IntroYesterday I gave a workshop on applied predictive modelling with caret at the 1st LSE Computational Social Science hackathon. Organiser privileges. I put together some introductory code and started a simple GitHub repo for the participants, so I thought I’d share it here as well. This is not supposed ...

It’s Happening, Folks!Whew! Less than a month left and I still haven’t publicised this on my blog. People, we are hosting the 1st Computational Social Science Hackathon at the London School of Economics and you are invited!It’s completely free an...

It’s Happening, Folks!Whew! Less than a month left and I still haven’t publicised this on my blog. People, we are hosting the 1st Computational Social Science Hackathon at the London School of Economics and you are invited!It’s completely free an...

Outcome Supervision Yesterday I was part of an introductory session on machine learning and unsurprisingly, the issue of supervised vs. unsupervised learning came up. In social sciences, there is a definite tendency for the former; there is more or less always a target outcome or measure that we want to ...

Outcome SupervisionYesterday I was part of an introductory session on machine learning and unsurprisingly, the issue of supervised vs. unsupervised learning came up. In social sciences, there is a definite tendency for the former; there is more or less always a target outcome or measure that we want to optimise ...

Get WikiTables from Lists Recently I was asked to submit a short take-home challenge and I thought what better excuse for writing a quick blog post! It was on short notice so initially I stayed within the confines of my comfort zone and went for something safe and bland. However, ...

Get WikiTables from Lists Recently I was asked to submit a short take-home challenge and I thought what better excuse for writing a quick blog post! It was on short notice so initially I stayed within the confines of my comfort zone and went for something safe and bland. However, ...

An Unlikely Pairing Last week, Marc Cohen from Google Cloud was on campus to give a hands-on workshop on image classification using TensorFlow. Consequently, I spent most of my time thinking about how I can incorporate image classifiers in my work. As my research is primarily on forecasting armed conflict ...

Introducing adavis My second ever post on this blog was on introducing adamap, a Shiny app that maps Americans for Democratic Action voting scores (the so-called Liberal Quotient) between 1947-2015. It was built with highcharter, and hence it was nicely interactive but quite slow. I wanted to switch to another ...

Quantitative Text Analysis Part II I meant to showcase the quanteda package in my previous post on the Weinstein Effect but had to switch to tidytext at the last minute. Today I will make good on that promise. quanteda is developed by Ken Benoit and maintained by Kohei Watanabe - ...

Quantifying He-Said, She-Said: Newspaper Reporting I have been meaning to get into quantitative text analysis for a while. I initially planned this post to feature a different package (that I wanted to showcase), however I ran into some problems with their .json parsing methods and currently waiting for the issue ...

Seasonality and Trends Time-series analysis is a battle on multiple fronts by definition. One has to deal with (dynamic) trends, seasonality effects, and good old noise. A general formula can be given as

y = level + trend + seasonality + noise

However, the relationships between these factors can be realized in many, and sometimes quite complex, ways. ...