Enabling Feature Location for API Method Recommendation and Usage Location

Sun, Xiaobing; Xu, Congying; Li, Bin; Duan, Yucong; Lu, Xintong

doi:10.1109/access.2019.2910732

Cited by 12 publications

(9 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MULAPI identifies features, related files and API usage location. Furthermore, Sun et al (2019), proposed a method that first analyzes software repositories, utilizes the feature-related files then based on API libraries to recommend the API next method to a developer. Moreover, we perform a SWOT analysis (Table 8), which shows the strengths, weaknesses, opportunities and threats of the papers in the context of APIs recommendations.…”

Section: Reporting the Resultsmentioning

confidence: 99%

A study on application programming interface recommendation: state-of-the-art techniques, challenges and future directions

Nawaz

Khan

Hussain

et al. 2022

LHT

View full text Add to dashboard Cite

PurposeThis study aims to identify the developer’s objectives, current state-of-the-art techniques, challenges and performance evaluation metrics, and presents outlines of a knowledge-based application programming interfaces (API) recommendation system for the developers. Moreover, the current study intends to classify current state-of-the-art techniques supporting automated API recommendations.Design/methodology/approachIn this study, the authors have performed a systematic literature review of studies, which have been published between the years 2004–2021 to achieve the targeted research objective. Subsequently, the authors performed the analysis of 35 primary studies.FindingsThe outcomes of this study are: (1) devising a thematic taxonomy based on the identified developers’ challenges, where mashup-oriented APIs and time-consuming process are frequently encountered challenges by the developers; (2) categorizing current state-of-the-art API recommendation techniques (i.e. clustering techniques, data preprocessing techniques, similarity measurements techniques and ranking techniques); (3) designing a taxonomy based on the identified objectives, where accuracy is the most targeted objective in API recommendation context; (4) identifying a list of evaluation metrics employed to assess the performance of the proposed techniques; (5) performing a SWOT analysis on the selected studies; (6) based on the developer’s challenges, objectives and SWOT analysis, presenting outlines of a recommendation system for the developers and (7) delineating several future research dimensions in API recommendations context.Research limitations/implicationsThis study provides complete guidance to the new researcher in the context of API recommendations. Also, the researcher can target these objectives (accuracy, response time, method recommendation, compatibility, user requirement-based API, automatic service recommendation and API location) in the future. Moreover, the developers can overcome the identified challenges (including mashup-oriented API, Time-consuming process, learn how to use the API, integrated problem, API method usage location and limited usage of code) in the future by proposing a framework or recommendation system. Furthermore, the classification of current state-of-the-art API recommendation techniques also helps the researchers who wish to work in the future in the context of API recommendation.Practical implicationsThis study not only facilitates the researcher but also facilitates the practitioners in several ways. The current study guides the developer in minimizing the development time in terms of selecting relevant APIs rather than following traditional manual selection. Moreover, this study facilitates integrating APIs in a project. Thus, the recommendation system saves the time for developers, and increases their productivity.Originality/valueAPI recommendation remains an active area of research in web and mobile-based applications development. The authors believe that this study acts as a useful tool for the interested researchers and practitioners as it will contribute to the body of knowledge in API recommendations context.

show abstract

Section: Reporting the Resultsmentioning

confidence: 99%

A study on application programming interface recommendation: state-of-the-art techniques, challenges and future directions

Nawaz

Khan

Hussain

et al. 2022

LHT

View full text Add to dashboard Cite

show abstract

“…RELATED WORK API recommendation for natural language queries. Researchers use embeddings [1]- [4], [6], [28]- [33] to model and translate among natural language queries, application documentation, and API functionalities. Others use graphs for representation and recommendation [5], [7].…”

