- Download this data into your R working directory. And directly unzip downloaded file right into working directory. (You should find the "UCI HAR Dataset" folder.)
- Run the "run_analysis.R".
- In the working directory, "step5.txt" will be generated.
- At first, it reads in fragmented datasets within the "UCI HAR Dataset" folder.
- It combines activity label and subject number data, and then combines test and train datasets all together. Finally, it organizes the col names.
- Then, it extracts only mean() and std() information together with activity label and subject number data.
- Afterward, it starts to make activity labels and col names more descriptive.
- Finally, by using dplyr package, it summarises the mean of each variable by each activity and each subject.
- Reference of variables is in CodeBook.md