Effective API recommendation without historical software repositories

Liu, Xiaoyu; Huang, LiGuo; Ng, Vincent

doi:10.1145/3238147.3238216

Cited by 45 publications

(29 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nguyen et al [9] proposed to learn from a corpus the regularity between fine-grained code changes [34], [35] and APIs, and use that to make recommendations. Liu et al [11] proposed a method independent of historical commits by ranking the Top-10 recommendations of Gralan [10] to achieve better Top-1 accuracy than APIREC [9]. Nguyen et al [12] mine open-source software (OSS) repositories [36], [37] to provide developers with API function calls and usage patterns by analyzing how APIs are used in projects similar to the current project using a 3D matrix.…”

Section: F Results Analysismentioning

confidence: 99%

“…We propose a novel API recommendation technique specifically designed for Python. It was shown that data-flow is extremely useful in improving API recommendation results [11], [15], [16]. However, existing techniques heavily rely on some precise data flow analysis engine, which is very difficult for a dynamic language like Python.…”

Section: Motivating Examplementioning

confidence: 99%

“…Many existing API recommending approaches are built on these analyses and hence do not support Python. For example, data-flow features are widely used in existing API recommendation approaches [11], [15], [16]. However, it's challenging to extract accurate data-flow for Python programs.…”

Section: Introductionmentioning

confidence: 99%

“…Compared to existing solutions, PyART can recommend both library APIs and APIs defined within the same project; it does not rely on any third party tools; it is lightweight and provides recommendations without noticeable delay; and it delivers recommendations with good accuracy. The key to the success of many existing API recommendation projects lies in the use of high quality data-flow information [11], [15], [16]. They largely utilize data-flow analyses in mature compilers/analysisinfrastructures, which tend to be conservative as they were designed to ensure safety in code transformation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Section: F Results Analysismentioning

confidence: 99%

Section: Motivating Examplementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

show abstract

“…Unlike code search [29], systems for API search do not necessarily have access to source code repositories, and may rely solely upon API documentation or specifications. API search also targets resources and operations with specific properties within APIs, unlike API discovery/recommendation and software component retrieval, which may target other software units [30], [31] or base results on code context rather than queries [32]. Still, there is significant overlap between the research fields, and concepts and techniques from one can often be applied in the others.…”

Section: Api Searchmentioning

confidence: 99%

Dialogue Management for Interactive API Search

Eberhart¹,

McMillan²

2021

Preprint

View full text Add to dashboard Cite

API search involves finding components in an API that are relevant to a programming task. For example, a programmer may need a function in a C library that opens a new network connection, then another function that sends data across that connection. Unfortunately, programmers often have trouble finding the API components that they need. A strong scientific consensus is emerging towards developing interactive tool support that responds to conversational feedback, emulating the experience of asking a fellow human programmer for help. A major barrier to creating these interactive tools is implementing dialogue management for API search. Dialogue management involves determining how a system should respond to user input, such as whether to ask a clarification question or to display potential results. In this paper, we present a dialogue manager for interactive API search that considers search results and dialogue history to select efficient actions. We implement two dialogue policies: a hand-crafted policy and a policy optimized via reinforcement learning. We perform a synthetics evaluation and a human evaluation comparing the policies to a generic single-turn, top-N policy used by source code search engines.

show abstract

Application programming interface recommendation for smart contract using deep learning from augmented code representation

Cai,

et al. 2024

J Software Evolu Process

View full text Add to dashboard Cite

Application programming interface (API) recommendation plays a crucial role in facilitating smart contract development by providing developers with a ranked list of candidate APIs for specific recommendation points. Deep learning‐based approaches have shown promising results in this field. However, existing approaches mainly rely on token sequences or abstract syntax trees (ASTs) for learning recommendation point‐related features, which may overlook the essential knowledge implied in the relations between or within statements and may include task‐irrelevant components during feature learning. To address these limitations, we propose a novel code graph called pruned and augmented AST (pa‐AST). Our approach enhances the AST by incorporating additional knowledge derived from the control and data flow relations between and within statements in the smart contract code. Through this augmentation, the pa‐AST can better represent the semantic features of the code. Furthermore, we conduct AST pruning to eliminate task‐irrelevant components based on the identified flow relations. This step helps mitigate the interference caused by these irrelevant parts during the model feature learning process. Additionally, we extract the API sequence surrounding the recommendation point to provide supplementary knowledge for the model learning. The experimental results demonstrate our proposed approach achieving an average mean reciprocal rank (MRR) of 68.02%, outperforming the baselines' performance. Furthermore, through ablation experiments, we explore the effectiveness of our proposed code representation approach. The results indicate that combining pa‐AST with the API sequence yields improved performance compared with using them individually. Moreover, our AST augmentation and pruning techniques significantly contribute to the overall results.

show abstract

Effective API recommendation without historical software repositories

Cited by 45 publications

References 29 publications

PyART: Python API Recommendation in Real-Time

PyART: Python API Recommendation in Real-Time

Dialogue Management for Interactive API Search

Application programming interface recommendation for smart contract using deep learning from augmented code representation

Contact Info

Product

Resources

About