Spreadsheets are routinely used in business and scientific contexts, and one of the most vexing challenges is performing data cleaning prior to analysis and evaluation. The ad-hoc and arbitrary nature of data cleaning problems, such as typos, inconsistent formatting, missing values, and a lack of standardization, often creates the need for highly specialized pipelines. We ask whether an LLM can find its way around a spreadsheet and how to support end-users in taking their free-form data processing requests to fruition. Just like RAG retrieves context to answer users' queries, we demonstrate how we can retrieve elements from a code library to compose data preprocessing pipelines. Through comprehensive experiments, we demonstrate the quality of our system and how it is able to continuously augment its vocabulary by saving new codes and pipelines back to the code library for future retrieval.

In machine learning, hyperparameter optimization (HPO) is essential for effective model training and significantly impacts model performance. Hyperparameters are predefined model settings which fine-tune the model's behavior and are critical to modeling complex data patterns. Traditional HPO approaches such as Grid Search, Random Search, and Bayesian Optimization have been widely used in this field. However, as datasets grow and models increase in complexity, these approaches often require a significant amount of time and resources for HPO. This research introduces a novel approach using t-way testing---a combinatorial approach to software testing used for identifying faults with a test set that covers all t-way interactions---for HPO. T-way testing substantially narrows the search space and effectively covers parameter interactions. Our experimental results show that our approach reduces the number of necessary model evaluations and significantly cuts computational expenses while still outperforming traditional HPO approaches for the models studied in our experiments.

When a failure occurs in a big data application, debugging with the original dataset can be difficult due to the large amount of data being processed. This paper introduces a framework for effectively generating method-level tests to facilitate debugging of big data applications. This is achieved by running a big data application with the original dataset and by recording the inputs to a small number of method executions, which we refer to as method-level tests, that preserve certain code coverage, e.g., edge coverage. The size of each method-level test is further reduced if needed, while maintaining code coverage. When debugging, a developer could inspect the execution of these method-level tests, instead of the entire program execution with the original dataset. We applied the framework to seven algorithms in the WEKA tool. The initial results show that in many cases a small number of method-level tests are sufficient to preserve code coverage. Furthermore, these tests could kill between 57.58% to 91.43% of the mutants generated using a mutation testing tool. This suggests that the framework could significantly reduce the efforts required for debugging big data applications.