Pandas的基本使用

来源：互联网发布：淘宝小号查询源码编辑：程序博客网时间：2024/05/29 04:47

import numpy as npimport pandas as pd#首先创建索引dates = ['2017-01-01', '2017-02-1', '2017-03-01', '2017-04-01', '2017-05', '2017-06-01']dates = pd.to_datetime(dates)print(dates)

DatetimeIndex(['2017-01-01', '2017-02-01', '2017-03-01', '2017-04-01',
'2017-05-01', '2017-06-01'],
dtype='datetime64[ns]', freq=None)

#创建DataFrame对象df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))print(df)

A B C D
2017-01-01 0.470732 1.261291 -1.478082 -0.117008
2017-02-01 0.439358 1.373300 1.463247 -1.508368
2017-03-01 0.894984 1.280350 -0.660829 -1.133081
2017-04-01 1.618866 0.835632 0.547147 0.023842
2017-05-01 -0.129568 -0.540310 1.757176 0.867668
2017-06-01 0.358594 0.656273 1.240374 -1.172496

print(df.columns)

Index(['A', 'B', 'C', 'D'], dtype='object')

print(df.index)

DatetimeIndex(['2017-01-01', '2017-02-01', '2017-03-01', '2017-04-01',
'2017-05-01', '2017-06-01'],
dtype='datetime64[ns]', freq=None)

print(df.values)

[[ 0.47073212 1.26129099 -1.47808151 -0.11700753]
[ 0.43935763 1.37329994 1.46324734 -1.50836817]
[ 0.89498355 1.28035036 -0.66082914 -1.13308051]
[ 1.61886613 0.83563176 0.54714678 0.02384197]
[-0.12956774 -0.54030978 1.7571758 0.86766752]
[ 0.35859426 0.65627347 1.24037368 -1.1724956 ]]

print(df.describe())

A B C D
count 6.000000 6.000000 6.000000 6.000000
mean 0.608828 0.811089 0.478172 -0.506574
std 0.592908 0.719697 1.289665 0.912271
min -0.129568 -0.540310 -1.478082 -1.508368
25% 0.378785 0.701113 -0.358835 -1.162642
50% 0.455045 1.048461 0.893760 -0.625044
75% 0.788921 1.275586 1.407529 -0.011370
max 1.618866 1.373300 1.757176 0.867668

0 0