def gen_wordcloud(text, filename):
# 1). 强调分割中有问题的词;
# jieba.suggest_freq(('微博'), True)
# jieba.suggest_freq(('热搜'), True)
# 2). 难点: 如何切割中文, jieba, lcut
result = jieba.lcut(text)
# print(result)
# 绘制词云
# 3). 打开图片， 获取图片的数据信息;
imgObj = Image.open('./doc/wordcloud.jpg')
img_mask = np.array(imgObj)
# print(img_mask)
# 4). 创建词云对象， 设置属性
wcObj = wordcloud.WordCloud(
mask=img_mask, # 数据如何填充到图片
background_color="snow", # 北京颜色
font_path="/usr/share/fonts/wqy-zenhei/wqy-zenhei.ttc", # 如果是中文， 指定字体库(fc-list :lang=zh)
min_font_size=5, # 图片中最小的字体大小
max_font_size=50, # 图片中最小的字体大小
width=1000, # 图片宽度
height=1000, # 高
)
# 5). 生成图片;
# 词云绘制时， 默认之处理字符串类型， 怎么分隔每个单词? 必须以逗号分隔符分割
wcObj.generate(",".join(result))
wcObj.to_file(filename)
print("生成图片%s成功......." %(filename))
def generate_ciyun():
try:
# 调用jieba的lcut()方法对原始文本进行中文分词，得到string
string = " ".join(get_news_content())
print(string)
#string = " ".join(txtlist)
# 构建并配置词云对象w
w = wordcloud.WordCloud(width=1000,
height=700,
background_color='black',
font_path='/Library/Fonts/华文行楷.ttf')
# 将string变量传入w的generate()方法，给词云输入文字
w.generate(string)
#检测词云文件是否存在，如果存在就删除
my_file = 'key_word_ciyun.png'
if os.path.exists(my_file):
# 删除文件，可使用以下两种方法。
os.remove(my_file)
# os.unlink(my_file)
else:
print
'no such file:%s' % my_file
# 将词云图片导出到当前文件夹
w.to_file('key_word_ciyun.png')
except Exception as e:
print(e)
def create_word_cloud(f):
f = remove_stop_words(f)
cut_text = nltk.word_tokenize(f)
cut_text = " ".join(cut_text)
wc = wordcloud.WordCloud(max_words=100, width=2000, height=1200)
wc.generate(cut_text)
wc.to_file("WordCloud.jpg")
def draw_wordcloud(self):
#texts = self.find_freq()
texts = self.remove_stopword()
wcloud = wordcloud.WordCloud('./data/D2Coding.ttf',
relative_scaling=0.2,
background_color='white').generate(
" ".join(texts))
plt.figure(figsize=(12, 12))
plt.imshow(wcloud, interpolation='bilinear')
plt.axis('off')
plt.show()
def get_and_show_keywords(total):
keywords_list = []
for item in total['keywords']:
keywords_list.append(item)
keywords_list = '|'.join(keywords_list)
wc = wordcloud.WordCloud(background_color='black',
max_words=3000,
scale=1.5).generate(keywords_list)
plt.figure(figsize=(14, 8))
plt.imshow(wc)
plt.axis('off')
plt.show()
def wordcloudshow(keywordsfrequency):
background_image = imread("heart.jpg")
wordcloudobject = wordcloud.WordCloud(
font_path="/library/fonts/microsoft/simsun.ttf",
mask=background_image,
background_color="white",
max_font_size=300,
random_state=30).generate_from_frequencies(keywordsfrequency, 200)
image_colors = ImageColorGenerator(background_image)
wordcloudobject.recolor(color_func=image_colors)
plt.imshow(wordcloudobject)
plt.axis("off")
plt.show()
def createWordCloud(data, font_path, mask_path, background_color, max_words):
if background_color == "-1":
background_color = "white"
if max_words == "-1":
max_words = 300
