Stepwise API usage assistance using n -gram language models

Abstract

Reusing software involves learning third-party APIs, a process that is often time-consuming and error-prone. Recommendation systems for API usage assistance based on statistical models built from source code corpora are capable of assisting API users through code completion mechanisms in IDEs. A valid sequence of API calls involving different types may be regarded as a well-formed sentence of tokens from the API vocabulary. In this article we describe an approach for recommending subsequent tokens to complete API sentences using n-gram language models built from source code corpora. The provided system was integrated in the code completion facilities of the Eclipse IDE, providing contextualized completion proposals for Java taking into account the nearest lines of code. The approach was evaluated against existing client code of four widely used APIs, revealing that in more than 90% of the cases the expected subsequent token is within the 10-top-most proposals of our models. The high score provides evidence that the recommendations could help on API learning and exploration, namely through the assistance on writing valid API sentences.

Profiling Software Developers with Process Mining and N-Gram Language Models

“…• A language model is a statistical model that allows computing the probability of a sentence, or predict the next word in a sentence for a given language [33]. From a generative perspective, all sentences of a (natural) language can be described in terms of the product of a set of conditional probabilities [34]. Hence, the probability of a sentence ω = (t 0 ,t 1 ,...t n ) is given by : P(ω) = P(t 0 )P(t 1 |t 0 )P(t 2 |t 0 t 1 )...P(t n |t 0 t 1 ...t n-1 )…”

“…A system that assists developers in API usage with code completion recommendation, using a n-gram probabilistic language model, supported by API sentences extracted from source code corpora, is described in [34].…”

Software Development Process Mining: Discovery, Conformance Checking and Enhancement

“…• A language model is a statistical model that allows computing the probability of a sentence, or predict the next word in a sentence for a given language [31]. From a generative perspective, all sentences of a (natural) language can be described in terms of the product of a set of conditional probabilities [185]. Hence, the probability of a sentence ω = (t 0 ,t 1 ,...t n ) is given by : P(ω) = P(t 0 )P(t 1 |t 0 )P(t 2 |t 0 t 1 )...P(t n |t 0 t 1 ...t n-1 )…”

“…In [185], a system was built to assists developers in Application Program Interface (API) usage with code completion recommendation, using a n-gram probabilistic language model, supported by API sentences extracted from source code corpora.…”

API integration and organisational agility outcomes in digital music platforms: A qualitative case study

“…First, existing research appears one-sided (technically-focused), arguably because APIs were mostly conceptualised as technical systems and limited to the domain of developers [ 11 , 27 ]. Thus, there is less attention on other social concepts like agility at the individual, firm or multi-firm levels [ [30] , [31] , [32] ]. API integration within organisations significantly influences strategic transformation and decision-making [ 33 ].…”