I've done a cross-validated SVC analysis. Reading the scikit-learn docs for svc, I see this:
"Kernel cache size: For SVC, SVR, nuSVC and NuSVR, the size of the kernel cache has a strong impact on run times for larger problems. If you have enough RAM available, it is recommended to set cache_size to a higher value than the default of 200(MB), such as 500(MB) or 1000(MB)."
http://scikit-learn.org/stable/modules/svm.html
So I re-ran my analysis several times and timed the results using several different values for cache_size (50, 100, 200, 800, 1200, 2000, 4000, 8000).
My full analysis takes about 11.2 seconds when the cache_size is below 2000, and the time jumps to 40 seconds when the cache_size is greater than 2000.
The analysis takes place on a modern computer with 16 gigabytes of ram.
I'm wondering if anybody knows possible reasons why the processing time wouldn't change at all for any cache value below 2000, and why the processing time would get longer with higher values. Again, the computer has 16 gigs of ram and no signs of otherwise slowing occurs at any value of cache_size.
Thank you for anybody's thoughts.