',
'已经', '要是', '觉得', '那样', '而且', "微博", "转发", "通过", "现在", "有人", "时候"
]
for pair in wcls[:10]:
if pair[0] not in xx:
self.keywors.append(pair)
#生成词云
jpg = imread('cc.jpg')
mask = np.array(Image.open('cc.jpg'))
image_colors = wordcloud.ImageColorGenerator(mask)
text_list = []
for (word, cnt) in wcls:
times = min(cnt, 30)
for i in range(times):
text_list.append(word)
yc_text = ",".join(text_list)
if len(yc_text) > 0:
wc = WordCloud(background_color="white",
max_words=300,
min_font_size=15,
repeat=False,
max_font_size=50,
width=400,
font_path="/Users/wu/Downloads/msyh/msyh.ttf",
mask=mask,
color_func=image_colors)
#wc.generate(yc_text)
wc.generate_from_frequencies(dict(wcls))
file_path = "./derived/kw_" + self.user_id + ".png"
wc.to_file(file_path)
def parse(self, response):
a = []
b = []
c = ''
for quote in response.css('.detail_text'):
for i in quote.css('p::text').extract():
a.append(i)
for i in a:
c += i
d = sta(c)
data = Counter(d)
e = data.most_common()
f = ()
g = list(f)
for i in e:
g.append(i)
h = tuple(g)
j = dict(h)
mask = np.array(Image.open(path.join(path.dirname(__file__),
"py.png")))
transformed_mask = np.ndarray((mask.shape[0], mask.shape[1]), np.int32)
for i in range(len(mask)):
transformed_mask[i] = list(map(self.transform_format, mask[i]))
cloud = wordcloud.WordCloud(
background_color="#000",
width=1000,
height=800,
mask=transformed_mask,
collocations=False).generate_from_frequencies(j)
image_colors = wordcloud.ImageColorGenerator(mask)
plt.figure()
# plot words
plt.imshow(cloud.recolor(color_func=image_colors),
interpolation="bilinear")
# remove axes
plt.axis("off")
# show the result
plt.show()
def word_cloud(wordsCnt, i):
mask = np.array(Image.open('wordcloud.jpg')) # 定义词云背景
wc = wordcloud.WordCloud(
font_path='C:/Windows/Fonts/simhei.ttf', # 设置字体格式
mask=mask, # 设置背景图
max_words=200, # 最多显示词数
max_font_size=100 # 字体最大值
)
wc.generate_from_frequencies(wordsCnt) # 从字典生成词云
image_colors = wordcloud.ImageColorGenerator(mask) # 从背景图建立颜色方案
wc.recolor(color_func=image_colors) # 将词云颜色设置为背景图方案
plt.imshow(wc) # 显示词云
plt.axis('off') # 关闭坐标轴
plt.show() # 显示图像
wc.to_file('WordCloud' + str(i)) # 输出文件 设置文件名
def draw_word_cloud(word, graph):
"""画出词云图片，保存到本地，并可视化"""
font_path = 'C:\\Windows\\Fonts\\Deng.ttf' # 设置字体路径
wc = wordcloud.WordCloud(font_path=font_path,
background_color='white',
max_words=200,
mask=graph,
scale=1.5,
random_state=10) # wordCloud参数设置
wc.generate(word)
image_color = wordcloud.ImageColorGenerator(graph)
wc.to_file('word9.png') # 将生成的文件保存起来
plt.imshow(wc.recolor(color_func=image_color))
plt.axis('off')
plt.show()
def get_word_cloud(self,
chinese_slice=False,
stopwords=None,
image_out_name=None):
"""
:param chinese_slice: Whether Use jieba to slice the sentences.
:param stopwords: a set include some words to exclude.
:return:
"""
font_path = self.font_path
if image_out_name is None:
image_out_name = 'word-heart.png'
if chinese_slice:
text = ",".join(self.chat_content)
text_list = jieba.lcut(text)
text = " ".join(text_list)
image_out_name = 'zh-'.__add__(image_out_name)
else:
text = " ".join(self.chat_content)
mk = imageio.imread("heart.png")
# 构建并配置词云对象w，注意要加scale参数，提高清晰度
w = wordcloud.WordCloud(width=1000,
height=700,
background_color='white',
font_path=font_path,
mask=mk,
scale=2,
stopwords=stopwords,
contour_width=1,
contour_color='red')
# 将string变量传入w的generate()方法，给词云输入文字
w.generate(text)
# 展示图片
# 根据原始背景图片的色调进行上色
image_colors = wordcloud.ImageColorGenerator(mk)
plt.imshow(w.recolor(color_func=image_colors))
# 根据原始黑白色调进行上色
# plt.imshow(wc.recolor(color_func=grey_color_func, random_state=3), interpolation='bilinear') #生成黑白词云图
# 根据函数原始设置进行上色
# plt.imshow(wc)
# 隐藏图像坐标轴
plt.axis("off")
plt.show()
# 将词云图片导出到当前文件夹
w.to_file(image_out_name)
def word_cloud_generator(self, font_name="ShangShouXiuYuanTi.ttf"):
origin_img_path = BASE_DIR + '/static/backgrounds/' + self.img_name
new_img_path = BASE_DIR + '/static/resume/images/' + self.img_name
mask_image = imread(origin_img_path, flatten=False)
if self.color_adaption:
image_colors = wc.ImageColorGenerator(mask_image)
word_pic = WordCloud(font_path=font_base_path + font_name,
background_color=self.background_color,
mask=mask_image,
color_func=image_colors).generate(self.text)
else:
word_pic = WordCloud(font_path=font_base_path + font_name,
background_color=self.background_color,
mask=mask_image).generate(self.text)
imsave(new_img_path, word_pic)
return new_img_path
def plot(self):
wc = wordcloud.WordCloud(
background_color='white', # 设置背景颜色
font_path='/System/Library/Fonts/Hiragino Sans GB.ttc', # 设置字体格式
mask=self.mask, # 设置背景图
max_words=200, # 最多显示词数
max_font_size=80, # 字体最大值
scale=128 # 调整图片清晰度，值越大越清楚
)
wc.generate_from_frequencies(self.word_counts) # 从字典生成词云
image_colors = wordcloud.ImageColorGenerator(self.mask) # 从背景图建立颜色方案
wc.recolor(color_func=image_colors) # 将词云颜色设置为背景图方案
wc.to_file(self.output_pic_path) # 将图片输出为文件
plt.imshow(wc) # 显示词云
plt.axis('off') # 关闭坐标轴
plt.show() # 显示图像
