run_analysis.R

The run_analysis.R script is a script written to fulfill the requirements for the project in the Getting and Cleaning Data course offered by Coursera. The course was initially undertaken in August 2015.

There is no need to download the files to your hard drive or unzip them, as the script takes care of that.

The script does the following:

• Installs the packages required
• Downloads the raw .zip file from the internet to the users working directory
• Unzips the files
• Extracts the data in the individual files
• Compiles the data into one data set
• Extracts the mean and standard deviation of variables from the whole set
• Transforms variable names into human readable names (see the Variable Descriptions Codebook for further details)
• Makes a few more modifications to the variable names given in the original .txt files for the raw data.
• These include removing duplications within variable names
• Converting to camel case
• Replacing abbreviations for words with the words themselves.
• Variable names are also modified to remove any potentially ambigous nature to them.

Output

The script creates a tidy data set from the combined data, according to the principles outlined by Hadley Wickham (Journal of Statistical Software, “Tidy Data”, Vol. 59, Issue 10, Sep 2014, http://www.jstatsoft.org/v59/i10) downlaodable in pdf format from http://vita.had.co.nz/papers/tidy-data.pdf.

The script writes the tidy data set to a table.

Reading the data set back into R

The following code can be used to read the file back into R: tidy <- read.table(“./average.txt”, quote = “”, header = TRUE, fill = TRUE, check.names = FALSE)

Expected Structure of Output

The data set dimensions are:

dim(tidy)

[1] 180 68

An expected output for a portion of the data set is: “Activities” “SubjectId” “TBodyAccelerationMeanX” 1 “Laying” 1 0.2215982 2 “Sitting” 1 0.2612376 3 “Standing” 1 0.2789176 4 “Walking” 1 0.2773308 5 “WalkingDownstairs” 1 0.2891883

Requirements for running the script:

1. Set the working directory in the script by changing the path in line 2 of the code. i.e. > setwd(“/Users/tina/desktop/GaCD_Project”) The path must be indicated as the arguement to setwd(), within quotation marks.

2. If the link to the .zip files has changed from the link given in line 14 of the code, i.e. > dataFile <- “https://d396qusza40orc.cloudfront.net/getdata%2Fprojectfiles%2FUCI%20HAR%20Dataset.zip” Insert the updated https address.

3. Save the script and source it.