This repo contains the code for producing the tidy data file based on the har data.
The code performs the following steps:
- read in the descriptive data files features.txt and activity_labels.txt
- read in the training and test data sets
- merge the data sets together
- add some column names to the merged data set - this uses the data read in step 1
- join the 3 separate files into one big data file of subject, activity and measurements
- extract just the columns we are interested in (mean and standard deviation)
- write out the new file