@article{10902/35271,
year = {2020},
month = {10},
url = {https://hdl.handle.net/10902/35271},
abstract = {Input data of a data mining algorithm must conform to a very specific tabular format. Data scientists arrange data into that format by creating long and complex scripts, where different low-level operations are performed, and which can be a time-consuming and error-prone process. To alleviate this situation, we present Lavoisier, a declarative language for data selection and formatting in a data mining context. Using Lavoisier, script size for data preparation can be reduced by ⁓40% on average, and by up to 80% in some cases. Additionally, accidental complexity present in state-of-the-art technologies is considerably
mitigated.},
organization = {This work has been funded by the Spanish Government under grant TIN2017-86520-C3-3-R.},
publisher = {Elsevier},
publisher = {Journal of Computer Languages, 2020, 60, 100987},
title = {Lavoisier: a DSL for increasing the level of abstraction of data selection and formatting in data mining},
author = {Vega Ruiz, Alfonso de la and García Saiz, Diego and Zorrilla Pantaleón, Marta E. and Sánchez Barreiro, Pablo},
}