
handle: 2183/46144
[Resumen]: La información constituye el principal recurso para el desarrollo de sistemas de Inteligencia Artificial. En general, cuanto mayor sea el volumen y la calidad de los datos utilizados durante el entrenamiento, mejores serán los resultados obtenidos por los modelos. Sin embargo, uno de los problemas más comunes en los conjuntos de datos reales es la presencia de valores faltantes o nulos, que afectan negativamente tanto a la calidad de los datos como al rendimiento de los modelos. Estos valores faltantes reducen la cantidad de información útil disponible, lo que limita la capacidad predictiva de los algoritmos de aprendizaje automático. En este trabajo, se desarrolla una librería en Python orientada al análisis y recuperación de valores faltantes mediante distintos métodos. El objetivo principal es minimizar la pérdida de datos al aplicar estrategias de imputación o eliminación, permitiendo así conservar la mayor cantidad posible de información sin comprometer la fiabilidad de los resultados.
[Abstract]: Information is the main resource for the development of Artificial Intelligence systems. In general, the larger and higher-quality the volume of data used during training, the better the results achieved by the models. However, one of the most common problems in real-world datasets is the presence of missing values or nulls, which negatively affect both data quality and model performance. These missing values reduce the amount of useful information available, thereby limiting the predictive capability of machine learning algorithms. In this work, a Python library was developed focused on the analysis and recovery of missing values using various methods. The primary objective is to minimize data loss by applying imputation or deletion strategies, thus preserving as much information as possible without compromising the reliability of the results.
Traballo fin de grao (UDC.FIC). Enxeñaría Informática. Curso 2024/2025
Machine Learning, Method evaluation, Evaluación de métodos, Modular library, Imputación de valor, Valores faltantes, Missing values, Librería modular, Value imputation, Aprendizaje Automático, Aprendizaje automático
Machine Learning, Method evaluation, Evaluación de métodos, Modular library, Imputación de valor, Valores faltantes, Missing values, Librería modular, Value imputation, Aprendizaje Automático, Aprendizaje automático
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
