pandas系列6-重塑reshape

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

data = pd.DataFrame(np.arange(6).reshape(2,3)
                   ,index=pd.Index(['Inhio','Colorado'], name='state')
                   ,columns=pd.Index(['one', 'two', 'three']
                   ,name='number'   # name 参数在column里面，不是单独的，相当于是给columns起名字
                     )    
                   )

data

res = data.stack()   # 列转成行
res

state     number
Inhio     one       0
          two       1
          three     2
Colorado  one       3
          two       4
          three     5
dtype: int32

res.index

MultiIndex(levels=[['Inhio', 'Colorado'], ['one', 'two', 'three']],
           codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 1, 2]],
           names=['state', 'number'])

type(res)     # res 是S型对象

pandas.core.series.Series

res.unstack()   # 行转成列：one、two、three 变成列属性

res.unstack(1)   # 默认操作最内层
# res.unstack()  
# res.unstack('number')  同上；恢复原状

res.unstack(0)   # 实现了将行索引和列属性的位置互换
# res.unstack('state')    同上功能

s1 = pd.Series([0,1,2,3], index=['a','b','c','d'])
s2 = pd.Series([4,5,6], index=['c','d','e'])

data1 = pd.concat([s1,s2], keys=['one', 'two'])
data1

one  a    0
     b    1
     c    2
     d    3
two  c    4
     d    5
     e    6
dtype: int64

data1.unstack()  # 行索引转成列属性，unstack引入缺失值

data1.unstack().stack()   # 操作可逆，stack操作默认过滤缺失值

one  a    0.0
     b    1.0
     c    2.0
     d    3.0
two  c    4.0
     d    5.0
     e    6.0
dtype: float64

data1.unstack().stack(dropna=False)   # 通过dropna参数保留缺失值

one  a    0.0
     b    1.0
     c    2.0
     d    3.0
     e    NaN
two  a    NaN
     b    NaN
     c    4.0
     d    5.0
     e    6.0
dtype: float64

tuples = list(zip(*[['bar', 'bar', 'baz', 'baz',
                     'foo', 'foo', 'qux', 'qux'],
                    ['one', 'two', 'one', 'two',
                     'one', 'two', 'one', 'two']]))
tuples

[('bar', 'one'),
 ('bar', 'two'),
 ('baz', 'one'),
 ('baz', 'two'),
 ('foo', 'one'),
 ('foo', 'two'),
 ('qux', 'one'),
 ('qux', 'two')]

zip(*[['bar', 'bar', 'baz', 'baz',
   'foo', 'foo', 'qux', 'qux'],
  ['one', 'two', 'one', 'two',
   'one', 'two', 'one', 'two']])

<zip at 0x1d68ccb0d08>

list(zip(*[["name", "age", "fee"],    # zip函数的用法
         ["xiaoming", 18, "28.22"]]))

[('name', 'xiaoming'), ('age', 18), ('fee', '28.22')]

index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])  # 错层次索引如何创建

# index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])
index

MultiIndex(levels=[['bar', 'baz', 'foo', 'qux'], ['one', 'two']],
           codes=[[0, 0, 1, 1, 2, 2, 3, 3], [0, 1, 0, 1, 0, 1, 0, 1]],
           names=['first', 'second'])

df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B'])
df

df2 = df[:4]
df2

stacked = df2.stack()   # 列---->行
stacked

first  second   
bar    one     A   -0.904164
               B    0.001987
       two     A   -0.299222
               B   -1.895165
baz    one     A    2.029077
               B   -0.618868
       two     A   -3.423209
               B    0.621895
dtype: float64

stacked.unstack()  # 行----->列
# stacked.unstack(0)
# stacked.unstack('first')

stacked.unstack(1)
# stacked.unstack('second')

df[df['bar'] == 'A']     # select out everything for variable A 

df.pivot(index='foo', columns='bar', values='baz')   # 分别指定行索引、列属性还有value值

In [1]: df
Out[1]: 
         date variable     value
0  2000-01-03        A  0.469112
1  2000-01-04        A -0.282863
2  2000-01-05        A -1.509059
3  2000-01-03        B -1.135632
4  2000-01-04        B  1.212112
5  2000-01-05        B -0.173215
6  2000-01-03        C  0.119209
7  2000-01-04        C -1.044236
8  2000-01-05        C -0.861849
9  2000-01-03        D -2.104569
10 2000-01-04        D -0.494929
11 2000-01-05        D  1.071804

In [2]: df.pivot(index='date', columns='variable', values='value')
Out[2]: 
variable           A         B         C         D
date                                              
2000-01-03  0.469112 -1.135632  0.119209 -2.104569
2000-01-04 -0.282863  1.212112 -1.044236 -0.494929
2000-01-05 -1.509059 -0.173215 -0.861849  1.071804

In [3]: df[df['variable'] == 'A']
Out[3]: 
        date variable     value
0 2000-01-03        A  0.469112
1 2000-01-04        A -0.282863
2 2000-01-05        A -1.509059
    
In [4]: df['value2'] = df['value'] * 2
In [5]: pivoted = df.pivot(index='date', columns='variable')

In [6]: pivoted
Out[6]: 
               value                                  value2                              
variable           A         B         C         D         A         B         C         D
date                                                                                      
2000-01-03  0.469112 -1.135632  0.119209 -2.104569  0.938225 -2.271265  0.238417 -4.209138
2000-01-04 -0.282863  1.212112 -1.044236 -0.494929 -0.565727  2.424224 -2.088472 -0.989859
2000-01-05 -1.509059 -0.173215 -0.861849  1.071804 -3.018117 -0.346429 -1.723698  2.143608