pandas中DataFrame的查询

import pandas as pd

import numpy as np

arr = np.random.randn(3,3)

arr

array([[-0.4840499 , -1.10358516, -2.02087998],
       [ 1.47393252, -0.64985477, -0.11712859],
       [-0.44069225, -0.37788616,  0.56497586]])

df = pd.DataFrame(arr,index=('a','b','c'),columns=('A','B','C'))

df

	A	B	C
a	1.440345	0.702222	1.268813
b	0.268986	0.954185	-0.273460
c	-1.187953	0.717754	0.083791

[ ]切片方法

#行选择
df['a':'b']

	A	B	C
a	1.440345	0.702222	1.268813
b	0.268986	0.954185	-0.273460

#列选择
df[['A','C']]

	A	C
a	1.440345	1.268813
b	0.268986	-0.273460
c	-1.187953	0.083791

#行列选择
df['b':'c'][['B','C']]

	B	C
b	0.954185	-0.273460
c	0.717754	0.083791

loc函数(使用索引值)

#行选择
df.loc['a':'b']

	A	B	C
a	1.440345	0.702222	1.268813
b	0.268986	0.954185	-0.273460

#列选择
df.loc[:,['A','C']]

	A	C
a	1.440345	1.268813
b	0.268986	-0.273460
c	-1.187953	0.083791

#行列选择
df.loc['a':'b',['B','C']]

	B	C
a	0.702222	1.268813
b	0.954185	-0.273460

iloc函数(使用索引位置)

#行选择
df.iloc[0:1]

	A	B	C
a	1.440345	0.702222	1.268813

df.iloc[[0]]

	A	B	C
a	1.440345	0.702222	1.268813

#列选择
df.iloc[:,0:1]

	A
a	1.440345
b	0.268986
c	-1.187953

#行列选择
df.iloc[0:2,0:2]

	A	B
a	1.440345	0.702222
b	0.268986	0.954185

at函数(使用索引值访问单个元素)

df.at['a','A']

1.4403454841699048

iat函数(使用索引位置访问单个元素)

df.iat[0,0]

1.4403454841699048

ix函数(loc与iloc的混合)

df.ix[0:2,'A':'C']

/Users/f7689781/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:1: DeprecationWarning: 
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing

See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/indexing.html#ix-indexer-is-deprecated
  """Entry point for launching an IPython kernel.

	A	B	C
a	-0.484050	-1.103585	-2.020880
b	1.473933	-0.649855	-0.117129