Published:
Last week I passed the BCS Business Analysis Foundation exam. Preparation took me about a week, with a good deal of cramming over one weekend — though I'd already covered a lot of the material on an earlier project management... Read more
Published:
Introduction The latest stable version of my UK geocoder package has finally made it to CRAN . PostcodesioR is a wrapper for postcodes.io and it provides multiple functions to work with UK geospatial data. The package draws exclusively on open... Read more
Published:
My task was to extract pitch values from a long list of audio files. Previously I'd used Praat and R for this, but looping in R was rather slow, so I went looking for another approach. I developed the following... Read more
Published:
In my previous post , I described how to split audio files into chunks in R. This time I wanted to use Python to prepare long audio files (. mp3 ) for further analysis. The typical use case is splitting... Read more
Published:
R might not be the most obvious choice for analysing audio data, but a growing number of packages now make it possible to analyse and synthesise sound. One of them is seewave, and Jérôme Sueur , one of its authors,... Read more
Published:
Creating a spectrogram is a basic step in almost any analysis of audio signals — it shows how the frequencies in a sound change over time. Happily, R has a good few packages for the job, and here I’ll run... Read more
Published:
HOMER2 expects a particular .nirs format that can’t contain consecutive triggers (also called Marks in Hitachi files). The hitachi2nirs MATLAB script does strip the markers, but I wanted to recreate the whole process myself and be sure I was doing... Read more
Published:
Niedawno odnalazłem ciekawy pakiet geofacet , który umożliwia rozmieszczenie wykresów zgodnie z ich pozycją na mapie. Główna funkcja facet_geo() zastępuje facet_wrap() z ggplot2. Polska mapa jeszcze nie jest dostępna w standardowym pakiecie geofacet, ale mam nadzieję, że już wkrótce tam... Read more
Published:
Zoopla offers limited access to its API , which serves up the latest property prices and area indices. I wrote an R package for querying it — see the GitHub documentation or zooplaR’s page for the latest. Read more
Published:
Introduction Read more
Published:
After a while of using R notebooks, I found working with MATLAB in its IDE really unintuitive. I’d read that you can run MATLAB from IPython, but the instructions seemed a bit dated, and following them still didn’t get MATLAB... Read more
Published:
While developing another R package, I lost a bit of time working out how to add code coverage to it. I’d had the same trouble the time before, so this time I decided to write up the procedure step by... Read more
Published:
The quickest way to plot ETG-4000 data in R is plot_ETG4000() from the fnirsr package. But if you want to explore your data in more detail, an interactive plot works better. Read more
Published:
I hadn’t touched fnirsr (my R package for analysing fNIRS data) in a while, so I decided it was time for some improvements. I read a great introduction to Travis CI and was determined to get it working this time.... Read more
Published:
Here’s a quick demonstration of the notebook that ships with the fnirsr package: Read more
Published:
While designing my latest experiment in PsychoPy , I realised that setting up the serial port connection is far from obvious. I wrote this tutorial so that others — and future me — don’t have to waste time reinventing the... Read more
Published:
As I mentioned in my previous post , I’m getting to grips with analysing fNIRS data collected on a Hitachi ETG-4000. A recording session can be saved as a raw CSV file (here’s an example ), and it’s fairly straightforward... Read more
Published:
I’ve recently been learning to use the Hitachi ETG-4000 for functional near-infrared spectroscopy (fNIRS) in my research. I quickly discovered that, as so often in neuroscience, the main analysis packages are written in MATLAB. I couldn’t find any R code... Read more
Published:
As a fan of both open data and the Royal Opera House (ROH), I was excited to find an article promising that the ROH’s data might be opened up. That article was from 2014, though, and the only open ROH... Read more
Published:
I found a new dataset on UK broadband speeds and started analysing it in R. Once the data was cleaned, though, building a dashboard in Shiny looked like it would take too long, so I switched to Tableau. To keep... Read more
Published:
When I work with UK geographical data, I often need to extract geolocation information for postcodes. A handy way to do this in R is the geocode function from the ggmap package, which returns latitude and longitude via the Google... Read more
Published:
One of my recent tasks at work was to analyse the Brexit referendum results alongside the UK housing market.Happily, everything except the rental data (which came from Zoopla) was publicly available. The property and rental prices took some wrangling, because... Read more
Published:
Kaggle released a new dataset that looked perfect for trying out the interactive visualisations from the qtlcharts , ggvis , and radarchart packages. Read more
