Pandas矢量化-在另一个DataFrame中查找最近的未来时间

import pandas as pd

# 创建示例 DataFrame
data1 = {
    'timestamp': ['2023-01-01 10:00:00', '2023-01-01 11:00:00', '2023-01-01 12:00:00'],
    'event': ['A', 'B', 'C']
}
df1 = pd.DataFrame(data1)
df1['timestamp'] = pd.to_datetime(df1['timestamp'])

data2 = {
    'reference_time': ['2023-01-01 10:30:00', '2023-01-01 11:30:00']
}
df2 = pd.DataFrame(data2)
df2['reference_time'] = pd.to_datetime(df2['reference_time'])

# 将 df1 的时间戳设置为索引
df1.set_index('timestamp', inplace=True)

# 在 df2 中查找最近的未来时间
df2['nearest_future_time'] = df2['reference_time'].apply(lambda x: df1.index[df1.index > x].min())

print(df2)

  reference_time nearest_future_time
0 2023-01-01 10:30:00        2023-01-01 11:00:00
1 2023-01-01 11:30:00        2023-01-01 12:00:00