# 导⼊所需的package
import seaborn as sns #⽤于画图
from bs4 import BeautifulSoup #⽤于爬取arxiv的数据
import re #⽤于正则表达式,匹配字符串的模式
import requests #⽤于⽹络连接,发送⽹络请求,使⽤域名获取对应信息
import json #读取数据,我们的数据为json格式的
import pandas as pd #数据处理,数据分析
import matplotlib.pyplot as plt #画图⼯具
data = [] #初始化
#使⽤用with语句句优势: 1.⾃自动关闭⽂文件句句柄; 2.⾃自动显示(处理理)⽂文件读取数据异常
with open("C:\\Users\\Administrator\\Desktop\\arxiv-metadata-oai-2019.json", 'r') as f:
for idx, line in enumerate(f):
d = json.loads(line)
d = {'abstract': d['abstract'], 'categories': d['categories'],'comments': d['comments']}
data.append(d)
data = pd.DataFrame(data) #将list变为dataframe格式,⽅方便便使⽤用pandas进⾏行行分析C:\Users\Administrator\Desktop
# 使⽤用正则表达式匹配, XX pages
data['pages'] = data['comments'].apply(lambda x: re.findall('[1-9][0-9]* pages', str(x)))
# 筛选出有pages的论⽂文
data = data[data['pages'].apply(len) > 0]
# 由于匹配得到的是⼀一个list,如['19 pages'],需要进⾏行行转换
data['pages'] = data['pages'].apply(lambda x: float(x[0].replace(' pages','')))
统计结果如下:论文平均的页数为17⻚页, 75%的论⽂文在22页以内,最长的论文有56⻚页。
data['pages'].describe().astype(int)
count 9
mean 17
std 16
min 3
25% 7
50% 17
75% 22
max 56
Name: pages, dtype: int32
# 选择主要类别
data['categories'] = data['categories'].apply(lambda x: x.split(' ')[0])
data['categories'] = data['categories'].apply(lambda x: x.split('.')[0])
# 每类论⽂文的平均⻚页数
plt.figure(figsize=(12, 6))
data.groupby(['categories'])['pages'].mean().plot(kind='bar')
<AxesSubplot:xlabel='categories'>
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-8Sonunbe-1611107265755)(output_5_1.png)]
data['figures'] = data['comments'].apply(lambda x: re.findall('[1-9][0-9]* figures', str(x)))
data = data[data['figures'].apply(len) > 0]
data['figures'] = data['figures'].apply(lambda x: float(x[0].replace('figures', '')))
最后我们对论文的代码链接进行提取,为了简化任务我们只抽取github链接:
# 筛选包含github的论⽂文
data_with_code = data[(data.comments.str.contains('github')==True)|(data.abstract.str.contains('github')==True)]
data_with_code['text'] = data_with_code['abstract'].fillna('') + data_with_code['comments'].fillna('')
# 使⽤用正则表达式匹配论⽂文
pattern = '[a-zA-z]+://github[^\s]*'
data_with_code['code_flag'] = data_with_code['text'].str.findall(pattern).apply(len)
并对论⽂文按照类别进行绘图:
data_with_code = data_with_code[data_with_code['code_flag'] == 1]
plt.figure(figsize=(12, 6))
data_with_code.groupby(['categories'])['code_flag'].count().plot(kind='bar')
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-24-6eb836b47fda> in <module>
1 data_with_code = data_with_code[data_with_code['code_flag'] == 1]
2 plt.figure(figsize=(12, 6))
----> 3 data_with_code.groupby(['categories'])['code_flag'].count().plot(kind='bar')
~\anaconda3\lib\site-packages\pandas\plotting\_core.py in __call__(self, *args, **kwargs)
947 data.columns = label_name
948
--> 949 return plot_backend.plot(data, kind=kind, **kwargs)
950
951 __call__.__doc__ = __doc__
~\anaconda3\lib\site-packages\pandas\plotting\_matplotlib\__init__.py in plot(data, kind, **kwargs)
59 kwargs["ax"] = getattr(ax, "left_ax", ax)
60 plot_obj = PLOT_CLASSES[kind](data, **kwargs)
---> 61 plot_obj.generate()
62 plot_obj.draw()
63 return plot_obj.result
~\anaconda3\lib\site-packages\pandas\plotting\_matplotlib\core.py in generate(self)
276 for ax in self.axes:
277 self._post_plot_logic_common(ax, self.data)
--> 278 self._post_plot_logic(ax, self.data)
279
280 def _args_adjust(self):
~\anaconda3\lib\site-packages\pandas\plotting\_matplotlib\core.py in _post_plot_logic(self, ax, data)
1459 name = self._get_index_name()
1460
-> 1461 s_edge = self.ax_pos[0] - 0.25 + self.lim_offset
1462 e_edge = self.ax_pos[-1] + 0.25 + self.bar_width + self.lim_offset
1463
IndexError: index 0 is out of bounds for axis 0 with size 0
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-7djILG7f-1611107265757)(output_10_1.png)]