RSS Challenge 2015

I thought I’d take a look at the RSS (Royal Statistical Society ) “Statistical Analytics Challenge” after being sent it at work today. It involves analysing eye movement on 60 pictures.

Whilst I’m not going to enter the competition I am going to have a go and see how far I get. My plan goes something like this:

  • Read the image into R
  • Split it into a grid
    • Initially a large grid and then progressively smaller ones
  • Calculate some properties of each of the grid cells
  • Check how each of these properties correlate with where the eye movement points are
  • Check the properties of the surrounding grid cells relative the current cell
  • See how these new properties interact with the eye movements.
  • Do each of the above for a number of pictures to come up with a model and then test this on one of the other pictures.

Read More

Creating a postcode file in R from different public data sources

Following on from my previous post on creating a postcode file with the 2015 general election results I wanted to create a larger file with more variables. Some from the ONS lookups, others from different public datasets. The one I have added so far is the Office of Communications Broadband Coverage dataset from 2013.

The final dataset will contain for each postcode in the UK:

  • The 2015 general election result
  • The Westminster Election Constituency
  • The Easting and Northing coordinates
  • Census lookup areas
  • Rural Indicator
  • Broadband coverage data
  • Which (if any) national park the postcode is in

Read More

Using the ONS postcode file to get the 2015 General Election Results by unit postcode

I was wanting to do some analysis on the results of the 2015 UK general election. In a lot of the datasets I use the only geographical marker I have is the unit postcode. So before I can do any analysis on the results I first need to map all of the UK constituencies onto a postcode list. Luckily for me this can be done using the ONS postcode file which has, amongst other things, the Westminster Electoral Constituencies for all UK unit postcodes. I would normally do this in SAS but since I'm learning R I thought I would do it there first.

First I need to get my data:

  • ONS postcode file

Mapping in Excel

Over the past year I've been having a play mapping things in Excel, not the best tool for doing this I know but it does the trick. Mapping the data directly from Excel has the advantage that I've my data is already in Excel. I would like to do the same exercise in R but that's for another day once I get to know R better.

The method I used is based on tips and methods used on Chandoo and Clear and Simply.

My output looks like this:

Which looks pretty good to me.
Read More