Exercise in the frame of the course "Getting and Cleaning Data"
https://class.coursera.org/getdata-003/
From a raw public datasets, build tidy dataset ready for later analysis
Tool used for that is R.
The repository contains:
- README.md
- UCI HAR Dataset.zip : raw data compressed (inputs)
- summarized-data.txt : tidy summarized data (output)
- run_analysis.R : script transforming the raw datasets into tidy one
- codebook.md : description of data
- R already installed
- R package "reshape2" installed, otherwise run in R:
install.packages("reshape2")
- Unzip the raw data in a folder
- Download and put the script "run_analysis.R" in same folder
- Launch R
- Set working directory as the folder in which raw data are unzipped
- write following command:
source("run_analysis.R")
When "COMPLETED" :
- A tidy dataset summarizing the variables from train and test datasets for each pair activity / subject : "summarized-data.txt"
====
Author: Jean-Sebastien Gourdet