pandas 2 选择数据

from __future__ import print_function
import pandas as pd
import numpy as np

np.random.seed(1)
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=['A', 'B', 'C', 'D'])

print(df['A'], df.A)                       # 选取属性值为‘A’的列，两种方法效果相同
print(df[0:3], df['20130102':'20130104'])  # 选取数据的前三行，选取行属性之间的数据（包括了右边属性的数据） 两种方法效果相同

select by label: loc 属性值

# select by label: loc
print(df.loc['20130102'])             #  选取行属性为‘20130102’的数据
print(df.loc[:,['A','B']])            # 选取列属性为‘A’，‘B’的所有数据
print(df.loc['20130102', ['A','B']])  # 选取行属性为‘20130102’，列属性为‘A’，‘B’的数据

select by position: iloc 属性编号

# select by position: iloc
print(df.iloc[3])              # 选取行第4行的数据
print(df.iloc[3, 1])           # 选取第4行第2列的数据
print(df.iloc[3:5,0:2])        # 选取行编号为3,4 列编号为0,1的数据
print(df.iloc[[1,2,4],[0,2]])  # 选取第2,3,5行，第1，3列的数据

mixed selection: ix 标签值+标签标号

# mixed selection: ix
print(df.ix[:3, ['A', 'C']])   # 选取前3行，列属性为‘A’，‘C’的数据

Boolean indexing 布尔

# Boolean indexing
print(df[df.A > 0])            # 选取所有值大于0的数据

下面是所有的输出结果：

print(df)

>                   A         B         C         D
> 2013-01-01  1.624345 -0.611756 -0.528172 -1.072969 
> 2013-01-02  0.865408 -2.301539  1.744812 -0.761207
> 2013-01-03  0.319039 -0.249370  1.462108 -2.060141
> 2013-01-04 -0.322417 -0.384054  1.133769 -1.099891
> 2013-01-05 -0.172428 -0.877858  0.042214  0.582815
> 2013-01-06 -1.100619  1.144724  0.901591  0.502494

print(df['A'])
print('\n')
print(df.A)

> 2013-01-01    1.624345
> 2013-01-02    0.865408
> 2013-01-03    0.319039
> 2013-01-04   -0.322417
> 2013-01-05   -0.172428
> 2013-01-06   -1.100619
> Freq: D, Name: A, dtype: float64


> 2013-01-01    1.624345
> 2013-01-02    0.865408
> 2013-01-03    0.319039
> 2013-01-04   -0.322417
> 2013-01-05   -0.172428
> 2013-01-06   -1.100619
> Freq: D, Name: A, dtype: float64

print(df[0:3])
print('\n')
print(df['20130102':'20130104'])

>                    A         B         C         D
> 2013-01-01  1.624345 -0.611756 -0.528172 -1.072969
> 2013-01-02  0.865408 -2.301539  1.744812 -0.761207
> 2013-01-03  0.319039 -0.249370  1.462108 -2.060141
 
 
>                    A         B         C         D
> 2013-01-02  0.865408 -2.301539  1.744812 -0.761207
> 2013-01-03  0.319039 -0.249370  1.462108 -2.060141
> 2013-01-04 -0.322417 -0.384054  1.133769 -1.099891

# select by label: loc
print(df.loc['20130102'])

> A    0.865408
> B   -2.301539
> C    1.744812
> D   -0.761207
> Name: 2013-01-02 00:00:00, dtype: float64

print(df.loc[:, ['A', 'B']])

>                    A         B
> 2013-01-01  1.624345 -0.611756
> 2013-01-02  0.865408 -2.301539
> 2013-01-03  0.319039 -0.249370
> 2013-01-04 -0.322417 -0.384054
> 2013-01-05 -0.172428 -0.877858
> 2013-01-06 -1.100619  1.144724

print(df.loc['20130102', ['A', 'B']])

> A    0.865408
> B   -2.301539
> Name: 2013-01-02 00:00:00, dtype: float64

# select by position: iloc
print(df.iloc[3])

> A   -0.322417
> B   -0.384054
> C    1.133769
> D   -1.099891
> Name: 2013-01-04 00:00:00, dtype: float64

print(df.iloc[3, 1])

> -0.38405435466841564

print(df.iloc[3:5, 0:2])

>                    A         B
> 2013-01-04 -0.322417 -0.384054
> 2013-01-05 -0.172428 -0.877858

print(df.iloc[[1, 2, 4], [0, 2]])

                   A         C
2013-01-02  0.865408  1.744812
2013-01-03  0.319039  1.462108
2013-01-05 -0.172428  0.042214

# mixed selection: ix
print(df.ix[:3, ['A', 'C']])

>                    A         C
> 2013-01-01  1.624345 -0.528172
> 2013-01-02  0.865408  1.744812
> 2013-01-03  0.319039  1.462108

# Boolean indexing
print(df[df.A > 0])

>                    A         B         C         D
> 2013-01-01  1.624345 -0.611756 -0.528172 -1.072969
> 2013-01-02  0.865408 -2.301539  1.744812 -0.761207
> 2013-01-03  0.319039 -0.249370  1.462108 -2.060141

END