Getting and Cleaning Data Course Project

This repository contains the files for the Johns Hopkins Coursera Getting and Cleaning Data course project.

Files

• run_analysis.R: R script that downloads, cleans, merges, and summarizes the data.
• CodeBook.md: Describes the source data, variables, and transformations.
• tidy_data.txt: Final tidy data set created by running run_analysis.R.

How to run

1. Put run_analysis.R in your working directory.
2. Open R or RStudio.
3. Set your working directory to the folder containing run_analysis.R.
4. Run:

source("run_analysis.R")

The script downloads and unzips the data if needed, then creates tidy_data.txt in the working directory.

What the script does

The script performs the following steps:

1. Merges the training and test sets into one data set.
2. Extracts only mean and standard deviation measurements.
3. Uses descriptive activity names.
4. Labels variables with descriptive names.
5. Creates a second tidy data set with the average of each variable for each activity and subject.