import pandas as pd
import numpy as np
data = pd.DataFrame(np.arange(6).reshape((2,3)),index=pd.Index(['Ohio','Colorado'],name='state')
     ,columns=pd.Index(['one','two','three'],name='number'))
data

result = data.stack()
result

result.unstack()

s1 = pd.Series([0,1,2,3],index=list('abcd'))
s2 = pd.Series([4,5,6],index=list('cde'))
data2 = pd.concat([s1,s2],keys=['one','two'])
data2

data2.unstack().stack()

def pivot_simple(index, columns, values):
  """
  Produce 'pivot' table based on 3 columns of this DataFrame.
  Uses unique values from index / columns and fills with values.
  Parameters
  ----------
  index : ndarray
    Labels to use to make new frame's index
  columns : ndarray
    Labels to use to make new frame's columns
  values : ndarray
    Values to use for populating new frame's values

from collections import OrderedDict
from pandas import DataFrame
import pandas as pd
import numpy as np
 
data = OrderedDict((
  ("item", ['Item1', 'Item1', 'Item2', 'Item2']),
  ('color', ['red', 'blue', 'red', 'black']),
  ('user', ['1', '2', '3', '4']),
  ('bm',  ['1', '2', '3', '4'])
))
data = DataFrame(data)
print(data)

  item color user bm
0 Item1  red  1 1
1 Item1  blue  2 2
2 Item2  red  3 3
3 Item2 black  4 4

df = data.pivot(index='item', columns='color', values='user')
print(df)

color black blue red
item         
Item1 None   2  1
Item2   4 None  3

# 原始數(shù)據(jù)集
print(data[(data.item=='Item1') & (data.color=='red')].user.values)
 
# 變換后的數(shù)據(jù)集
print(df[df.index=='Item1'].red.values)

['1']
['1']

df2 = data.pivot(index='item', columns='color')
print(df2)

    user       bm     
color black blue red black blue red
item                 
Item1 None   2  1 None   2  1
Item2   4 None  3   4 None  3

data = OrderedDict((
  ("item", ['Item1', 'Item1', 'Item1', 'Item2']),
  ('color', ['red', 'blue', 'red', 'black']),
  ('user', ['1', '2', '3', '4']),
  ('bm',  ['1', '2', '3', '4'])
))
data = DataFrame(data) 
df = data.pivot(index='item', columns='color', values='user')

ValueError: Index contains duplicate entries, cannot reshape

def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
        fill_value=None, margins=False, dropna=True,
        margins_name='All'):
  """
  Create a spreadsheet-style pivot table as a DataFrame. The levels in the
  pivot table will be stored in MultiIndex objects (hierarchical indexes) on
  the index and columns of the result DataFrame
  Parameters
  ----------
  data : DataFrame
  values : column to aggregate, optional
  index : column, Grouper, array, or list of the previous
    If an array is passed, it must be the same length as the data. The list
    can contain any of the other types (except list).
    Keys to group by on the pivot table index. If an array is passed, it
    is being used as the same manner as column values.
  columns : column, Grouper, array, or list of the previous
    If an array is passed, it must be the same length as the data. The list
    can contain any of the other types (except list).
    Keys to group by on the pivot table column. If an array is passed, it
    is being used as the same manner as column values.
  aggfunc : function or list of functions, default numpy.mean
    If list of functions passed, the resulting pivot table will have
    hierarchical columns whose top level are the function names (inferred
    from the function objects themselves)
  fill_value : scalar, default None
    Value to replace missing values with
  margins : boolean, default False
    Add all row / columns (e.g. for subtotal / grand totals)
  dropna : boolean, default True
    Do not include columns whose entries are all NaN
  margins_name : string, default 'All'
    Name of the row / column that will contain the totals
    when margins is True.
    接下來我們來看一個(gè)示例：
data = OrderedDict((
  ("item", ['Item1', 'Item1', 'Item1', 'Item2']),
  ('color', ['red', 'blue', 'red', 'black']),
  ('user', ['1', '2', '3', '4']),
  ('bm',  ['1', '2', '3', '4'])
))
data = DataFrame(data)
 
df = data.pivot_table(index='item', columns='color', values='user', aggfunc=np.min)
print(df)

color black blue  red
item          
Item1 None   2   1
Item2   4 None None

from pandas import DataFrame
import pandas as pd
import numpy as np
 
# 建立多個(gè)行索引
row_idx_arr = list(zip(['r0', 'r0'], ['r-00', 'r-01']))
row_idx = pd.MultiIndex.from_tuples(row_idx_arr)
 
# 建立多個(gè)列索引
col_idx_arr = list(zip(['c0', 'c0', 'c1'], ['c-00', 'c-01', 'c-10']))
col_idx = pd.MultiIndex.from_tuples(col_idx_arr)
 
# 創(chuàng)建DataFrame
d = DataFrame(np.arange(6).reshape(2,3), index=row_idx, columns=col_idx)
d = d.applymap(lambda x: (x // 3, x % 3))
 
# Stack/Unstack
s = d.stack()
u = d.unstack()
print(s)
print(u)

         c0   c1
r0 r-00 c-00 (0, 0)   NaN
    c-01 (0, 1)   NaN
    c-10   NaN (0, 2)
  r-01 c-00 (1, 0)   NaN
    c-01 (1, 1)   NaN
    c-10   NaN (1, 2)
 
    c0               c1    
   c-00      c-01      c-10    
   r-00  r-01  r-00  r-01  r-00  r-01
r0 (0, 0) (1, 0) (0, 1) (1, 1) (0, 2) (1, 2)