Displaying 20 results from an estimated 54 matches for "nstart".
Did you mean:
start
2009 Apr 26
2
eager to learn how to use "sapply", "lapply", ...
...really like to shake my C programming style off.
I am staring at my R script and thinking "how can I improve it ?"
For instance, I have a lot of loops similar to the following one and wonder whether I can replace them with a proper call to a high level R function that does the same:
Nstart <- Nfour/(2^Lev) + 1
Nfinish <- Nstart -1 + Nfour/(2^Lev)
LengLev <- Nfinish - Nstart + 1
NW <- floor(LengLev*N/Nfour)
if(NW > 0){
for(j in Nstart:(Nstart + NW -1)){
Dw <- abs(Y[j])
Rnorm <- Rnorm + Dw^2
}
}
Than...
2005 Dec 02
1
k-means / role of 'nstart'
Hello,
the k-means {stats} help and the Hartigan&Won paper say nothing about
the way random sets works (parameter nstart). I would expect to get
the different results for each random initial set but I always obtain
only one result: how is it selected?
Charles Raux
2013 Mar 13
1
Empty cluster / segfault using vanilla kmeans with version 2.15.2
Hello,
here is a working reproducible example which crashes R using kmeans or
gives empty clusters using the nstart option with R 15.2.
library(cluster)
kmeans(ruspini,4)
kmeans(ruspini,4,nstart=2)
kmeans(ruspini,4,nstart=4)
kmeans(ruspini,4,nstart=10)
?kmeans
either we got empty always clusters and or, after some further commands
an segfault.
regards,
Detlef Groth
------------
[R] Empty cluster / segfau...
2005 Sep 20
2
script.aculo.us: pause before effect.appear
...the images randomly appear at different times; e.g. the 3rd image might
start appearing 2 seconds after load, the 6th image immediately after load,
the first image 1 second after load, etc...
How can I achieve this affect?
--- example HTML and Javascript ---
function img_appear() {
var ndur=2, nstart=1, nend=22;
for(var loop = nstart; loop < nend; loop++)
{
var nid=''a''+loop;
new Effect.Appear(nid, {transition: Effect.Transitions.linear, duration:
ndur});
}
}
<body onload="img_appear()">
<div class="images">
<img src="1.jpg" al...
2012 Jan 14
1
Error: unexpected '<' in "<" when modifying existing functions
Hi.
I am trying to modify kmeans function.
It seems that is failing something obvious with the workspace.
I am a newbie and here is my code:
myk = function (x, centers, iter.max = 10, nstart = 1, algorithm =
c("Hartigan-Wong",
+ "Lloyd", "Forgy", "MacQueen"))
+ {
+ do_one <- function(nmeth) {
+ Z <- switch(nmeth, {
+ Z <- .Fortran(R_kmns, as.double(x), as.integer(m),
+ as.integer(ncol(x)), cent...
2004 Sep 06
1
A naive lsoda question....
...quot;rx"]; ry <- p["ry"]
Kx <- p["Kx"]; Ky <- p["Ky"]
phix <- p["phix"]; phiy <- p["phiy"]
dx.dt <- rx*x*(1 - x/Kx) - phix*x*y
dy.dt <- ry*y*(1 - y/Ky) - phiy*x*y
list(c(dx.dt, dy.dt))
}
# running lsoda
nstart <- c(x=0.5, y=0.5)
parms <- c(rx=1, ry=1, Kx=1, Ky=1, phix=1.2, phiy=0.8)
tmax <- 100
times <- seq(0,tmax)
require(odesolve)
out <- as.data.frame(lsoda(nstart, times, lotvol, parms))
Thanks,
Manojit
2000 Apr 11
0
aggregate.ts (PR#514)
...Series:
Start = 2
End = 8
Frequency = 0.5
[1] 2 4 6 8
S> x <- rts(1:10)
S> aggregate(x, nf=0.5, fun = min)
[1] 1 3 5 7 9
start deltat frequency
1 2 0.5
I have edited the aggregate.ts function to reproduce the S-PLUS
behaviour, which I find more intuitive:
old:
#nstart <- ceiling(tsp(x)[1] * nfrequency)/nfrequency
#x <- as.matrix(window(x, start = nstart))
new:
nstart <- tsp(x)[1]
# Can't use nstart <- start(x) as this causes problems if
# you get a vector of length 2.
x <- as.matrix(x)
I have tried this on a range of e...
2007 Jul 09
1
factanal frustration!
Hi.
It seems that nearly every time I try to use factanal I get the following
response:
>faa2db1<-factanal(mretdb1,factors=2,method="mle",control=list(nstart=25))
Error in factanal(mretdb1, factors = 2, method = "mle", control =
list(nstart = 25)) :
unable to optimize from these starting value(s)
>
In the case cited above, mretdb1 is synthetic data created from two factors,
that is, mretdb1 has dimensions 3050*1000, and each of t...
