top of page
PCA can be a powerful tool for spectral decomposition of variable X-ray data. It is particularly useful when multiple variable components contribute to the net spectrum and variance, as these components can then be isolated.
​
The code for used for this analysis can be found through the link below, although significant modification may be required depending on the use case.
​
Please bear in mind that I wrote this code while I was still a graduate student, and it is inefficient and poorly documented! The basic methodology is to construct a 2D array of normalised residual count rates as a function of time and energy, then pass that array through the numpy singular value decomposition function.
​
bottom of page