Andrew Davison

Andrew Davison

PhD in Statistics

Posts by Tags

R

What data do companies have on me? (Part 1: Spotify)

24 minute read

Published:

Recently I’ve been curious as to the extent to which different companies will track and keep data on me, and also what data they are willing to share with me if I request it. In a series of articles, I’m going to take a look at a few different companies which will be collecting data on me (either for the purposes of recommender systems or for advertising) and what they’ll let me download, and have a look to see what insights about myself and my own behavior I can gain from it. Hopefully I can learn something interesting about both myself, and also a bit more about the way in which different companies will store and process the data they collect on me.

algs

Using MCMC to manipulate images

5 minute read

Published:

A few years ago, I was interested in exploring some ideas around the content of images and vision, and in trying to think of ways of reconstructing images from smaller amounts of information. At this point those who are “technically inclined” may think of compression techniques or using wavelet bases, but I was interested in doing something a bit more artistic. In playing around with this, I ended up coming up with an idea based around sampling a small percentage of pixels in the image and drawing paths between them, which to me gives rise to some interesting looking images:

companies

What data do companies have on me? (Part 1: Spotify)

24 minute read

Published:

Recently I’ve been curious as to the extent to which different companies will track and keep data on me, and also what data they are willing to share with me if I request it. In a series of articles, I’m going to take a look at a few different companies which will be collecting data on me (either for the purposes of recommender systems or for advertising) and what they’ll let me download, and have a look to see what insights about myself and my own behavior I can gain from it. Hopefully I can learn something interesting about both myself, and also a bit more about the way in which different companies will store and process the data they collect on me.

data

Using MCMC to manipulate images

5 minute read

Published:

A few years ago, I was interested in exploring some ideas around the content of images and vision, and in trying to think of ways of reconstructing images from smaller amounts of information. At this point those who are “technically inclined” may think of compression techniques or using wavelet bases, but I was interested in doing something a bit more artistic. In playing around with this, I ended up coming up with an idea based around sampling a small percentage of pixels in the image and drawing paths between them, which to me gives rise to some interesting looking images:

What data do companies have on me? (Part 1: Spotify)

24 minute read

Published:

Recently I’ve been curious as to the extent to which different companies will track and keep data on me, and also what data they are willing to share with me if I request it. In a series of articles, I’m going to take a look at a few different companies which will be collecting data on me (either for the purposes of recommender systems or for advertising) and what they’ll let me download, and have a look to see what insights about myself and my own behavior I can gain from it. Hopefully I can learn something interesting about both myself, and also a bit more about the way in which different companies will store and process the data they collect on me.

python

Using MCMC to manipulate images

5 minute read

Published:

A few years ago, I was interested in exploring some ideas around the content of images and vision, and in trying to think of ways of reconstructing images from smaller amounts of information. At this point those who are “technically inclined” may think of compression techniques or using wavelet bases, but I was interested in doing something a bit more artistic. In playing around with this, I ended up coming up with an idea based around sampling a small percentage of pixels in the image and drawing paths between them, which to me gives rise to some interesting looking images: