Message-ID: <alpine.LFD.2.03.1302040827570.21486@stats.ox.ac.uk>
Date: 2013-02-04T08:32:03Z
From: Brian Ripley
Subject: RandomForest, Party and Memory Management
In-Reply-To: <op.wrx3w2kbzqkd1e@garibaldi>
On Sun, 3 Feb 2013, Lorenzo Isella wrote:
> Dear All,
> For a data mining project, I am relying heavily on the RandomForest and Party
> packages.
> Due to the large size of the data set, I have often memory problems (in
> particular with the Party package; RandomForest seems to use less memory). I
> really have two questions at this point
> 1) Please see how I am using the Party and RandomForest packages. Any comment
> is welcome and useful.
>
>
>
> myparty <- cforest(SalePrice ~ ModelID+
> ProductGroup+
> ProductGroupDesc+MfgYear+saledate3+saleday+
> salemonth,
> data = trainRF,
> control = cforest_unbiased(mtry = 3, ntree=300, trace=TRUE))
>
>
>
>
> rf_model <- randomForest(SalePrice ~ ModelID+
> ProductGroup+
> ProductGroupDesc+MfgYear+saledate3+saleday+
> salemonth,
> data = trainRF,na.action = na.omit,
> importance=TRUE, do.trace=100, mtry=3,ntree=300)
>
> 2) I have another question: sometimes R crashes after telling me that it is
> unable to allocate e.g. an array of 1.5 Gb.
Do not use the word 'crash': see the posting guide. I suspect it
gives you an error message.
> However, I have 4Gb of ram on my box, so...technically the memory is there,
> but is there a way to enable R to use more of it?
Yes. I am surmising this is Windows but you have not told us so.
See the rw-FAQ. The real answer is to run a 64-bit OS: your computer
may have 4GB of RAM, but your OS has a 2GB address space which could
be raised to 3GB.
>
> Many thanks
>
> Lorenzo
>
--
Brian D. Ripley, ripley at stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UK Fax: +44 1865 272595