PYTHON

pandas transform

>>> df = pd.DataFrame({'A': range(3), 'B': range(1, 4)})
>>> df
   A  B
0  0  1
1  1  2
2  2  3
>>> df.transform(lambda x: x + 1)
   A  B
0  1  2
1  2  3
2  3  4

pandas transform

# when used with groupby, transform is faster than filter
# use transform instead of filter e.g.
df = df[(df.groupby('col1')['col2'].transform('sum')>=200) 
        & (df.groupby('col1')['col3'].transform('nunique')>=20)]