层次化索引MultiIndex

mask=pd.MultiIndex.from_arrays([['Ohio', 'Ohio', 'Colorado'], ['Green','bed', 'Green']],
                               names=('state', 'color'))

df = pd.DataFrame(np.arange(12).reshape((4, 3)),index=[['a', 'a', 'b', 'b'], [1, 2, 1, 2]],
                  columns=mask)


df.index.names=['key1','key2']
df.columns.names=['state','color']

print("
源数据：
",df)


print("
对源数据index排序：
",df.sort_index(level=1))
print("
交换级别：
")
print(df.swaplevel('key1','key2'))
print("
交换级别后排序：
")
print(df.swaplevel('key1','key2').sort_index(level=0))

结果：

 

 可以对比看到，排序的结果是一样的

 END

#df.set_index( )函数的用法
df=pd.DataFrame({'a':range(7),'b':range(7,0,-1),'c':['one','one','one','two','two','two','two'],
                 'd':[0,1,2,0,1,2,3]})


print("源数据：
",df)

df2=df.set_index(['c','d'])
df3=df.set_index(['c','d'],drop=False)


print("
df.set_index(['c','d']层次化索引,df2:
",df2)
print("
df.set_index(['c','d'],drop=False层次化索引,drop,df3:
",df3)

结果：

 END

left1 = pd.DataFrame({'key': ['a', 'b', 'a', 'a', 'b','c'],'value': range(6)})
right1 = pd.DataFrame({'group_val': [3.5, 7]}, index=['a', 'b'])

print("left1:
",left1)
print("right1:
",right1)

mask=left1.join(right1)
mask2=left1.join(right1,on='key')

print("
不指定key值：
",mask)
print("
指定key值：
",mask2)

结果：

  END