if font_path == "-1" and mask_path == "-1":
w = wordcloud.WordCloud(background_color=background_color,
max_words=int(max_words))
elif font_path == "-1" and mask_path != "-1":
mask = imread(mask_path)
w = wordcloud.WordCloud(background_color=background_color,
mask=mask,
max_words=int(max_words))
elif font_path != "-1" and mask_path == "-1":
w = wordcloud.WordCloud(background_color=background_color,
font_path=font_path,
max_words=int(max_words))
else:
mask = imread(mask_path)
w = wordcloud.WordCloud(background_color=background_color,
mask=mask,
font_path=font_path,
max_words=int(max_words))
w.generate(data['DM'])
timec = time.ctime()
timec = timec.replace(":", "-")
save_path = "【" + data['ownerName'] + "】" + data[
'videoName'] + " @BV：" + data['bvid'] + " @时间：" + str(
timec) + "(词量：" + str(
max_words) + " ,分词模式：" + data['mode'] + ")" + ".png"
blacklist = r"[\/\\\:\*\?\"\<\>\|]"
save_path = ".\\" + re.sub(blacklist, "", save_path)
w.to_file(save_path)
def wordcloud_plot(self, txtfile, imgfile, para):
# txtfile = "./text/我的孤独是一座花园.txt"
# imgfile = "./images/动物/1225574.png"
self.bct = barchart()
self.bct.wordfreqsum(txtfile)
self.wfreq = self.bct.wfreq # 词频字典
txt = open(txtfile, encoding='UTF-8').read()
txtlist = jieba.lcut(txt)
string = " ".join(txtlist)
para['stopwords'] = jieba.lcut(para['stopwords'])
mk = imageio.imread(imgfile)
# 设定参数
self.wc = wordcloud.WordCloud(
width=para["width"],
height=para['height'],
background_color='white',
font_path=para['font_path'],
mask=mk,
max_words=para['number'],
scale=para['scale'],
stopwords=para['stopwords'],
contour_width=para['contour_width'],
relative_scaling=para['relative_scaling'],
colormap=para['colormap']) # matplotlib colormap
if para['swf'] == 0:
self.wc.generate(string) # 先生成对象，然后考虑着色
else:
print(self.wfreq)
self.wc.generate_from_frequencies(self.wfreq)
#清除原来的图像
self.axes.clear()
if para['tc'] == 0:
self.axes.imshow(self.wc)
else:
image_colors = ImageColorGenerator(mk)
wc_color = self.wc.recolor(color_func=image_colors)
self.axes.imshow(wc_color)
self.draw()
def buildTags2WordCloud(self,tags):
text = {}
for (word,flag),weight in tags:
if 'n' == flag:
self.n_s.append(word)
elif 'ns' == flag:
self.ns_s.append(word)
elif 'vn' == flag:
self.vn_s.append(word)
text[word] = weight
w = wordcloud.WordCloud(
font_path = '/usr/share/fonts/truetype/SIMKAI.TTF',
width = 1000,
height = 700,
background_color = 'white',
color_func = self.__color_fun__
)
w.generate_from_frequencies(text)
from spider.io import settings
cloud_img = settings.FILE_ROOT_PATH + str(hash(self.user_url)) +'.png'
w.to_file(cloud_img)
return cloud_img
from wordcloud import wordcloud
if __name__ == '__main__':
key = '1'
with open('pure_json_data\\' + key + '.json', 'r', encoding="utf-8") as f:
data = json.loads(f.read())
with open('other_data\\a', 'r', encoding="utf-8") as sf:
stopWords = sf.read().split("\n")
