Data 624 - Predictive Analytics - Homework 8

Este es el taller 4 respecto a la materia de programación 2 de la carrera de Estadistica

En este taller, se trasladaron los ejercicios del taller 2 y 3 realizados en R a un formato de R Markdown. A través de este proceso, se aprendió a combinar código, resultados y explicaciones en un único documento, aprovechando las capacidades de R Markdown para generar informes reproducibles. Este informe incluye todos los ejercicios realizados, junto con sus resultados y las explicaciones correspondientes.

My partners and I predicted the source based on a word from the articles we chose. We chose articles about sleep from Scientific American and Time Magazine and split each article into paragraphs to increase the size of our data set. Then we tokenized our words and used factors such as the amount of times a word showed up in a particular source to predict which source a given word would come from. We used both supervised and unsupervised learning (Hierarchical Clustering, PCA) to do this.

In this assignment, we (my partners and I) used k-Nearest Neighbors, Linear Discriminant Analysis, and Decision Trees to predict which wines in a new data set would be classified as good quality wines and which ones would be classified as bad quality wines.

This is a recommender system for movies based on movie rating.