Editing radio interferometer data, a process commonly known as ‘flagging’, can be laborious and time-consuming. One quickly tends to flag more data than actually required, sacrificing sensitivity and image fidelity in the process. I describe a program, PIEFLAG, which can analyze radio interferometer data to filter out measurements which are likely to be affected by interference. PIEFLAG uses two algorithms to allow for data sets which are either dominated by receiver noise or by source structure. Together, the algorithms detect essentially all affected data whilst the amount of data which is not affected by interference but falsely marked as such is kept to a minimum. The sections marked by PIEFLAG are very similar to what would be deemed affected by the observer in a visual inspection of the data. PIEFLAG displays its results concisely and allows the user to add and remove flags interactively. It is written in python, is easy to install and use, and has a variety of options to adjust its algorithms to a particular observing situation. I describe how PIEFLAG works and illustrate its effect using data from typical observations.