cm103 2015-11-03 Tuesday overview
- HW07 due
Wednesday November 11 Friday November 13
- Bring the Candy Survey data – or part of it – to a ready-to-analyze state and do basic exploration.
- It is vital that you finish some task, nachos to cheesecake. We want a bit of story, some tables, some figures. Keep scaling back the cleaning and reshaping until you can manage this. Then scale up til you run out of time or patience.
We might add an optional regex exercise.
- The candy survey data is available:
Slides available on speakerdeck
Links from the slides or generally relevant to data cleaning
- An introduction to data cleaning with R, a PDF based on a tutorial given by Edwin de Jonge and Mark van der Loo at the useR!2013 conference.
- Excel and delimited files, a whopping two pages by JB on writing plain text delimited files from Excel. Writing a delimited file from Excel is often the first step in data cleaning, but some people are mysteriously reluctant to do this. Here’s how!