Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/98706
Title: Desarrollo de una GUI para el analisis y modelizacion de problemas de clasificacion
Author: Hernández Ballesteros, Susana
Tutor: Adsuar Gómez, Antonio Jesús
Abstract: The problem of classification of machine learning in general is one of the most common problems in the world of research and specifically in the field of bioinformatics. Being able to determine the class of a set of biological inputs within a group of options plays an important role. However, in order to carry out these analyzes, the user must have some knowledge of programming and knowledge about the different models available. This work aims to create a web application that allows users who do not have sufficient knowledge of programming, to perform a complete pipeline of data analysis with machine learning models for classification purposes. For this, a pipeline is developed in the R programming language that will mark the path to follow for the analysis and, later, this pipeline will be implemented in a web tool created by the Shiny tool. To check the correct functionality of both the pipeline and the web application, datasets with binary and multiclass target containing the data in one or two files have been used, in CSV format with different separators with both categorical and numeric variables that allow performing the analysis using different parameters. The tool allows to load the data, describe it, separate them and model them to determine which classification model is the most appropriate to apply to each data set.
Keywords: classification
Shiny
machine learning
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 4-Jun-2019
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
sherbalTFM0619memoria.pdf3,75 MBAdobe PDFThumbnail
View/Open