Implementation of collaborative filtering using fastai and pytorch

AI model for summarizing and categorizing news articles

AD & PD cohort variable distributions

Clustering of 1,135 Arabidopsis thaliana genomes from 1001 Genomes Project (https://1001genomes.org/)

Analysis of the phylogeny and domains of OLIG2, as well as its expression in cerebral cells using t-SNE. And a chip-seq analysis to further investigate OLIG2 function.

Twitter Analysis Algorithms

This project is a flask app which allows to recommend 5 movies which are close to a chosen one. A demonstration is available at http://bit.ly/mk_recom_movies

En este repositorio se encuentra el Trabajo de Fin de Máster de la Titulación Máster en Ciencia de Datos por la Universitat Oberta de Catalunya.

Some introductory data science projects, along with code and documentation. Of course, these projects are university projects.

t-SNE visualization of parties participating in the Landtagswahl 2017 in NRW

LinguaNet is a language identification model built on DNNs using Python and TensorFlow. It utilizes character n-grams for accurate language classification. With an 89.2% accuracy, LinguaNet effectively identifies and differentiates languages. The repository includes model details, visualization of learned features, and implementation code.