python - 动态创建和重命名数据框

Question

我想通过 df1 和 df2 的重命名(和代码)来运行数据帧列表。这可以通过 def ....etc 或任何其他方法来完成吗？

df = pd.DataFrame( {
   'A': ['d','d','d','d','d','d','g','g','g','g','g','g','k','k','k','k','k','k'],
   'B': [5,5,6,4,5,6,-6,7,7,6,-7,7,-8,7,-6,6,-7,50],
   'C': [1,1,1,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2],
   'S': [2012,2013,2014,2015,2016,2012,2012,2014,2015,2016,2012,2013,2012,2013,2014,2015,2016,2014]     
    } );

df = (df.B + df.C).groupby([df.A, df.S]).agg(['sum','size']).unstack(fill_value=0)
df1 = df.groupby(level=0, axis=1).sum()
new_cols= list(zip(df1.columns.get_level_values(0),['total'] * len(df.columns)))
df1.columns = pd.MultiIndex.from_tuples(new_cols)
df2 = pd.concat([df1,df], axis=1).sort_index(axis=1).sort_index(axis=1, level=1)
df2.columns = ['_'.join((col[0], str(col[1]))) for col in df2.columns]
df2.columns = df2.columns.str.replace('sum_','')
df2.columns = df2.columns.str.replace('size_','T')

Answer 1

我认为你可以使用自定义函数:

def func(df):
    df = (df.B + df.C).groupby([df.A, df.S]).agg(['sum','size']).unstack(fill_value=0)
    df1 = df.groupby(level=0, axis=1).sum()
    new_cols= list(zip(df1.columns.get_level_values(0),['total'] * len(df.columns)))
    df1.columns = pd.MultiIndex.from_tuples(new_cols)
    df2 = pd.concat([df1,df], axis=1).sort_index(axis=1).sort_index(axis=1, level=1)
    df2.columns = ['_'.join((col[0], str(col[1]))) for col in df2.columns]
    df2.columns = df2.columns.str.replace('sum_','')
    df2.columns = df2.columns.str.replace('size_','T')
    return df2

print (func(df))    
   T2012  2012  T2013  2013  T2014  2014  T2015  2015  T2016  2016  Ttotal  \
A                                                                            
d      2    13      1     6      1     7      1     5      1     6       6   
g      2   -11      1     8      1     8      1     8      1     7       6   
k      1    -6      1     9      2    48      1     8      1    -5       6   

   total  
A         
d     37  
g     20  
k     54     

如果需要处理多个数据帧:

for df in [df1,df2,df3]:
    print (func(df)) 

如果需要输出到数据帧列表:

dfs = [func(df) for df in [df1,df2,df3]]