def main():
wiki = wikipedia.page('Web scraping')
text = wiki.content
text = re.sub(r'==.*?==+', '', text)
text = text.replace('\n', '')
# black square
wordcloud = WordCloud(width=3000,
height=2000,
random_state=1,
background_color='black',
colormap='Set2',
collocations=False,
stopwords=STOPWORDS).generate(text)
#wordcloud = WordCloud(width = 3000, height = 2000, random_state=1, background_color='salmon', colormap='Pastel1', collocations=False, stopwords = STOPWORDS).generate(text)
wordcloud.to_file("wordcloud1.png")
# Thumb
mask = np.array(Image.open('upvote.png'))
wordcloud = WordCloud(width=3000,
height=2000,
random_state=1,
background_color='black',
colormap='Set2',
collocations=False,
stopwords=STOPWORDS,
mask=mask).generate(text)
wordcloud.to_file("upvote.png")
def wordCloud():
#reads the words from a txt file
tags = open("path/to/file", "r").read().split("\n")
#reads the words from a csv file(used to display the frequency of words)
dataset = pd.read_csv("path/to/file/file_name.csv")
#display frequency of each word
print(
pd.Series(np.concatenate([word.split()
for word in dataset.Tag])).value_counts())
#dictionary with the frequecy of each word
tagFreq = Counter()
for word in tags:
tagFreq[word] += 1
#cloud mask from local machine
mask = np.array(
Image.open(path.join("path/to/mask/file", "mask_file_name.png")))
#cloud mask from an online resource
#mask = np.array(Image.open(requests.get('http://www.clker.com/cliparts/O/i/x/Y/q/P/yellow-house-hi.png', stream=True).raw))
wordcloud = WordCloud(width=1000,
height=900,
background_color='white',
relative_scaling=.8,
mask=mask).generate_from_frequencies(tagFreq)
#save the word cloud as a png file
wordcloud.to_file("myfile.png")
plt.imshow(wordcloud)
plt.axis("off")
plt.show()
def get_wordcloud(image,font,sw,word,result):
wordcloud = WordCloud(scale=15, font_path=font, mask=image, stopwords=sw, background_color='white',
max_words=80000,max_font_size=10, random_state=42)
wordcloud.generate(word)
img_colors = ImageColorGenerator(image)
plt.imshow(wordcloud.recolor(color_func=img_colors))
plt.imshow(wordcloud)
plt.axis('off')
plt.show()
wordcloud.to_file(result)
print('Task Done!')
def Plot_WordCloud(text, catdog):
print("\nOK. The wordcloud for \n".format(catdog))
#Create wordclouds
wordcloud = WordCloud(background_color="black", width=1600, height=800).generate(text)
# Display the generated image:
# the matplotlib way:
plt.figure( figsize=(20,10), facecolor='k')
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
plt.show()
wordcloud.to_file(graph_directory+ catdog+".png")
def create_topic_wordcloud_img(self, topic, frec):
# Create wordcloud img for the topic using words frequencies e.g:
#frec = [('hi', 0.01), ('bye', 0.5), ('wow', 0.3), ('dfg', 0.1), ('efef', 0.9)]
import wordcloud
wordcloud = wordcloud.WordCloud(
prefer_horizontal=1,
ranks_only=True,
background_color='white',
mask=imread('topic_distribution_visualization/red-circle.png'
)).fit_words(frec)
picture_path = '%stopic_wordcloud/topic%s.png' % (
self._viz_output_path, topic)
wordcloud.to_file(picture_path)
pass
def show_wordcloud(data, title=None):
wordcloud = WordCloud(
background_color='beige',
stopwords=stopwords_c,
max_words=60,
max_font_size=30,
scale=3,
random_state=1 # random value
).generate(str(data))
fig = plt.figure(1, figsize=(12, 12))
plt.axis('off')
if title:
fig.suptitle(title, fontsize=20)
fig.subplots_adjust(top=2.3)
plt.imshow(wordcloud)
plt.show()
wordcloud.to_file("D:\\1. Merene\\NLP\Challenge 4\\C_W_Cloud_st.png")
def get_wc_data(self, request, pk='reviewID'):
allData = ""
stopwords = set(STOPWORDS)
for i in range(12):
reviews = YelpReviews.objects.filter(business=pk,
date__month=i + 1)
for x in reviews:
allData = allData + x.review
wordcloud = wc(stopwords=stopwords,
max_words=25,
background_color="white").generate(allData)
wordcloud.to_file("./images/image{}.png".format(i))
oo = WordCloudPhoto(title="x",
image="images/image{}.png".format(i))
oo.save()
serializer = WordCloudPhotoSerializer(oo, many=True)
response = {'message': 'Word Cloud Data', 'result': serializer.data}
return Response(response, status=status.HTTP_200_OK)
def generate_pic(frequency, name):
wordcloud = WordCloud(
width=900, # 词云图片宽度，默认400像素
height=383, # 词云图片高度 默认200像素
