## From Pelican to Hugo

After some time using Pelican to keep up my site (not that I have doing that often enough), it started to get more complicated to get all the dependencies and plugins in line, in particular some minor tweaks I’ve done that broke some of my site builds – Long story short, I moved to Hugo.

## Introduction

For the “Practical Machine Learning” course at Coursera, the class was given a dataset from a Human Activity Recognition (HAR) study1 that tries to assess the quality of an activity (defined as “… the adherence of the execution of an activity to its specification …”), namely a weight lifting exercise, using data from sensors attached to the individuals and their equipment.

## Background

Sitepoint has published the results of their 2015 PHP Framework popularity survey1. In that post they show that the survey gives a very large edge to Laravel. The people at Sitepoint were also nice enough to publish their properly anonymized dataset in a github repo2

So I went ahead, and forked their repo and fired up R to give this data a go.

## Background

### Motivation

I am currently reading the book “Machine Learning with R”1 by Brent Lantz, and also want to learn more about the caret2 package, so I decided to replicate the SPAM/HAM classification example from the chapter 4 of the book using caret instead of the e10713 package used in the text.

There are other differences apart from using a different R package: instead of using as comparison the number of false positives, I decided to use the sensitivity and specificity as criteria to evaluate the prediction models. Also, I used the calculated models on a (different) second dataset to test their validity and prediction performance.