Jessica Moore

Lei Zhang, Sean Howard, Tom Montpool et al.

There has been a massive explosion of data generated by customers and retained by companies in the last decade. However, there is a significant mismatch between the increasing volume of data and the lack of automation methods and tools. The lack of best practices in data science programming may lead to software quality degradation, release schedule slippage, and budget overruns. To mitigate these concerns, we would like to bring software engineering best practices into data science. Specifically, we focus on automated data validation in the data preparation phase of the software development life cycle. This paper studies a real-world industrial case and applies software engineering best practices to develop an automated test harness called RESTORE. We release RESTORE as an open-source R package. Our experience report, done on the geodemographic data, shows that RESTORE enables efficient and effective detection of errors injected during the data preparation phase. RESTORE also significantly reduced the cost of testing. We hope that the community benefits from the open-source project and the practical advice based on our experience.

Jacob Dormuth, Ben Gelman, Jessica Moore et al.

Many software analysis methods have come to rely on machine learning approaches. Code segmentation - the process of decomposing source code into meaningful blocks - can augment these methods by featurizing code, reducing noise, and limiting the problem space. Traditionally, code segmentation has been done using syntactic cues; current approaches do not intentionally capture logical content. We develop a novel deep learning approach to generate logical code segments regardless of the language or syntactic correctness of the code. Due to the lack of logically segmented source code, we introduce a unique data set construction technique to approximate ground truth for logically segmented code. Logical code segmentation can improve tasks such as automatically commenting code, detecting software vulnerabilities, repairing bugs, labeling code functionality, and synthesizing new code.

Ben Gelman, Bryan Hoyle, Jessica Moore et al.

Code search and comprehension have become more difficult in recent years due to the rapid expansion of available source code. Current tools lack a way to label arbitrary code at scale while maintaining up-to-date representations of new programming languages, libraries, and functionalities. Comprehensive labeling of source code enables users to search for documents of interest and obtain a high-level understanding of their contents. We use Stack Overflow code snippets and their tags to train a language-agnostic, deep convolutional neural network to automatically predict semantic labels for source code documents. On Stack Overflow code snippets, we demonstrate a mean area under ROC of 0.957 over a long-tailed list of 4,508 tags. We also manually validate the model outputs on a diverse set of unlabeled source code documents retrieved from Github, and we obtain a top-1 accuracy of 86.6%. This strongly indicates that the model successfully transfers its knowledge from Stack Overflow snippets to arbitrary source code documents.

Jessica Moore, Ben Gelman, David Slater

Descriptive comments play a crucial role in the software engineering process. They decrease development time, enable better bug detection, and facilitate the reuse of previously written code. However, comments are commonly the last of a software developer's priorities and are thus either insufficient or missing entirely. Automatic source code summarization may therefore have the ability to significantly improve the software development process. We introduce a novel encoder-decoder model that summarizes source code, effectively writing a comment to describe the code's functionality. We make two primary innovations beyond current source code summarization models. First, our encoder is fully language-agnostic and requires no complex input preprocessing. Second, our decoder has an open vocabulary, enabling it to predict any word, even ones not seen in training. We demonstrate results comparable to state-of-the-art methods on a single-language data set and provide the first results on a data set consisting of multiple programming languages.