all_contents = ''
for i in data: #put all comments together
for content in i['content']:
all_contents += content
word = jieba.cut(
all_contents
) #use jieba api to break down all words so can be put in use
presentive = []
for i in word:
if i not in stopWords:
presentive.append(i)
wc = wordcloud.WordCloud(font_path='msyh',
width=1920,
height=1080,
background_color='white')
wc.generate(" ".join(presentive))
wc.to_file('pic\\' + key + '_period(word).png')
# 1.read word
test = open("test.txt", 'r', encoding='utf-8').read()
print(test)
# 2.seperate word
cut_test = jieba.cut(test)
# 3. merge with space
res = ' '.join(cut_test)
# 4.generate word cloud
wc = wordcloud.WordCloud(
font_path='迷你简太极.ttf',
background_color='white', # 背景颜色
width=1000,
height=600,
max_font_size=50, # 字体大小
min_font_size=10,
mask=plt.imread('cloud.jpg'), # 背景图片
max_words=1000)
wc.generate(res)
wc.to_file('wc_res.png')
# 5.display image
plt.figure('wc_res.png') # 图片显示的名字
plt.imshow(wc)
plt.axis('off') # 关闭坐标
plt.show()
# 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(15) # 获取前10最高频的词
print(word_counts_top10) # 输出检查
word_counts_top10 = str(word_counts_top10)
# 词频展示
mask = np.array(Image.open('background.jpg')) # 定义词频背景
img_colors = ImageColorGenerator(mask) # 提取背景图片颜色
wc = wordcloud.WordCloud(
font_path='simfang.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=180, # 字体最大值
background_color='white',
width=640,
height=480,
scale=0.6,
colormap='binary',
)
wc.generate_from_frequencies(word_counts) # 从字典生成词云
#wc.recolor(color_func=img_colors) #重新上色
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.png')
from selenium import webdriver
import sys
import numpy as np
from PIL import Image
import time
from wordcloud import wordcloud, STOPWORDS, ImageColorGenerator
import matplotlib.pyplot as plt
driver=webdriver.Chrome()
driver.get('https://www.youtube.com/watch?v=9eX-HRFwCnU')
driver.execute_script('window.scrollTo(1, 500);')
#now wait let load the comments
time.sleep(10)
driver.execute_script('window.scrollTo(1, 3000);')
comment_div=driver.find_element_by_xpath('//*[@id="contents"]')
comments=comment_div.find_elements_by_xpath('//*[@id="content-text"]')
mimg=np.array(Image.open("C:/Users/Sony/Downloads/images (1).jpg"))
mcolour=ImageColorGenerator(mimg)
text="".join(r.text for r in comments)
wordcloud1 =wordcloud.WordCloud(stopwords=set(STOPWORDS),background_color="white",mask=mimg,contour_width=2,contour_color='yellow',max_font_size=40)
wordcloud1.generate(text)
plt.figure(figsize=(10,10))
plt.imshow(wordcloud1.recolor(color_func=mcolour), interpolation='bilinear')
plt.axis("off")
plt.show()
import jieba
from PIL import Image
from wordcloud import wordcloud
import matplotlib.pyplot as plt
import numpy as np
#英文词云
wc = wordcloud.WordCloud()
words = wc.generate("Choose a life of action, not one of ostentation.")
