Contextualized Data-Wrangling Code Generation in Computational Notebooks

• Published in: IEEE/ACM International Conference on Automated Software Engineering : [proceedings] pp. 1282 - 1294
• Main Authors: Huang, Junjie, Guo, Daya, Wang, Chenglong, Gu, Jiazhen, Lu, Shuai, Inala, Jeevana Priya, Yan, Cong, Gao, Jianfeng, Duan, Nan, Lyu, Michael R.
• Format: Conference Proceeding
• Language: English
• Published: ACM 27.10.2024
• Subjects: code generation; Codes; Computational modeling; computational notebooks; Context modeling; Data models; Data science; data wrangling; Large language models; Software; Software engineering; Source coding; Training
• ISSN: 2643-1572
• DOI: 10.1145/3691620.3695503

Data wrangling, the process of preparing raw data for further analysis in computational notebooks, is a crucial yet time-consuming step in data science. Code generation has the potential to automate the data wrangling process to reduce analysts' overhead by translating user intents into executable code. Precisely generating data wrangling code necessitates a comprehensive consideration of the rich context present in notebooks, including textual context, code context and data context. However, notebooks often interleave multiple non-linear analysis tasks into linear sequence of code blocks, where the contextual dependencies are not clearly reflected. Directly training models with source code blocks fails to fully exploit the contexts for accurate wrangling code generation.To bridge the gap, we aim to construct a high quality datasets with clear and rich contexts to help training models for data wrangling code generation tasks. In this work, we first propose an automated approach, CoCoMine to mine data-wrangling code generation examples with clear multi-modal contextual dependency. It first adopts data flow analysis to identify the code blocks containing data wrangling codes. Then, CoCoMine extracts the contextualized data-wrangling code examples through tracing and replaying notebooks. With CoCoMine, we construct CoCoNote, a dataset containing 58,221 examples for Contextualized Data-wrangling Code generation in Notebooks. To demonstrate the effectiveness of our dataset, we finetune a range of pretrained code models and prompt various large language models on our task. Furthermore, we also propose DataCoder, which encodes data context and code&textual contexts separately to enhance code generation. Experiment results demonstrate the significance of incorporating data context in data-wrangling code generation and the effectiveness of our model. We release code and data at https://github.com/Jun-jie-Huang/CoCoNote.CCS CONCEPTS* Software and its engineering → Automatic programming.