R help - Aug 2002 - asking for help (was RE: nnet trouble, continued)

> From: Sirotkin, Alexander [mailto:demiurg at ti.com]
> 
> P.S. Anybody who finds my postings insulting, please write a 
> mail filter
>     for my address. Although I can not understand why it may insult
>     anybody.
> 
> P.P.S. Must be related to cultural differences, I guess...
It's not insulting to me, personally, but quite possibly to the author of
that software, who spent unknown amount of time to create it and give it
away for free.

May I suggest that you learn how to ask questions in a way that will
actually encourage people to help you, if that is your intent?  For starter:

o Give the version info for VR (which includes nnet), R, and your OS.

o Give the command(s) that failed, not just the error message.

o Attach data used, or use a dataset included in R or one of the packages.  
  "Almost like the iris data" obviously isn't true: there are no
NAs in
iris.

I've used nnet quite a few times, and the only occasions that it failed is
when the data is too large.

Andy


------------------------------------------------------------------------------
Notice:  This e-mail message, together with any attachments, contains
information of Merck & Co., Inc. (Whitehouse Station, New Jersey, USA) that
may be confidential, proprietary copyrighted and/or legally privileged, and is
intended solely for the use of the individual or entity named in this message. 
If you are not the intended recipient, and have received this message in error,
please immediately return this by e-mail and then delete it.

=============================================================================
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

I agree (mostly) with what you've said here. I did not intend to send 
that comment
to the auther of the software. Well, maybe I should have checked who's 
the author
and wether or not he is subscribed to that list, but... In any case, I 
don't think it justified
the response, which was much more insulting.

As for the question itself - I already found that missing values in 
arguments to predict.nnet()
caused that error. I guess I just have to replace all NAs with means 
before using my data
with nnet. I though that the fact that nnet() accepts na.action = 
na.omit parameter suggests
that predict.nnet() will be able to deal with NAs in one way or another, 
but I guess it's not.

Anyway, thanks.

Liaw, Andy wrote:
>>From: Sirotkin, Alexander [mailto:demiurg at ti.com]
>>
>>P.S. Anybody who finds my postings insulting, please write a 
>>mail filter
>>    for my address. Although I can not understand why it may insult
>>    anybody.
>>
>>P.P.S. Must be related to cultural differences, I guess...
>>    
>>
>
>It's not insulting to me, personally, but quite possibly to the author
of
>that software, who spent unknown amount of time to create it and give it
>away for free.
>
>May I suggest that you learn how to ask questions in a way that will
>actually encourage people to help you, if that is your intent?  For starter:
>
>o Give the version info for VR (which includes nnet), R, and your OS.
>
>o Give the command(s) that failed, not just the error message.
>
>o Attach data used, or use a dataset included in R or one of the packages.  
>  "Almost like the iris data" obviously isn't true: there are
no NAs in
>iris.
>
>I've used nnet quite a few times, and the only occasions that it failed
is
>when the data is too large.
>
>Andy
>
>
>------------------------------------------------------------------------------
>Notice:  This e-mail message, together with any attachments, contains
information of Merck & Co., Inc. (Whitehouse Station, New Jersey, USA) that
may be confidential, proprietary copyrighted and/or legally privileged, and is
intended solely for the use of the individual or entity named in this message. 
If you are not the intended recipient, and have received this message in error,
please immediately return this by e-mail and then delete it.
>
>=============================================================================>
>

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._