Pandas统计分析
pandas数据的基本统计分析
和numpy的函数近似
import pandas as pd
dates = pd.date_range('20130101',periods=10)
dates
DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
'2013-01-05', '2013-01-06', '2013-01-07', '2013-01-08',
'2013-01-09', '2013-01-10'],
dtype='datetime64[ns]', freq='D')
import numpy as np
df = pd.DataFrame(np.random.randn(10,4),index=dates,columns=['A','B','C','D'])
df
A | B | C | D | |
---|---|---|---|---|
2013-01-01 | -1.587560 | -0.198819 | 0.720054 | 1.921686 |
2013-01-02 | 0.296288 | 1.876570 | 0.338344 | 0.597835 |
2013-01-03 | -1.832852 | 0.752045 | 2.184984 | -0.157722 |
2013-01-04 | -0.650829 | 1.690322 | -1.145963 | -0.798702 |
2013-01-05 | -0.729986 | -0.494417 | 2.166254 | 1.131232 |
2013-01-06 | -1.759444 | -1.104058 | 0.462934 | 2.050315 |
2013-01-07 | 0.760111 | -1.753986 | 0.104831 | 1.075343 |
2013-01-08 | 0.096572 | 0.383660 | 0.604831 | 0.715224 |
2013-01-09 | 0.126292 | 1.025429 | 0.019330 | -0.417396 |
2013-01-10 | -0.179047 | 0.175366 | 0.826219 | -0.451984 |
df.describe() # 快速统计结果
A | B | C | D |
---|