Hello,
I'm working with the gam function and due to the amount of data I am
working with it is taking a long time to run. I looked at the tips to get
it to run faster, but none have acceptable side effects. That is the real
problem.
I have accepted that gam will run a long time. I will be running gam many
times for many different models. To make gam useable I am looking at
splitting the work up and putting all of it on an Amazon EC2 cloud. I have
a Windows machine and I'm (planning on) running Linux EC2 instances via
Amazon.
I have R running on one EC2 instance now. Now I'm looking to:
1) division of processing
2) creating/terminating instances via R
3) porting code and data to the cloud
4) producing plots on the cloud and getting them back on my (Windows)
computer for review
5) do all of the above programmically (over night)
I am new'ish to R, brand new to the cloud, and I am new to Linux (but I
have access to a Linux expert at my company). I'm looking for 1) guidance
so I am headed in the best direction from the start, 2) any gotchas I can
learn from, 3) package suggestions.
Thank you very much for your assistance!
Regards,
Ben
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
