第5章-2 DataFrame

# -*- coding: utf-8 -*-
"""
Spyder Editor
This is a temporary script file.
"""
import numpy as np
import pandas as pd
from pandas import Series, DataFrame
data = {'state': ['Ohio','Ohio','Ohio','Nevada','Nevada'],'year':[2000,2001,2002,2001,2002],'pop':[1.5,1.7,3.6,2.4,2.9]}
frame = DataFrame(data)
print frame
#对DataFrame的列标进行自定义排序
frame = DataFrame(data, columns=['year','state','pop'])
print frame.columns
#index为DataFrame的索引项，可以通过list进行更改
frame2 = DataFrame(data, columns=['year','state','pop','debt'], index=['one','two','three','four','five'])
print frame2
#frame2.state同义表达方式
print frame2['state']
print frame2.ix['three']
#对debt列进行赋值的不同方式
frame2['debt'] = 16.5   #对debt赋值16.5
frame2['debt'] = np.arange(5)   #对debt赋值0-4
frame2.debt = Series([-1.2,-1.5,-1.7],index=['two','four','five'])  #对debt按Series进行赋值
print frame2
#对不存在的列进行赋值，会直接产生一个新的列。此处不能用frame2.eastern代替
frame2['eastern'] = frame2.state == 'ohio'
print frame2
del frame2['eastern']
print frame.columns
#对嵌套字典传给DataFrame，外层字典key为列标，内层字典key为行索引
pop = {'Nevada':{2001:2.4,2002:2.9},'Ohio':{2000:1.5,2001:1.7,2002:3.6}}
frame3 = DataFrame(pop)
print frame3
print frame3.T
print DataFrame(pop, index=[2001,2002,2003])
#对DataFrame的行名称和索引名称可通过name进行更改
frame3.index.name = 'year'
frame3.columns.name = 'state'
print frame3
print frame3.values