从现有的分隔列名创建多索引DataFrame

import pandas as pd

# 创建一个简单的DataFrame
data = {
    'date': ['2021-01-01', '2021-01-01', '2021-01-02', '2021-01-02'],
    'city': ['Beijing', 'Shanghai', 'Beijing', 'Shanghai'],
    'temperature': [3, 8, 4, 7]
}

df = pd.DataFrame(data)
print("原始DataFrame:")
print(df)

原始DataFrame:
         date      city  temperature
0  2021-01-01   Beijing           3
1  021-01-01  Shanghai           8
2  2021-01-02   Beijing           4
3  2021-01-02  Shanghai           7

# 将'date'和'city'列设置为多索引
multi_index_df = df.set_index(['date', 'city'])
print("\n多索引DataFrame:")
print(multi_index_df)

多索引DataFrame:
                     temperature
date       city                
2021-01-01 Beijing           3
           Shanghai          8
2021-01-02 Beijing           4
           Shanghai          7

# 去除重复项
df = df.drop_duplicates(subset=['date', 'city'])
multi_index_df = df.set_index(['date', 'city'])