Code completion with statistical language models

We address the problem of synthesizing code completions for pro-grams using APIs. Given a program with holes, we synthesize com-pletions for holes with the most likely sequences of method calls. Our main idea is to reduce the problem of code completion to a natural-language processing problem of predicting probabilities of sentences. We design a simple and scalable static analysis that extracts sequences of method calls from a large codebase, and index these into a statistical language model. We then employ the language model to find the highest ranked sentences, and use them to synthesize a code completion. Our approach is able to synthesize sequences of calls across multiple objects together with their arguments. Experiments show that our approach is fast and effective. Virtu-ally all computed completions typecheck, and the desired comple-tion appears in the top 3 results in 90 % of the cases