Section: F Results Analysismentioning

confidence: 99%

“…For example, Pycharm relies on python-skeletons 2 and typeshed 3 to make API recommendations. Visual Studio IntelliCode 4 leverages Machine Learning to learn programming patterns from a huge repository of 2 https://github.com/JetBrains/python-skeletons 3 https://github.com/python/typeshed 4 https://visualstudio.microsoft.com/zh-hans/services/intellicode arXiv:2102.04706v1 [cs.SE] 9 Feb 2021 Python projects. As we will show in Section II, they still have various drawbacks, caused by the aforementioned challenges.…”

Section: Introductionmentioning

confidence: 99%

PyART: Python API Recommendation in Real-Time

Zhang

et al. 2021

2021 IEEE/ACM 43rd International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)

View full text Add to dashboard Cite

API recommendation in real-time is challenging for dynamic languages like Python. Many existing API recommendation techniques are highly effective, but they mainly support static languages. A few Python IDEs provide API recommendation functionalities based on type inference and training on a large corpus of Python libraries and third-party libraries. As such, they may fail to recommend or make poor recommendations when type information is missing or target APIs are projectspecific. In this paper, we propose a novel approach, PyART, to recommending APIs for Python programs in real-time. It features a light-weight analysis to derive so-called optimistic data-flow, which is neither sound nor complete, but simulates the local data-flow information humans can derive. It extracts three kinds of features: data-flow, token similarity, and token co-occurrence, in the context of the program point where a recommendation is solicited. A predictive model is trained on these features using the Random Forest algorithm. Evaluation on 8 popular Python projects demonstrates that PyART can provide effective API recommendations. When historic commits can be leveraged, which is the target scenario of a state-of-theart tool ARIREC, our average top-1 accuracy is over 50% and average top-10 accuracy over 70%, outperforming APIREC and Intellicode (i.e., the recommendation component in Visual Studio) by 28.48%-39.05% for top-1 accuracy and 24.41%-30.49% for top-10 accuracy. In other applications such as when historic comments are not available and cross-project recommendation, PyART also shows better overall performance. The time to make a recommendation is less than a second on average, satisfying the real-time requirement.

show abstract

“…Multiple existing works [15], [31], [37], [48], [49], [54], [58], [73], [78], [90], [91], [99], [100], [102], [103], [104], [109], [109] explore the possibility to provide developers with concrete API recommendation, using the natural language queries as input. Most of these works utilize open-source code bases, and some also use the knowledge in crowd-sourcing forums and wiki websites for augmentation.…”

Section: Query Based Api Recommendationmentioning

confidence: 99%

Revisiting, Benchmarking and Exploring API Recommendation: How Far Are We?

Peng¹,

Liu²,

Gu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Application Programming Interfaces (APIs), which encapsulate the implementation of specific functions as interfaces, greatly improve the efficiency of modern software development. As numbers of APIs spring up nowadays, developers can hardly be familiar with all the APIs and usually need to search for appropriate APIs for usage. So lots of efforts have been devoted to improving the API recommendation task. However, it has been increasingly difficult to gauge the performance of new models due to the lack of a uniform definition of the task and a standardized benchmark. For example, some studies regard the task as a code completion problem, while others recommend relative APIs given natural language queries. To reduce the challenges and better facilitate future research, in this paper, we revisit the API recommendation task and aim at benchmarking the approaches. Specifically, the paper groups the approaches into two categories according to the task definition, i.e., query-based API recommendation and code-based API recommendation. We study 11 recently-proposed approaches along with 4 widely-used IDEs. One benchmark named as APIBench is then built for the two respective categories of approaches. Based on APIBench, we distill some actionable insights and challenges for API recommendation. We also achieve some implications and directions for improving the performance of recommending APIs, including data source selection, appropriate query reformulation, low resource setting, and cross-domain adaptation.

show abstract

Enabling Feature Location for API Method Recommendation and Usage Location

Cited by 12 publications

References 38 publications

A study on application programming interface recommendation: state-of-the-art techniques, challenges and future directions

A study on application programming interface recommendation: state-of-the-art techniques, challenges and future directions

PyART: Python API Recommendation in Real-Time

Revisiting, Benchmarking and Exploring API Recommendation: How Far Are We?

Contact Info

Product

Resources

About