df.duplicated(subset=['age','job','marital','education','day','month'],keep=False)
df3=df.loc[:,['age','job','marital','education','day','month']]
df_dup=df3[df3.duplicated(['age','job','marital','education','day','month'])==True]
df_dup
我认为是对的
你是想要达到什么目的? keep=False 这里是重复的都不保留,你是想去重留一个还是去重一个不留?