Course project for Coursera "Getting and Cleaning Data" course (August 2014)
This project consists of an R script "run_analysis.R" that tidies the UCI HAR Dataset as long as it is in the working directory. Its output is described in the codebook.
The plyr package is required to run the script.
- Reads test and train data and combines them into a single data frame
- Subsets the dataframe into mean and standard deviation features
- For each observation, maps activity index to its descriptive activity name
- Names each feature column to its correct feature name
- For each combination of subject and activity, creates a data frame containing the average of each feature
The script creates several variables, with the tidy
variable being the final output.