R: create data set with average of each variable for each activity and each subject

Question

I am having issues on how to proceed with this R query. I have to create an independent tidy data set with the average of each variable for each activity and each subject.

The data set data_table looks like this:

These data have 10299 obs. (rows) and 81 variables (columns). Also, there are 30 subjects (1,...,30) and 6 different activities (STANDING, WALKING, WALKING UPSTAIRS, WALKING DOWNSTAIRS, SITTING, LAYING).

Therefore, I understand I need to have a mean for each variable corresponding to each one of the combinations of subject and activity. Example:

Col1     Col2         Col 3                  Col4
subject  activity     timeBody...-X mean     timeBody...-Y mean
1        STANDING     corresponding mean     corresponding mean
...      ...          ...                    ...
30       LAYING       corresponding mean     corresponding mean

I tried many things with the group_by, lapply, sumarrise,...but I have not been able to figure this out. Can you help me with this?

This is not [reproducible](http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example). — user2100721, Nov 08 '16 at 06:09
I'd recommend the `dplyr` solution with `summarize_each` [found here](http://stackoverflow.com/a/28677167/903061) — Gregor Thomas, Nov 08 '16 at 06:48

R: create data set with average of each variable for each activity and each subject

0 Answers0