Stochastic geometry and the London underground

PoissonPoints

Way back when I was analysing London house price data for the Summer Data Challenge, I made a histogram of the distances from a random point in London to the nearest tube station. I noted that it peaked around half a kilometre, but ignored the shape of the distribution itself. This is an unfortunate faux pas for the accomplished procrastinator, so let’s right that wrong with the help of some stochastic geometry.

Continue reading

England and Wales House Prices

ScatterZoom-01

The last time I looked at house prices it went pretty well, and I ended up winning a data science competition. There I was only dealing with a million or so records, and a relatively small 120 MB dataset. Then I found out it was possible to download 3.7GB of property sale records for all of England and Wales since 1995, so let’s have another go. Continue reading

Writing a thesis

Word clouds corresponding to each chapter of the thesis

It’s done! After 58,627 words, 233 pages, 369 references, 162 figures and 3 lonely tables I finished my PhD thesis. Weighing in at 161.8MB, it was unceremoniously uploaded and that was that. Here are a few tips and observations I made on the way, which are probably only useful to those of you battling through a long Latex document. Never fear, normal blogging service will resume shortly.

Continue reading