[R] Partition into quantiles

2006-10-05 Thread Alberto Monteiro 
Is there any function that divides a sample into N quantiles?

For example, for N = 2, this would be the solution:

x - rnorm(100)
m - median(x)
q - ifelse(x = median, 1, 2)

Alberto Monteiro

__
R-help@stat.math.ethz.ch 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.

Re: [R] Partition into quantiles

2006-10-05 Thread Peter Dalgaard 
Alberto Monteiro [EMAIL PROTECTED] writes:

 Is there any function that divides a sample into N quantiles?
 
 For example, for N = 2, this would be the solution:
 
 x - rnorm(100)
 m - median(x)
 q - ifelse(x = median, 1, 2)

Have a look at

 N - 2
 table(cut(x,quantile(x,seq(0,1,1/N)), include.lowest=TRUE))

[-2.78,0.205]  (0.205,2.22]
   5050

 table(cut(x,c(-Inf,quantile(x,(1:(N-1))/N),Inf)))

(-Inf,0.205] (0.205, Inf]
  50   50

-- 
   O__   Peter Dalgaard Øster Farimagsgade 5, Entr.B
  c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K
 (*) \(*) -- University of Copenhagen   Denmark  Ph:  (+45) 35327918
~~ - ([EMAIL PROTECTED])  FAX: (+45) 35327907

__
R-help@stat.math.ethz.ch 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.

Re: [R] Partition into quantiles

2006-10-05 Thread Richard M. Heiberger 
cut.quantile - function(x, N, use.ppoints=TRUE) {
  qq - if (use.ppoints) c(0,ppoints(N-1),1)
  else seq(0, 1, 1/N)
  breaks - quantile(x, qq)
  breaks[1] - breaks[1] - 1 
  breaks[N+1] - breaks[N+1]+1
  cut(x, breaks)
}

tmpT - cut.quantile(rnorm(100), 10, TRUE)
table(tmpT)
tmpF - cut.quantile(rnorm(100), 10, FALSE)
table(tmpF)

__
R-help@stat.math.ethz.ch 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.

Re: [R] Partition into quantiles

2006-10-05 Thread David Barron 
You might also want to look at the function quantcut in the gtools
package (part of the gregmisc bundle).



On 05/10/06, Alberto Monteiro [EMAIL PROTECTED] wrote:
 Is there any function that divides a sample into N quantiles?

 For example, for N = 2, this would be the solution:

 x - rnorm(100)
 m - median(x)
 q - ifelse(x = median, 1, 2)

 Alberto Monteiro

 __
 R-help@stat.math.ethz.ch 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.



-- 
=
David Barron
Said Business School
University of Oxford
Park End Street
Oxford OX1 1HP

__
R-help@stat.math.ethz.ch 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.

Re: [R] Partition into quantiles

2006-10-05 Thread Frank E Harrell Jr 
David Barron wrote:
 You might also want to look at the function quantcut in the gtools
 package (part of the gregmisc bundle).

Also, cut2 in Hmisc will do this and will label the intervals compactly.

Frank

 
 
 
 On 05/10/06, Alberto Monteiro [EMAIL PROTECTED] wrote:
 Is there any function that divides a sample into N quantiles?

 For example, for N = 2, this would be the solution:

 x - rnorm(100)
 m - median(x)
 q - ifelse(x = median, 1, 2)

 Alberto Monteiro

 __
 R-help@stat.math.ethz.ch 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.

 
 


-- 
Frank E Harrell Jr   Professor and Chair   School of Medicine
  Department of Biostatistics   Vanderbilt University

__
R-help@stat.math.ethz.ch 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.

Re: [R] Partition into quantiles

2006-10-05 Thread Alberto Monteiro 
Sorry, folks. Thanks for the help, but none of the suggestions 
worked quite as I wanted :-/

So I wrote the code. It seems to work:

gera_particao - function(x, n) {
  y - sort(x)
  icut - as.integer(seq(1, length(x)+1, length = n + 1))
  icut - icut[c(-(n+1))]
  ycut - y[icut]
  for (i in 1:length(x))
xpart[i] - sum(x[i] = ycut)
  return(xpart)
}

First, x is sorted to y. Then, I select the minima y
of each of the n segments. Then, an ugly and slow loop,
counts for each x how many ycut lie below them.

 x - runif(12)
 x
 [1] 0.2971455266 0.6112766485 0.5571073645 0.5886481798 0.7499023860
 [6] 0.1681732289 0.6319822536 0.0005354732 0.8055324992 0.8841625380
[11] 0.0726578285 0.6250309648
 gera_particao(x, 2)
 [1] 1 2 1 1 2 1 2 1 2 2 1 2
 gera_particao(x, 3)
 [1] 1 2 2 2 3 1 3 1 3 3 1 2
 gera_particao(x, 4)
 [1] 2 3 2 2 4 1 3 1 4 4 1 3
 gera_particao(x, 12)
 [1]  4  7  5  6 10  3  9  1 11 12  2  8

Alberto Monteiro

__
R-help@stat.math.ethz.ch 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.