Skip to content
Back to formatted view

Raw Message

Message-ID: <zarafa.53e0cdf7.6cc5.4fc1e90215f751ee@home.ahschulz.de>
Date: 2014-08-05T12:28:38Z
From: Arne H. Schulz
Subject: Library(mice) too slow for my dataset
In-Reply-To: <DUB125-W846D9D3137B365EC5A9732B9E30@phx.gbl>

Dear Teresa,
using such services will only speed up the imputations significantly if you can split up/parallelize your code.

And maybe you can use more cores on your local machine by using packages like doSNOW, foreach and/or plyr. There are a lot of examples on the web.

Kind regards
Arne

-----Urspr?ngliche Nachricht-----
Von: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] Im Auftrag von M? Teresa Martinez Soriano
Gesendet: Dienstag, 5. August 2014 12:35
An: r-help at r-project.org
Betreff: [R] Library(mice) too slow for my dataset

Hi to everyone

I have a big dataset (40.000 columns (variables) and 50 rows)

I want to impute a lot of ?variables ?with ?library(mice), the problem is that this process is too slow (because of my dataset, the library is brilliant).

I am looking some options like Amazon web services, (?http://aws.amazon.com/es/datapipeline/developer-resources/?)

Has anyone used this service or knows other options?

Any ideas are welcome.

Thanks in advance

 		 	   		  
______________________________________________
R-help at 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.