import pandas as pdimport numpy as npdf = pd.DataFrame({ "uid": [1,2,2,3,4,np.nan,5], "name": ["张三","李四","李四","王五","赵六","钱七","孙八"], "age": ["25","30","30","35","-","42","38"], "salary": [5000, np.nan, 6000, 7000, 4000, 6500, np.nan]})df.to_excel("dirty_user.xlsx", index=False)print(" dirty_user.xlsx 含脏数据已生成")