Research On Code Line Recommendation Based On Context Of Programming

In the Onsite Programming of software development,there are a lot of information related to the current development task,such as code line context information,user development intention,etc.Therefore,if developers can get next code line or lines in advance by making full use of the existing information in the Onsite Programming and contextual relationships among code lines,then it will not only help the developer to complete the development task better,but also improve the efficiency.However,most existing approaches only focus on code repair or completion,which seldom considers how to meet the demand of recommending code lines based on contextual information.To solve this problem,a feasible solution is using deep learning methods to extract the relevant context factors of code lines through mining hidden context information based on the existing massive source data.Therefore,this paper proposes a novel approach based on deep learning for Onsite Programming.In this approach,the contextual relationships among various code lines are learned from existing large-scale code data sets and then Top-N code lines are recommended to programmers.The approach utilizes the well-known RNN Encoder-Decoder framework,which can encode several lines of code to a vector with context-aware information,and then obtain new codes line based on the context vector.Aiming to ensure the source code data,which comes from the open source data platform,has high quality,this paper proposes an approach to data quality evaluation for open source code.This paper researches how to define and evaluate the quality of source code extracted on Git Hub.An evaluation framework is proposed to analyze the code method data quality from five dimensions.The benefits of the approach can support related researchers to construct data sets with higher quality and make further improvement in intelligent application effects.Finally,the approach is empirically evaluated with the large-scale source code data come from open source platform.By comparing the evaluated results of our method between code data set without and with processing by approach to data quality evaluation,this paper verifies whether the proposed approach to data quality evaluation and analysis for open source code can improve the effectiveness of the code line recommendation method proposed in this paper.