Getting and Cleaning Data Course Project
The data was collected from sensors of smartphone carried by experiment subject when performing certain activity. There have been 30 subjects, and each subject performed 6 activities (WALKING, WALKING_UPSTAIRS, WALKING_DOWNSTAIRS, SITTING, STANDING, LAYING) wearing a smartphone (Samsung Galaxy S II) on the waist.
A full description is available at the site where the data was obtained.
The reshape2 package was required to melt() and dcast() the data frame.
- Download and unzip the data set file.
- Read the relevant files to variables:
- features.txt -> features
- activity_labels.txt -> act
- y_test.txt -> ytest
- y_train.txt -> ytrain
- subject_test.txt -> subj_test
- subject_train.txt -> subj_train
- X_test.txt -> xtest_df
- X_train.txt -> xtrain_df
- Merge the test and train data(xtest_df & xtrain_df),
cbind()the subject number (subj_test & subj_train) and activity labels (act) to the left of the merged data, and name the cols with features. - Extract the cols with "mean()" or "std()". Cols with "meanFreq()" are not included because it calculates the mean frequency not the mean value.
- Use the
melt()anddcast()functions to get the narrow tidy data. - Give the tidy data proper variable names and use
write.table()function to create a .txt file.