background_color='black', # 词云图片的背景颜色，默认为黑色
font_path='Microsoft Yahei.ttf', # 指定字体路径 默认None
font_step=1, # 字号增大的步进间隔 默认1号
min_font_size=4, # 最小字号 默认4号
max_font_size=None, # 最大字号 根据高度自动调节
max_words=30, # 最大词数 默认200
scale=15, # 默认值1。值越大，图像密度越大越清晰
prefer_horizontal=0.9, # 默认值0.90，浮点数类型。表示在水平如果不合适，就旋转为垂直方向，水平放置的词数占0.9%
relative_scaling=0,
# 默认值0.5，浮点型。设定按词频倒序排列，上一个词相对下一位词的大小倍数。有如下取值：“0”表示大小标准只参考频率排名，“1”如果词频是2倍，大小也是2倍
collocations=False, # 是否包括两个词的搭配
mask=None)
# 根据确诊病例的数目生产词云
wordcloud.generate_from_frequencies(frequency)
# 保存词云
wordcloud.to_file('%s.png' % (name))
"""爬取「后浪」弹幕"""
import requests
import re
import wordcloud
import os
os.chdir(r'.\Module\requests\images')
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36'
}
res = requests.get(
"https://api.bilibili.com/x/player/pagelist?bvid=BV1FV411d7u7&jsonp=jsonp",
headers=headers,
verify=False)
cid = res.json()['data'][0]['cid']
print(cid)
danmu_url = f"https://api.bilibili.com/x/v1/dm/list.so?oid={cid}"
result = requests.get(danmu_url, headers=headers, verify=False).content.decode(
'utf-8') # 如果不设置'verify=False',会引起 SSLError
pattern = re.compile('<d.*?>(.*?)</d>')
danmu_list = pattern.findall(result)
wordcloud = wordcloud.WordCloud(font_path='msyh.ttc', width=900,
height=1600).generate("".join(danmu_list))
wordcloud.to_file('wordcloud.png')
wordmap = {}
for w in wordList:
if not (w in wordmap) and not (w.lower() in stopwords.get_words()):
wordmap[w] = 1
elif not (w.lower() in stopwords.get_words()):
wordmap[w] = wordmap[w] + 1
t = OrderedDict(sorted(wordmap.items(), key=lambda x: x[1], reverse=True))
print(type(t))
# convert list to string and generate
wordcloud = WordCloud(
width=1000, height=500).generate_from_frequencies(wordmap)
plt.figure(figsize=(15, 8))
plt.imshow(wordcloud)
plt.axis("off")
plt.show()
wordcloud.to_file("cloud.png")
plt.close()
print("done")
with open(file_name, 'a') as outfile:
outfile.seek(0)
outfile.truncate()
outfile.write("\n" + "Favortes Given" + "\n")
for key in favorites_given:
outfile.write(str(users[key].encode('utf-8') + " ".encode("utf-8") +
str(favorites_given[key]).encode("utf-8") + "\n".encode("utf-8"),"utf-8"))
outfile.write("\n" + "Favorites Received" + "\n")
for key in favorites_received:
outfile.write(str(users[key].encode('utf-8') + " ".encode("utf-8") +
str(favorites_received[key]).encode("utf-8") + "\n".encode("utf-8"),"utf-8"))
outfile.write("\n" + "Ratio" + "\n")
for key in favorites_received:
j = j + 1
text += " " + col[6]
if "Central Time (US & Canada)" in col[5]: text1 += " " + col[6]
if "Eastern Time (US & Canada)" in col[5]: text2 += " " + col[6]
if "Pacific Time (US & Canada)" in col[5]: text3 += " " + col[6]
counter = 2
# text = tweetmap[23]
stopwords = set(STOPWORDS)
stopwords.update(["https", "http", "ud83d", "ude2d", "ude02", "co"])
# Create and generate a word cloud image:
wordcloud = WordCloud(stopwords=stopwords,
max_font_size=50,
max_words=100,
background_color="white").generate(text)
wordcloud.to_file("first_review.png")
wordcloud1 = WordCloud(stopwords=stopwords,
max_font_size=50,
max_words=100,
background_color="white").generate(text1)
wordcloud1.to_file("second_review.png")
wordcloud2 = WordCloud(stopwords=stopwords,
max_font_size=50,
max_words=100,
background_color="white").generate(text2)
wordcloud2.to_file("third_review.png")
wordcloud3 = WordCloud(stopwords=stopwords,
max_font_size=50,
max_words=100,
background_color="white").generate(text3)
wordcloud3.to_file("fourth_review.png")
cluster_content = '/Users/liziyang/Downloads/CaseWestern-master/cluster_content'
content_list = os.listdir(cluster_content)
# print(content_list)
for elem in content_list:
complete_name = os.path.join(cluster_content, elem)
cluster_name = elem.replace('.csv', '')
print(cluster_name)
f = open(complete_name, 'r').read()
f = f.lower()
f.replace('and', '')
f.replace('the', '')
f.replace('victim', '')
f.replace('the suspect', '')
f.replace('the victim', '')
f.replace('sex crime', '')
f.replace('victim states', '')
wordcloud = WordCloud(background_color="white",
width=1000,
height=860,
margin=2,
stopwords=stopwords).generate(f)
plt.imshow(wordcloud)
plt.axis("off")
plt.title(cluster_name)
plt.show()
wordcloud.to_file('test.png')
# 保存图片,但是在第三模块的例子中 图片大小将会按照 mask 保存
