Tidy Data

Raw Data

Raw data is collected from the accelerometers from the Samsung Galaxy S smartphone on 30 subjects over 6 activities. Full details here.

Here lists the procedures the project performs to tidy the data. The run_analysis.R file details how to tidy the data.

Combine the training set (train/X_train.txt), training labels (train/y_train.txt), subject (train/subject_train.txt).
Repeat step 1 for the testing data.
Combine the training and testing data.
Import the feature names from features.txt; keep only the measurements on the mean and standard deviation for each measurement; name the dataset accordingly.
Import the activity names from activity_labels.txt, replace the activity index by its descriptive name respectively
Calculate the average of each variable for each activity and each subject.
Export the tidy data into "tidydata.txt".