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 ....等,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')