wc.to_file("./picture/英文词云.png")
#中文词云
wc = wordcloud.WordCloud("font_path='C:/Windows/Fonts/simhei.ttf")
text = "今天是个好日子"
cut_text = jieba.cut(text) #分词
cuted = ' '.join(cut_text) #词语之间加空格
words = wc.generate(cuted)
wc.to_file("./picture/中文词云.png")
##生成带形状的词云
text = open("./Data/微博评论数据女排20191230.csv", 'r', encoding='UTF-8').read()
words_cuted = jieba.cut(text)
results = " ".join(words_cuted)
wc = wordcloud.WordCloud(mask=np.array(Image.open("./picture/china.jpg")),
font_path="C:\\Windows\\Fonts\\msyh.ttc",
background_color='white').generate(results)
# 显示词云
plt.imshow(wc, interpolation='bilinear')
plt.axis("off")
plt.show()
wc.to_file("./picture/形状词云.png")
word_list = []
for sent in resl:
word_list.append(sent)
stop_list = []
stop = collections.Counter(word_list)
for x in stop.keys():
if stop[x] > 200:
stop_list.append(x)
elif stop[x] < 10:
stop_list.append(x)
for st in stop_list:
stop.pop(st)
#生产词云
cloud = wordcloud.WordCloud(
font_path="./q.ttf",
background_color='black',
max_words=400, #最大号字体，如果不指定则为图像高度
max_font_size=100, #画布宽度和高度，如果设置了msak则不会生效
width=600,
height=400,
margin=2, #词语水平摆放的频率，默认为0.9.即竖直摆放的频率为0.1
prefer_horizontal=0.8)
wc = cloud.generate_from_frequencies(stop)
# news = ts.guba_sina(show_content=True)
# print(news.ix[3])
plt.imshow(wc) #不现实坐标轴
plt.axis(
'off'
) #绘制词云 #plt.figure(dpi = 600) image_colors = ImageColorGenerator(color_mask) #plt.imshow(wc.recolor(color_func=image_colors)) 重新上色，
plt.show()
import numpy as np # 矩阵运行
from matplotlib import pyplot as plt # 绘图,数据可视化
from wordcloud import wordcloud # 词云
from PIL import Image # 图形处理
import sqlite3
conn = sqlite3.connect('movie250.db')
cs = conn.cursor()
sql = 'select introduction from movie'
data = cs.execute(sql)
text = ''
for item in data:
text = text + item[0]
# print(item)
# print(text)
cs.close()
conn.close()
cuts = jieba.cut(text)
strs = ' '.join(cuts)
print(len(strs))
img = Image.open(r'kk2.jpeg')
img_arr = np.array(img) # 将图片转成数组
wc = wordcloud.WordCloud(background_color='white',
mask=img_arr,
font_path='msyh.ttc').generate_from_text(strs)
fig = plt.figure(1)
plt.imshow(wc)
plt.axis('off')
plt.show()
# parts=re.split('[^\w\u4e00-\u9fff]+',comment)#过滤非中文和非英文
# for ele in parts:
# if len(ele) >0:
# sentence.append(ele)
##########################################################################
with open('pure_json_data\\all_comments.json', 'r', encoding="utf-8") as f:
data_all = json.loads(f.read())
for content in data_all:
sentences = re.split('[^\w\u4e00-\u9fff]+', content)
for ele in sentences:
if len(ele) > 0:
sentence.append(ele)
print(sentence)
###########################################################################
presentive = []
for i in sentence:
if any(word in i for word in emotionwords):
# for word in emotionwords:
# if word in sentence:
presentive.append(i)
# break
print(presentive)
wc = wordcloud.WordCloud(font_path='msyh',
width=3840,
height=2160,
background_color='white')
wc.generate(" ".join(presentive))
wc.to_file('pic\\' + key + '(sentence)-keywords.png')
h = randint(0, 48)
s = int(100.0 * 255.0 / 255.0)
l = int(100.0 * float(randint(60, 120)) / 255.0)
return "hsl({}, {}%, {}%)".format(h, s, l)
#stopword设置，没有用到
stopWORD = []
stopWORD.append("国家")
stopWORD.append("中国")
#词云configuration
w = wordcloud.WordCloud( \
width = 3000, height = 2100,\
scale =4, background_color = "white",color_func = random_color_func, stopwords = stopWORD,
