I\'m using Jtransforms java library to perform analysis on a given dataset.
An example of the data is as follows:
980,988,1160,1080,928,1068,1156,11
Each entry in the transform represent the (complex) magnitude of the frequency in the sample.
the power density in a given frequency is just the magnitude of the complex amplitude of the transform in that frequency. the magnitude of a complex number is computed from its components and you should not have a problem obtaining this
Each column represents amplitudes for increasing frequencies, starting from 0 (the first entry), then 2 Pi/T (where T is the length of your sample), until the last sample 2*Pi*N /T (where N is the number of samples)
there are other conventions where the transform is returned for the -Pi * N /T frequency up to Pi * N / T, and the 0 frequency component is in the middle of the array
hope this helps