After a few thought provoking twitter conversations, this week I launched the first prototype of our Knife Classification tool built using FastAI and Streamlit (mirrored here).

Dressed up in a nifty package, the prototype currently:

  • Lets users upload pictures into a nifty, gorgeous web-app created in Streamlit, which works great on desktop or mobile
  • Classifies pictures into 1 of 5 knife “categories”, powered by a FastAI deep learning neural network
  • Asks for user feedback, using new pictures for model re-training

As usual, all the code is open-source (if not very well commented) — both the model training and development, as…

(or, why I wish I’d read the docs)

After much, much fighting it, last week I finally decided it was time to stop working entirely in Python, and figure out this R nonsense I keep hearing about. There are endless articles about which is best, so I won’t re-tread that here — suffice to say you can’t do everything in either — but there are a few niggles that I wish I’d learnt before I started. What I did instead was dive in head first, and wrote some very, very messy code exploring how burglary and robbery shifted under COVID lockdown in London.

With that in mind, here…

Quick and Dirty Predictions with LAPD Call Data

How hard is predicting policing demand in this age of easily accessible data-science? I’ve been exploring time series regression techniques, and while on the more advanced side they can get really complex, you can also use open source tools to quickly create operational insights, like here, where I’ve used publicly available LAPD call data to anticipate demand.

While some time series techniques require a fair bit of extra technical knowledge — I spent more time than any sane person should trying to understand how an ARIMA model works this weekend— we’re lucky in that Facebook has open-sourced their forecasting model…

What I Learnt Studying a Dying Market

A Note on Ethics

While writing this, I’ve tried to adhere to a few principles to try and balance the benefits and risks of sharing some of this information — I’ve listed those below:

  • This article will not teach you how to purchase drugs. I’ve purposefully not described in detail any steps to access any DNMs. Illegal drugs are dangerous, bad, and you won’t learn how to get them here.
  • I have anonymised the data to remove usernames that could be linked to other platforms or people — seller usernames have been replaced with unique numbers. …

Andreas Varotsis

quantitative crime science @ MPS | Coordinator @ Police Rewired | My (personal) thoughts on crime, data, and economics |

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store