mask=abel_mask, max_words=100,
font_path = "msyh.ttc"
)
w.generate(txt)
w.to_file("职位词频2.jpg")
#将底版和词云融合
img1 = Image.open("a.jpg")
img2 = Image.open("职位词频2.jpg")
img_1 = img1.resize(img2.size)
img = Image.blend(img_1, img2, 0.9)
img.save("职位词频3.png")
#w.recolor(color_func=image_colors)
returning = begining.flow_R()
content = returning[0]
Num = returning[1]
print(type(content))
contents = 0
for x in range(len(content)):
contents = str(contents) + str(content[x])
tfidf = jieba.analyse.extract_tags(contents, topK=10, withWeight=False)
wordcloud.random_color_func(word=None,
font_size=None,
position=None,
orientation=None,
font_path=None,
random_state=None)
image1 = PIL.Image.open(
r'C:\\Users\\Administrator\\Desktop\\pac\\1017\\ciyun\\item.JPG')
MASK = np.array(image1)
WC = wordcloud.WordCloud(font_path='STFANGSO.TTF',
max_words=2000,
mask=MASK,
height=400,
width=400,
background_color='white',
repeat=False,
mode='RGBA')
st1 = re.sub('[，。、“”‘ ’]', '', str(tfidf))
conten = ' '.join(jieba.lcut(st1))
con = WC.generate(conten)
plt.imshow(con)
WC.to_file('C:\\Users\\Administrator\\Desktop\\pac\\1017\\ciyun\\test.png')
plt.axis("off")
def getSubjectivity(text):
return TextBlob(text).sentiment.subjectivity
#Create a function to get polarity
def getPolarity(text):
return TextBlob(text).sentiment.polarity
#Create two new columns
df['Subjectivity'] = df['Tweets'].apply(getSubjectivity)
df['Polarity'] = df['Tweets'].apply(getPolarity)
df
# Plot the Word Cloud
allWords = ' '.join( [twts for twts in df['Tweets']] )
wordCloud = wordcloud.WordCloud(width = 500, height=300, random_state = 21, max_font_size = 119).generate(allWords)
plt.imshow(wordCloud, interpolation= "bilinear")
plt.axis('off')
plt.show()
#Create a function to compute the negative, neutral and positive analysis
def getAnalysis(score):
if score <0:
return 'Negative'
elif score ==0:
return 'Neutral'
else:
return 'Positive'
df['Analysis'] = df['Polarity'].apply(getAnalysis)
data = []
with open('/tmp/passwd') as f:
for line in f:
result1 = re.split(r'\s|:|/', line)
# 如果item存在数据并且不是空格或者数字， 则继续进行处理;
result2 = [
item for item in result1
if not re.findall(r'\s+|\d+', item) and item
]
# print(result2)
data.extend(result2)
# 2). 打开图片， 获取图片的数据信息;
imgObj = Image.open('./doc/wordcloud.jpg')
img_mask = np.array(imgObj)
# print(img_mask)
#
# 3). 创建词云对象， 设置属性
wcObj = wordcloud.WordCloud(
mask=img_mask,
background_color="snow",
min_font_size=5,
max_font_size=50,
width=1000,
height=1000,
)
# 4). 生成图片;
# 词云绘制时， 默认之处理字符串类型， 怎么分隔每个单词? 必须以逗号分隔符分割
wcObj.generate(",".join(data))
wcObj.to_file('doc/wcObj.png')
videoid = input("Please Enter Video ID: ")
outputformat = "dataframe"
data = ytc.get_comments(googleapikey, videoid, outputformat)
cs = "result"
data.to_csv(cs, index=True)
df = pd.read_csv(cs)
title_words = list(df["textDisplay"].apply(lambda x: x.split()))
title_words = [x for y in title_words for x in y]
wc = wordcloud.WordCloud(width=1200,
height=500,
collocations=False,
background_color="Azure",
colormap="viridis").generate(" ".join(title_words))
plt.figure(figsize=(15, 10))
plt.imshow(wc, interpolation="nearest")
_ = plt.axis("off")
plt.show()
if __name__ == "__main__":
import pandas as pd
dataset = pd.read_csv(cs)
X = dataset['textDisplay']
X.to_csv("comments.csv", index=True)
re = pd.read_csv("comments.csv")
