Supporting single responsibility through automated extract method refactoring

• URL: http://arxiv.org/abs/2305.03428v2
• Date: Sun, 26 Nov 2023 08:42:12 GMT
• Title: Supporting single responsibility through automated extract method refactoring
• Authors: Alireza Ardalani, Saeed Parsa, Morteza Zakeri-Nasrabadi, Alexander Chatzigeorgiou
• Abstract summary: We propose a backward slicing algorithm to decompose a long method into slightly overlapping slices. The slices are computed for each output instruction, representing the outcome of a responsibility delegated to the method. On average, our experiments demonstrate at least a 29.6% improvement in precision and a 12.1% improvement in the recall of uncovering opportunities.
• Score: 48.0838443679187
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The responsibility of a method/function is to perform some desired computations and disseminate the results to its caller through various deliverables, including object fields and variables in output instructions. Based on this definition of responsibility, this paper offers a new algorithm to refactor long methods to those with a single responsibility. We propose a backward slicing algorithm to decompose a long method into slightly overlapping slices. The slices are computed for each output instruction, representing the outcome of a responsibility delegated to the method. The slices will be non-overlapping if the slicing criteria address the same output variable. The slices are further extracted as independent methods, invoked by the original method if certain behavioral preservations are made. The proposed method has been evaluated on the GEMS extract method refactoring benchmark and three real-world projects. On average, our experiments demonstrate at least a 29.6% improvement in precision and a 12.1% improvement in the recall of uncovering refactoring opportunities compared to the state-of-the-art approaches. Furthermore, our tool improves method-level cohesion metrics by an average of 20% after refactoring. Experimental results confirm the applicability of the proposed approach in extracting methods with a single responsibility.

Related papers

• Context-Enhanced LLM-Based Framework for Automatic Test Refactoring [10.847400457238423]
  Test smells arise from poor design practices and insufficient domain knowledge. We propose UTRefactor, a context-enhanced, LLM-based framework for automatic test in Java projects. We evaluate UTRefactor on 879 tests from six open-source Java projects, reducing the number of test smells from 2,375 to 265, achieving an 89% reduction.
  arXiv  Detail & Related papers  (2024-09-25T08:42:29Z)
• Domain Generalization via Rationale Invariance [70.32415695574555]
  This paper offers a new perspective to ease the challenge of domain generalization, which involves maintaining robust results even in unseen environments. We propose treating the element-wise contributions to the final results as the rationale for making a decision and representing the rationale for each sample as a matrix. Our experiments demonstrate that the proposed approach achieves competitive results across various datasets, despite its simplicity.
  arXiv  Detail & Related papers  (2023-08-22T03:31:40Z)
• TreeDQN: Learning to minimize Branch-and-Bound tree [78.52895577861327]
  Branch-and-Bound is a convenient approach to solving optimization tasks in the form of Mixed Linear Programs. The efficiency of the solver depends on the branchning used to select a variable for splitting. We propose a reinforcement learning method that can efficiently learn the branching.
  arXiv  Detail & Related papers  (2023-06-09T14:01:26Z)
• Calibrated Multiple-Output Quantile Regression with Representation Learning [12.826754199680472]
  We use a deep generative model to learn a representation of a response with a unimodal distribution. We then transform the solution to the original space of the response. Experiments conducted on both real and synthetic data show that our method constructs regions that are significantly smaller.
  arXiv  Detail & Related papers  (2021-10-02T14:50:15Z)
• A Boosting Approach to Reinforcement Learning [59.46285581748018]
  We study efficient algorithms for reinforcement learning in decision processes whose complexity is independent of the number of states. We give an efficient algorithm that is capable of improving the accuracy of such weak learning methods.
  arXiv  Detail & Related papers  (2021-08-22T16:00:45Z)
• Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning [85.50033812217254]
  Actor-critic methods are widely used in offline reinforcement learning practice, but are not so well-understood theoretically. We propose a new offline actor-critic algorithm that naturally incorporates the pessimism principle.
  arXiv  Detail & Related papers  (2021-08-19T17:27:29Z)
• A concise method for feature selection via normalized frequencies [0.0]
  In this paper, a concise method is proposed for universal feature selection. The proposed method uses a fusion of the filter method and the wrapper method, rather than a combination of them. The evaluation results show that the proposed method outperformed several state-of-the-art related works in terms of accuracy, precision, recall, F-score and AUC.
  arXiv  Detail & Related papers  (2021-06-10T15:29:54Z)
• Variable Instance-Level Explainability for Text Classification [9.147707153504117]
  We propose a method for extracting variable-length explanations using a set of different feature scoring methods at instance-level. Our method consistently provides more faithful explanations compared to previous fixed-length and fixed-feature scoring methods for rationale extraction.
  arXiv  Detail & Related papers  (2021-04-16T16:53:48Z)
• DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and $L_0$ Regularization [0.0]
  Modern neural network architectures typically have many millions of parameters and can be pruned significantly without substantial loss in effectiveness. The contribution of this work is two-fold. The first is a method for approximating a multivariate Bernoulli random variable by means of a deterministic and differentiable transformation of any real-valued random variable. The second is a method for model selection by element-wise parameters with approximate binary gates that may be computed deterministically or multiplicationally and take on exact zero values.
  arXiv  Detail & Related papers  (2020-12-07T13:08:56Z)
• Fast Template Matching and Update for Video Object Tracking and Segmentation [56.465510428878]
  The main task we aim to tackle is the multi-instance semi-supervised video object segmentation across a sequence of frames. The challenges lie in the selection of the matching method to predict the result as well as to decide whether to update the target template. We propose a novel approach which utilizes reinforcement learning to make these two decisions at the same time.
  arXiv  Detail & Related papers  (2020-04-16T08:58:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.