python-DataFrame数据选择方法

DataFrame数据选择方法

将数据框看成字典

1. 把dataframe当作由若干个series对象构成的字典

import numpy as np
import pandas as pd

area = pd.Series({'California': 423967,'Texas': 695662,
                  'Nwe York':141297,'Florida':170312,'Illinois':149995})
pop = pd.Series({'California': 38332521,'Texas': 26448193,
                  'Nwe York':19651127,'Florida':19552860,'Illinois':12882135})
data = pd.DataFrame({'Area':area,'Pop':pop})
data

	Area	Pop
California	423967	38332521
Texas	695662	26448193
Nwe York	141297	19651127
Florida	170312	19552860
Illinois	149995	12882135

data.Pop

California    38332521
Texas         26448193
Nwe York      19651127
Florida       19552860
Illinois      12882135
Name: Pop, dtype: int64

data['Area']

California    423967
Texas         695662
Nwe York      141297
Florida       170312
Illinois      149995
Name: Area, dtype: int64

#添加新列
data['Density'] = data['Pop'] / data['Area']
data

	Area	Pop	Density
California	423967	38332521	90.413926
Texas	695662	26448193	38.018740
Nwe York	141297	19651127	139.076746
Florida	170312	19552860	114.806121
Illinois	149995	12882135	85.883763

2. 将dataframe看作二维数组

#用values属性查看数组数据
data.values

array([[4.23967000e+05, 3.83325210e+07, 9.04139261e+01],
       [6.95662000e+05, 2.64481930e+07, 3.80187404e+01],
       [1.41297000e+05, 1.96511270e+07, 1.39076746e+02],
       [1.70312000e+05, 1.95528600e+07, 1.14806121e+02],
       [1.49995000e+05, 1.28821350e+07, 8.58837628e+01]])

data.T

	California	Texas	Nwe York	Florida	Illinois
Area	4.239670e+05	6.956620e+05	1.412970e+05	1.703120e+05	1.499950e+05
Pop	3.833252e+07	2.644819e+07	1.965113e+07	1.955286e+07	1.288214e+07
Density	9.041393e+01	3.801874e+01	1.390767e+02	1.148061e+02	8.588376e+01

# 通过 pandas索引器 loc iloc ix
print(data.iloc[:1,:1])
print(data.loc[:'Texas',:'Pop']) # 按照列名索引
print(data.ix[:2,:'Pop']) #目前混合索引已经弃用

              Area
California  423967
              Area       Pop
California  423967  38332521
Texas       695662  26448193
              Area       Pop
California  423967  38332521
Texas       695662  26448193


d:\python3.6\lib\site-packages\ipykernel_launcher.py:4: 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
  after removing the cwd from sys.path.

# loc 的花式索引
data.loc[data.Density > 100 ,['Pop','Density']]

# 索引后更改数据 
data.iloc[0,2] = 90
data

	Area	Pop	Density
California	423967	38332521	90.000000
Texas	695662	26448193	38.018740
Nwe York	141297	19651127	139.076746
Florida	170312	19552860	114.806121
Illinois	149995	12882135	85.883763

3.其他取值方法

# 对数据直接过滤
data[data.Density > 100]

	Area	Pop	Density
Nwe York	141297	19651127	139.076746
Florida	170312	19552860	114.806121