[R] Problem in Binning of a data set

[Petr PIKAL]

Hi

well AFAICS nothing is in contradiction what I recommended so far.

> test<-read.delim("clipboard", sep="")

> head(test)
     A R  F  M
1 man1 1 11 21
2 man2 2 12 22
3 man3 3 13 23
4 man4 4 14 24
5 man5 5 15 25
6 man6 6 16 26
>

> rf<-cut(test$R, c(0,3,6,100))
> ff<-cut(test$F, c(0,13,16,100))
> mf<-cut(test$M, c(0,23,26,100))
> split(test, interaction(rf,ff,mf))
$`(0,3].(0,13].(0,23]`
     A R  F  M
1 man1 1 11 21
2 man2 2 12 22
3 man3 3 13 23

$`(3,6].(0,13].(0,23]`
[1] A R F M
<0 rows> (or 0-length row.names)

$`(6,100].(0,13].(0,23]`
[1] A R F M
<0 rows> (or 0-length row.names)

$`(0,3].(13,16].(0,23]`
[

Regards

Petr
petr.pikal at precheza.cz
724008364, 581252140, 581252257


"sumit gupta" <sumit.iitm at gmail.com> napsal dne 19.06.2008 12:13:27:

> 
> Hi..
> 
> I am giving a toy example here..
> 
>            R          F       M
> man1   1          11      21
> man2   2          12      22
> man3   3          13      23
> man4   4          14      24
> man5   5          15      25
> man6   6          16      26
> man7   7          17      27 
> man8   8          18      28
> man9   9          19      29
> man10  10        20      30
> Now I want to split the above data for following intervals
> R1- (1-3)    F1(11-13)     M1(21-23)
> R2- (4-6)    F2(14-16)     M1(24-26)
> R3- (7-10)   F3(17-20)     M1(27-30)
> now I want to create folowing 27 ( 3X3X3) bins 
> 1  R1,F1,M1 
> 2  R1,F1,M2
> 3  R1,F1,M3
> 4  .
>    .
>    .
>    .
>    .
> 9  R1,F3,M3
> 
> 10  R2,F1,M1 
> 11  R2,F1,M2
> 12  R2,F1,M3
> 13 .
>    .
>    .
>    .
>    .
> 18  R2,F3,M3
> 
> 19  R3,F1,M1 
> 20  R3,F1,M2
> 21  R3,F1,M3
> 22  .
>    .
>    .
>    .
>    .
> 27  R3,F3,M3
> and save each bin as a separate data set.
> 
> Thanx in advance
> Sumit
> 
> 
> On 6/19/08, Petr PIKAL <petr.pikal at precheza.cz> wrote: 
> Hi
> 
> "sumit gupta" <sumit.iitm at gmail.com> napsal dne 18.06.2008 14:24:28:
> 
> > the range of data in all three columns is different. so obviously the
> cut
> > points are different.
> > What I want to do is to create a 3D matrix
> >
> > Lets say I have the following data
> >
> > A              B              C
> > 500           5               4000
> > 563           4               6540
> > 563           4               3456
> > 587           2               8000
> > .               .                 .
> > .               .                 .
> > Now I will divide each and every colums in 3 bins
> A1,A2,A3,B1,B2,B3,C1,C2,C3
> >
> > Now I want a matrix like
> >
> > for
> > C1
> >
> >                 A1       A2       A3
> >  B1           a         b          c
> >  B2           d          e          f
> >  B3           g         h           i
> >
> > and create a separate table for each bin( a,b,c,d,e,f,g,h,i) that is
> what all
> > elements are there in each bin a ,b, c, and so on..
> > I hope this clarify the problem.
> 
> Not too much. What do you mean by bins? Is it some range of values from
> respective column? E.g. for A column the A1 bin is from 0 to 570? Then 
you
> can use my suggestion to split your whole data to list according to
> created factor.
> 
> And of course you can do it for B and C values too, e.g. with 
interaction.
> 
> split(data, interaction(A.bins, B.bins, C.bins))
> 
> shall give you a list of data values which are located in respective 
bins.
> If you are not satisfied with my answer, please do as posting guide
> suggests and provide some toy example which can be reproduced.
> 
> Regards
> Petr
> 
> >
> > Thanx
> > Regards,
> > Sumit
> >
> 
> > On 6/18/08, Petr PIKAL <petr.pikal at precheza.cz> wrote:
> > Hi
> >
> > Well. I am a bit lost in your bins. If I understand correctly you 
shall
> > have some factor with bin values
> >
> > bin.f <- cut(some data, levels)
> >
> > then you can split your data according to values of bin.f
> >
> > split(complete data, bin.f)
> >
> > If this does not solve your problem just throw it to some other bin 
:-)
> >
> > Regards
> > Petr
> >
> > r-help-bounces at r-project.org napsal dne 18.06.2008 08:04:50:
> >
> > > Hello,
> > >
> > > I am having problem with binning the data. I have a 50X3 matrix and 
I
> > binned
> > > the data for all the 3 columns. Using table command I got the total
> no.
> > of
> > > elements in a particular bin.
> > > Could you please tell me how to see that what all elements are there
> in
> > a
> > > particular bin and then create a different matrix for each bin?
> > >
> > > Thanks.
> > >
> > > Regards,
> > > Sumit
> > >
> > >    [[alternative HTML version deleted]]
> > >
> > > ______________________________________________
> > > 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.
> 
> >
> >
> >
> > --
> > Sumit Kumar Gupta
> > 4thYear ,Biotechnology
> > IIT Madras
> 
> 
> 
> -- 
> Sumit Kumar Gupta
> 4thYear ,Biotechnology
> IIT Madras