import pandas as pd import numpy as np #Create a dataframe with a categorical column with two categories and a (numpy) boolean column that is randomly True or False df = pd.DataFrame.from_dict({'category':['A']*10+['B']*10, 'bool_numpy': np.random.rand(20)>0.5}) #Now make another column that is a copy of the numpy boolean column, but converted to pyarrow df['bool_arrow'] = df['bool_numpy'].astype('bool[pyarrow]') print(df.head()) # category bool_numpy bool_arrow # 0 A True True # 1 A True True # 2 A True True # 3 A True True # 4 A False False #Now do a gruopby and aggregate to compute the fraction of True values in each column: true_fracs = df.groupby('category').agg(lambda x: x.sum()/x.count()) print(true_fracs) # bool_numpy bool_arrow # category  # A 0.7 True # B 0.6 True #I expect both columns above to have identical floating-point values, not boolean.

print(df.query("category=='A'")[['bool_numpy','bool_arrow']].sum()/df[['bool_numpy','bool_arrow']].count()) # bool_numpy 0.7 # bool_arrow 0.7 # dtype: float64