ydata-profiling: Accelerating data-centric AI with high-quality data

• Tipo: Artigo em Revista Científica Internacional
• Data: 2023

Autores

Clemente, F (Autor) Outra; Ribeiro, GM (Autor) Outra; Quemy, A (Autor) Outra; Santos, MS (Autor) Outra; Pereira, RC (Autor) Outra; Barros, A (Autor) Outra

Revista

Título: Neurocomputing

Vol. 554

ISSN: 0925-2312

Editora: Elsevier

Indexação

ISI Web of Knowledge - 9 Citações

Scopus - 12 Citações

Outras Informações

ID Authenticus: P-010-7KQ

DOI: 10.1016/j.neucom.2023.126585

Abstract (EN): ydata-profiling is an open-source Python package for advanced exploratory data analysis that enables users to generate data profiling reports in a simple, fast, and efficient manner, fostering a standardized and visual understanding of the data. Beyond traditional descriptive properties and statistics, ydata-profiling follows a Data-Centric AI approach to exploratory analysis, as it focuses on the automatic detection and highlighting of complex data characteristics often associated with potential data quality issues, such as high ratios of missing or imbalanced data, infinite, unique, or constant values, skewness, high correlation, high cardinality, non-stationarity, seasonality, duplicate records, and other inconsistencies. The source code, documentation, and examples are available in the GitHub repository: https://github.com/ydataai/ydata-profiling.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 10