def showPyechartsWordCloud(self, attr, value):
from pyecharts import WordCloud
wordcloud = WordCloud(width=1300, height=620)
wordcloud.add("租房信息词云", attr, value, word_size_range=[20, 100])
wordcloud.render(
r"c:\Users\Administrator\graduation design\spiderResult1\租房信息词云.html"
)
def word_cloud(content):
import jieba, re, numpy
from pyecharts import WordCloud
import pandas as pd
# 去除所有评论里多余的字符
content = content.replace(" ", ",")
content = content.replace(" ", "、")
content = re.sub('[,，。. \r\n]', '', content)
segment = jieba.lcut(content)
words_df = pd.DataFrame({'segment': segment})
# quoting=3 表示stopwords.txt里的内容全部不引用
stopwords = pd.read_csv(stopwords_path,
index_col=False,
quoting=3,
sep="\t",
names=['stopword'],
encoding='utf-8')
words_df = words_df[~words_df.segment.isin(stopwords.stopword)]
words_stat = words_df.groupby(by=['segment'])['segment'].agg(
{"计数": numpy.size})
words_stat = words_stat.reset_index().sort_values(by=["计数"],
ascending=False)
test = words_stat.head(500).values
codes = [test[i][0] for i in range(0, len(test))]
counts = [test[i][1] for i in range(0, len(test))]
wordcloud = WordCloud(width=1300, height=620)
wordcloud.add("影评词云", codes, counts, word_size_range=[20, 100])
wordcloud.render("H:\PyCoding\spider_maoyan\picture\c_wordcloud.html")
def wordcloudtest(self):
from pyecharts import WordCloud
import random
wd = WordCloud('回帖数词云图')
key, value = wd.cast(self.wordcloud)
shapes = [
'circle', 'cardioid', 'diamond', 'triangle-forward', 'triangle',
'pentagon', 'star'
]
wd.add('', key, value, shape=shapes[0])
wd.render(r'pic\主要发帖人词云图.html')
print('词云图测试成功')
def SimpleWordCloudMap(self):
'''
a lower-class wordcloud
:return:
'''
from pyecharts.charts.wordcloud import WordCloud
attr, value = self.Cast(name="comment_content")
wordcloud = WordCloud(self.title,
"数据来源：豆瓣电影",
title_pos="center",
width=1200,
height=600)
wordcloud.add("",
attr,
value,
shape="diamond",
word_size_range=[20, 100])
if self.saved_file_type is None:
wordcloud.render(os.path.join(self.path, "wordcloud.png"))
elif self.saved_file_type == "html":
wordcloud.render(os.path.join(self.path, "wordcloud.html"))
def showPyechartsWordCloud(self, attr, value):
from pyecharts import WordCloud
wordcloud = WordCloud(width=1300, height=620)
wordcloud.add("", attr, value, word_size_range=[20, 100])
wordcloud.render()
if element in data:
return '圣族'
for element in a[10]:
if element in data:
return '网文'
for element in a[11]:
if element in data:
return '境界'
data['data_clean'] = data['元尊贴吧标题'].apply(data_clean)
data = data.dropna(subset=['data_clean'])
data_count = data.groupby('data_clean').count()
#print(data.head())
#print(data_count.index)
#点云
name = list(data_count.index)
value = list(data_count.values)
mask = np.array(Image.open('爬虫测试\元尊\元尊.jpg'))
wordcloud = WordCloud(
width=800,
height=450,
background_color='#f2eada', # feeeed
mask=mask)
wordcloud.add("", name, value, word_size_range=[20, 100], shape='diamond')
wordcloud.render(r'E:\vscode_code\爬虫测试\元尊\元尊词频.html')
