pandas取值

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/5/24 15:03
# @Author  : zhang chao
# @File    : s.py
from scipy import linalg as lg
#按标签选择
#通过标签选择多轴

import pandas as pd
import numpy as np

dates = pd.date_range(‘20170101‘, periods=6)
df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=list(‘ABCD‘))
print("df:")
print(df)
print(‘-‘*50)
#通过索引选择
print("df.loc[:,[‘A‘,‘B‘]]")
print(df.loc[:,[‘A‘,‘B‘]])
#显示标签切片，包括两个端点
print(‘-‘*50)
print("df.loc[‘20170102‘:‘20170104‘,[‘A‘,‘B‘]]")
print(df.loc[‘20170102‘:‘20170104‘,[‘A‘,‘B‘]])
print(‘-‘*50)
#获得标量值  获取m行n列的单个数据值
print("df.loc[dates[0],‘A‘")
print(df.loc[dates[0],‘A‘])
#快速访问标量(等同于先前的方法)
print(‘-‘*50)
print("df.at[dates[0],‘A‘]")
print(df.at[dates[0],‘A‘])#at快速访问单个值；loc访问多指
#通过传递的整数的位置选择 通过下标选择
print("df.iloc[3]")
print(df.iloc[3])
print(‘-‘*50)
#通过整数切片，类似于numpy/python
print("df.iloc[3:5,0:2]")
print(df.iloc[3:5,0:2])#切片
#通过整数位置的列表，类似于numpy/python样式
print("df.iloc[[1,2,4],[0,2]]")
print(df.iloc[[1,2,4],[0,2]])#列表
print("df.iloc[1:3,:]")
print(df.iloc[1:3,:])
print("df.iloc[:,1:3]")
print(df.iloc[:,1:3])
print("df.iloc[1,1]")
print(df.iloc[1,1])
#要快速访问标量(等同于先前的方法)
print("print(df.iat[1,1])")
print(df.iat[1,1])
#布尔索引
#使用单列的值来选择数据
print("df[df.A > 0]")
print(df[df.A > 0][df.B<0])#多条件选择
print("df[df > 0]")
print(df[df > 0])#从满足布尔条件的DataFrame中选择值
#使用isin()方法进行过滤
df2 = df.copy()
df2[‘E‘] = [‘one‘, ‘one‘,‘two‘,‘three‘,‘four‘,‘three‘]
print("df2")
print(df2)
print("============= start to filter =============== ")
print("isin")
print(df2[df2[‘E‘].isin([‘two‘,‘four‘])])

D:\Download\python3\python3.exe D:/Download/pycharmworkspace/s.py
df:
A B C D
2017-01-01 -1.353900 -0.737163 -0.266858 -0.219116
2017-01-02 -2.328935 0.297892 0.244013 0.331435
2017-01-03 0.442864 -1.837813 -0.523082 -1.058623
2017-01-04 -2.117530 -0.480186 0.174002 -0.197551
2017-01-05 -0.312444 -0.958863 0.004229 -0.998425
2017-01-06 0.957020 -0.147027 0.125730 -0.643826
--------------------------------------------------
df.loc[:,[‘A‘,‘B‘]] #loc为原始索引 用键索引 字符索引
A B
2017-01-01 -1.353900 -0.737163
2017-01-02 -2.328935 0.297892
2017-01-03 0.442864 -1.837813
2017-01-04 -2.117530 -0.480186
2017-01-05 -0.312444 -0.958863
2017-01-06 0.957020 -0.147027
--------------------------------------------------
df.loc[‘20170102‘:‘20170104‘,[‘A‘,‘B‘]]
A B
2017-01-02 -2.328935 0.297892
2017-01-03 0.442864 -1.837813
2017-01-04 -2.117530 -0.480186
--------------------------------------------------
df.loc[dates[0],‘A‘
-1.3539004392106717
--------------------------------------------------
df.at[dates[0],‘A‘]#at快速取值
-1.3539004392106717

--------------------------------------------------
df.iloc[3]#iloc为数字索引
A -2.117530
B -0.480186
C 0.174002
D -0.197551
Name: 2017-01-04 00:00:00, dtype: float64
--------------------------------------------------
df.iloc[3:5,0:2]
A B
2017-01-04 -2.117530 -0.480186
2017-01-05 -0.312444 -0.958863
--------------------------------------------------
df.iloc[[1,2,4],[0,2]]
A C
2017-01-02 -2.328935 0.244013
2017-01-03 0.442864 -0.523082
2017-01-05 -0.312444 0.004229
--------------------------------------------------
df.iloc[1:3,:]
A B C D
2017-01-02 -2.328935 0.297892 0.244013 0.331435
2017-01-03 0.442864 -1.837813 -0.523082 -1.058623
--------------------------------------------------
df.iloc[:,1:3]
B C
2017-01-01 -0.737163 -0.266858
2017-01-02 0.297892 0.244013
2017-01-03 -1.837813 -0.523082
2017-01-04 -0.480186 0.174002
2017-01-05 -0.958863 0.004229
2017-01-06 -0.147027 0.125730
--------------------------------------------------
df.iloc[1,1]
0.29789175201181145
--------------------------------------------------
print(df.iat[1,1])#iat快速数字索引取值
0.29789175201181145
--------------------------------------------------
df[df.A > 0]#按照A列的元素大于0 进行筛选取值
A B C D
2017-01-03 0.442864 -1.837813 -0.523082 -1.058623
2017-01-06 0.957020 -0.147027 0.125730 -0.643826
--------------------------------------------------
df[df > 0]#保留数据大于0的元素，费大于0的元素为NaN
A B C D
2017-01-01 NaN NaN NaN NaN
2017-01-02 NaN 0.297892 0.244013 0.331435
2017-01-03 0.442864 NaN NaN NaN
2017-01-04 NaN NaN 0.174002 NaN
2017-01-05 NaN NaN 0.004229 NaN
2017-01-06 0.957020 NaN 0.125730 NaN
--------------------------------------------------
df2
A B C D E
2017-01-01 -1.353900 -0.737163 -0.266858 -0.219116 one
2017-01-02 -2.328935 0.297892 0.244013 0.331435 one
2017-01-03 0.442864 -1.837813 -0.523082 -1.058623 two
2017-01-04 -2.117530 -0.480186 0.174002 -0.197551 three
2017-01-05 -0.312444 -0.958863 0.004229 -0.998425 four
2017-01-06 0.957020 -0.147027 0.125730 -0.643826 three
--------------------------------------------------
============= start to filter ===============
isin

df2[‘E‘].isin([‘two‘,‘four‘]）

df2[df2[‘E‘].isin([‘two‘,‘four‘])]

#如果E列中的元素在 isin里面 则获取到值
A B C D E
2017-01-03 0.442864 -1.837813 -0.523082 -1.058623 two
2017-01-05 -0.312444 -0.958863 0.004229 -0.998425 four

Process finished with exit code 0