�� : ��

�� (�� )

�� (��). �� 10 �� 2010 � 2020 �� (�� , �� 10).

import pandas as pd
import matplotlib.pyplot as plt
df = pd.read_csv('ArXiv.csv')
df.columns = ['title', 'abstract', 'categories', 'created', 'id', 'doi']
dfc = df.drop(['title', 'abstract', 'doi', 'id'], axis=1)
dfc['created'] = pd.to_datetime(dfc['created'], dayfirst=False)
dfc['categories'] = df['categories'].map(lambda x: x.rstrip("'[]").lstrip("'[]"))
dfc.loc[:, "categories"] = dfc['categories'].str.split("', '")
dfc.loc[:, 'created'] = dfc.loc[:, 'created'].dt.year
dfc['created']=dfc['created'].astype(int)
df.iloc[4002:4009]
df.iloc[3991]
df.iloc[3998]
df.iloc[4000]
df.iloc[68422:68432]
dfc['created'].value_counts()
labels = ['1992', '1993', '1994', '1995', '1996','1997', '1998', '1999', '2000', '2001','2002', '2003', '2004', '2005', '2006','2007', '2008', '2009', '2010', '2011', '2012', '2013','2014', '2015', '2016', '2017', '2018', '2019', '2020']
data = [3, 1, 7, 115, 84, 146, 200, 236, 296, 356, 431, 397, 455, 509, 661, 564, 924, 2638, 4864, 5437, 5936, 5969, 6237, 6484, 6737, 7027, 7463, 8277, 427]
expl = (0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1)
plt.pie(data, labels=labels, explode=expl)
plt.title('Number of articles by year')

�� , �� Colab

��
ArXiv.csv

��

�������� ���� (������� �� ����)

�� (�� )