Pandas选择数据

dates= pd.date_range('20130101',periods=6)
print(dates)

DatetimeIndex([‘2013-01-01’, ‘2013-01-02’, ‘2013-01-03’, ‘2013-01-04’,
‘2013-01-05’, ‘2013-01-06’],
dtype=‘datetime64[ns]’, freq=‘D’)

df=pd.DataFrame(np.arange(24).reshape(6,4),index=dates,columns=['A','B','C','D'])
print(df)

        A   B   C   D

2013-01-01 0 1 2 3
2013-01-02 4 5 6 7
2013-01-03 8 9 10 11
2013-01-04 12 13 14 15
2013-01-05 16 17 18 19
2013-01-06 20 21 22 23

#两种打印A列的表达方式
print(df['A'],df.A)

2013-01-01 0
2013-01-02 4
2013-01-03 8
2013-01-04 12
2013-01-05 16
2013-01-06 20
Freq: D, Name: A, dtype: int32 2013-01-01 0
2013-01-02 4
2013-01-03 8
2013-01-04 12
2013-01-05 16
2013-01-06 20
Freq: D, Name: A, dtype: int32

print(df[0:3])

       A  B   C   D

2013-01-01 0 1 2 3
2013-01-02 4 5 6 7
2013-01-03 8 9 10 11

print(df['20130103':'20130105'])

         A   B   C   D

2013-01-03 8 9 10 11
2013-01-04 12 13 14 15
2013-01-05 16 17 18 19

#select by lable
#打印具体某一行
print(df.loc['20130103'])

A 8
B 9
C 10
D 11
Name: 2013-01-03 00:00:00, dtype: int32

#打印具体某一行的某列
print(df.loc['20130103',['A','B']])

A 8
B 9
Name: 2013-01-03 00:00:00, dtype: int32

print(df.loc['20130103',['A']])

Name: 2013-01-03 00:00:00, dtype: int32

print(df.iloc[3,1])

13

#切片，打印第二行到第三行,第3列到4列
print(df.iloc[1:3,2:4])

        C   D

2013-01-02 6 7
2013-01-03 10 11

print(df.iloc[[1,3,5],2:4])

        C   D

2013-01-02 6 7
2013-01-04 14 15
2013-01-06 22 23

#筛选大于某个数的df
print(df[df.A>8])

A   B   C   D
2013-01-04  12  13  14  15
2013-01-05  16  17  18  19
2013-01-06  20  21  22  23