Supervised, Unsupervised Learning & Data Visualization

Introduction

This is a final project for the Applied Data Science course. Main topics covered are data visualization, unsupervised learning (Multidimensional scaling, t-Distributed Stochastic Neighbor Embedding, PAM clustering), supervised learning (Multiple Linear and Log-linear Regressions, Decision (regression) trees and Random Forests) and related metrics. This project was planned to not only explore separate topics of supervised and unsupervised learning but also to compare them whereas possible, to determine the best approach to use considering presented data.

Working with two personal datasets, I performed data preparation, various data visualizations including regression trees, comparison of performing dimension reduction, clustering, and comparison of predictive models.

Datasets

Two personal datasets I've used:

• Data from activity tracker (Garmin Vivosmart 3)
• Data from phone usage application (Moment)