对DataFrame进行分组，计算一列中出现的次数，将其他列值放入集合中

import pandas as pd

data = {'column1': ['A', 'B', 'A', 'B', 'A'],
        'column2': [1, 2, 3, 4, 5]}
df = pd.DataFrame(data)

grouped = df.groupby('column1').size()

def collect_values(group):
    return set(group['column2'])

result = grouped.apply(lambda x: collect_values(df[df['column1'] == x]))

import pandas as pd

data = {'column1': ['A', 'B', 'A', 'B', 'A'],
        'column2': [1, 2, 3, 4, 5]}
df = pd.DataFrame(data)

grouped = df.groupby('column1').size()

def collect_values(group):
    return set(group['column2'])

result = grouped.apply(lambda x: collect_values(df[df['column1'] == x]))

print(result)