Pandas上两列的日期差异

import pandas as pd

# 创建示例 DataFrame
data = {
    'start_date': ['2023-01-01', '2023-01-02', '2023-01-03'],
    'end_date': ['2023-01-05', '2023-01-06', '2023-01-07']
}
df = pd.DataFrame(data)

# 将字符串转换为 datetime 类型
df['start_date'] = pd.to_datetime(df['start_date'])
df['end_date'] = pd.to_datetime(df['end_date'])

# 计算日期差异
df['date_diff'] = (df['end_date'] - df['start_date']).dt.days

print(df)

  start_date   end_date  date_diff
0 2023-01-01 2023-01-05         4
1 2023-01-02 2023-01-06         4
2 2023-01-03 2023-01-07         4

df['start_date'] = pd.to_datetime(df['start_date'], format='%Y-%m-%d')
df['end_date'] = pd.to_datetime(df['end_date'], format='%Y-%m-%d')

df['start_date'] = df['start_date'].dt.tz_localize('UTC')
df['end_date'] = df['end_date'].dt.tz_localize('UTC')
df['date_diff'] = (df['end_date'] - df['start_date']).dt.days