Published:
A while ago I discovered the London Datastore , a government data repository with a wide range of interesting datasets. One that caught my eye breaks down England’s school population by first language. As a non-native English speaker myself, I... Read more
Published:
Kaggle released another interesting dataset, this time the loan book of a peer-to-peer lender, Lending Club. Read more
Published:
Last month I entered my first Kaggle competition , working with BNP Paribas Cardif’s data. The official aim was to speed up the claims management process; my own goal was simply to put some machine learning techniques into practice. That... Read more
Published:
One of my work projects that gained a lot of publicity was an analysis of residential property sales in England and Wales. The underlying data is collected by the Land Registry and is publicly available. Read more
Published:
R has plenty of plotting libraries, and you can combine them with open GIS data to build custom maps. In this post I’ll walk through a few. Read more
Published:
Kaggle publishes plenty of interesting datasets, and one of them brings together several world university rankings . I thought I’d run a quick analysis of the CWUR data and map it in R with the rworldmap package. Read more
Published:
Praat is a great tool for analysing speech data, but I recently ran into a frustrating problem. Whenever I tried to open a txt file (a vector of numbers) in Praat, I’d get this error: File not recognized. File not... Read more
Published:
I finally found some time to crunch the numbers from a Kaggle swag competition . The dataset was rather large, but I wanted to focus on the most recent figures (from 2013), so I only analysed MERGED2013_PP.csv . I started... Read more
Published:
I’m back to analysing political data, having found a nicely formatted dataset on one of my favourite blogs . The post that got me started asked whether you can predict election results from polls and online popularity data. The short... Read more
Published:
Lately I’ve been toying with the idea of comparing how popular different people and ideas are. I’ve already queried Wikipedia page views in R, but I wondered whether I could do something similar with Google Trends or Google Ngrams .... Read more
Published:
I recently came across an interesting data journalism project called The Migrants’ Files , which collects and analyses information about migration. The data on dead and missing would-be migrants was publicly available, so I built a dashboard in Tableau using... Read more
Published:
Tableau Desktop 9.1 is out, and it introduces Web Data Connectors as a new type of data source. Handily, Tableau shipped a few working connectors to popular web data sources, and Google Sheets is one of them. I tried connecting... Read more
Published:
Quandl is a great source of all sorts of data, and it plugs straight into R . I wanted to have a play with some of it and see what insights I could tease out. Read more
Published:
I found an interesting dataset on Figshare showing how much University College London spent on Article Processing Charges (APCs). Its description says it should cover 1 April 2013 to 31 July 2014, but a few entries fall outside that window,... Read more
Published:
I recently came across a dataset published by Research Councils UK (RCUK) on the diversity of grant applicants. The report didn’t include a single plot, so I thought I’d fix that. Annoyingly, it was only available as a PDF, which... Read more
Published:
Times Higher Education published its 2015 pay survey back in April, but I’ve only just found time to turn the data into some interactive visualisations. Read more
Published:
The Department for Education regularly publishes a list of educational establishments in England and Wales. I wanted to see which areas have the most schools with Speech Special Educational Needs Coordinators (SENCOs), and what those schools look like. To find... Read more
Published:
Tableau 9.0 doesn’t include Polish post codes (yet?), so I built a map to show them myself. Read more
Published:
I needed to extract mean pitch values from recordings of human speech, and I wanted to automate the job so I could rerun my analyses easily. So I wrote a couple of scripts to do it much faster. Read more
Published:
I use EEGLAB to process my electroencephalographic data (that is, the brain’s electrical activity), but I wanted an interactive visualisation to show how different filter settings change the signal. I prefer R to MATLAB, so I built a Shiny app... Read more
Published:
I recently read an article (in Polish) about the Polish police massaging their statistics. It made me wonder what data they publish on their website, and whether any interesting patterns might turn up. Read more
Published:
With the 2015 General Election on the way, I thought I’d compare how popular the main UK political parties are on Wikipedia. Read more
Published:
After reading the paper by Steen et al. (2013) , I decided to have a play with the data published alongside it. Such an interesting topic deserved interactive plots, so I built some in Tableau. Read more