2014 Oct 31
0
[PATCH 1/3] fish: rl.{c, h} - escaping functions for readline
...+1, p+1+m, strlen (p+1+m) + 1);
+ }
+ }
+
+ return start;
+}
+
+// backslash scape
+char *
+bs_escape_filename (char *p)
+{
+ char *start = p;
+ // four times original length - if all chars are unprintable
+ // new string would be \xXY\xWZ
+ char *n = calloc(strlen(p) * 4 + 1, 1);
+ char *nstart = n;
+ if (strlen(p) == 0) {
+ n[0] = '\0';
+ return n;
+ }
+
+ for (; *p; p++, n++) {
+ int m = 1;
+
+ switch (*p) {
+ case '\\': break;
+ case '\a': *(n++) = '\\'; *n = 'a'; break;
+ case '\b': *(n++) = '\\'...
2014 Oct 31
6
[PATCH 0/3] WIP readline escaping functions
From: Maros Zatko <hacxman@gmail.com>
Auxiliary functions for readline to support space character escaping
in filenames in future.
Escaping function is taken from fish.c (used to be parse_quoted_string)
plus its un-escaping counterpart. There are a few tests for both.
Maros Zatko (3):
fish: rl.{c,h} - escaping functions for readline
fish: basic tests for readline escaping
autotools:
2009 Jun 10
1
Weird behavior in receive_data function
...file 1 and file 2 have the same name, just binary
difference):
Step 1: backup File 1
Step 2: backup Fil 2
--
Daniel Li
File 1:
This is the first time backup file.
> count = 1;
> nSize = 1;
> nBlock = 256;
> nInterval = 4;
> nAdjust = 256;
>
> printf("\nstart to build origin files!\n");
> ch = 0;
> for(l = 0; l < count; l++)
> {
> memset(buffer,0, 256);
> sprintf(buffer,"media-test-3MB-file/origin/test/test%02d.dat",l);
> printf("writting %s \n",buffer);
> fd = open(buffer, O_RDWR|O_CREA...
2013 Feb 03
1
Empty cluster / segfault using vanilla kmeans with version 2.15.2
...a I'm clustering is constituted by the rows of a 320 x 6 matrix
containing integers ranging from 1 to 7, no missing data.
I applied kmeans() to this matrix, literally, 256 x 10⁶ times using R
version 2.13.2 or 2.14.1, without never experiencing the slightest problem.
My usual setup is with k=5, nstart=256, iter.max=50.
Upgrading to R 2.15.2, I experienced either a warning message ('Empty
cluster. Choose a better set of initial centers') or a catastrophic
segfault. The only way I can get a solution whatsoever is putting nstart to
its default value, i.e. 1. However, just repeating the clu...
2013 Aug 26
2
Perl interface isn't working in 1.2.x
On 08/25/2013 05:02 PM, Olly Betts wrote:
> So the simple fix is
> probably just to install the perl-Search-Xapian RPM instead.
Thanks, the Centos 6 repos don't have that rpm and the
http://xapian.org/download page seems to only cover the XS bindings, if
I am reading this correctly:
But I was able to remove the rpm packages and compile and install the
core and swig from source.
2013 Jun 24
1
K-means results understanding!!!
...n R. I am applying
kmeans-algorithms to my big data file, and it is producing the results of
the clusters.
Q1) Does anybody knows how to find out in which cluster (I have fixed
numberofclusters = 5 ) which data have been used?
COMMAND
(kmeans.results <- kmeans(mydata,centers =5, iter.max= 1000, nstart =10000))
Q2) When I call kmeans.results I have the following output:
K-means clustering with 5 clusters of sizes 17, 1, 6, 4, 32
Cluster means:
[,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12]
1 0 0 0 0 0 0 0 0 0 0 0.0000000 0.000823529...
2005 Jun 14
1
KMEANS output...
Using R 2.1.0 on Windows
2 questions:
1. Is there a way to parse the output from kmeans within R?
2. If the answer to 1. is convoluted or impossible, how do you save the
output from kmeans in a plain text file for further processing outside R?
Example:
> ktx<-kmeans(x,12, nstart = 200)
I would like to parse ktx within R to extract cluster sizes, sum-of-squares
values, etc., OR save ktx in a plain text file in Windows to post-process it
with a parser I would have to write.
Thanks!
Omer
Cell: (914) 671-7447
2012 Feb 02
0
bigkmeans not parallel
...s to run the loop
system.time(x <- foreach(j=1:times ) %dopar% check(j))
user system elapsed
----- ------ 4
system.time(x <- foreach(j=1:times ) %do% check(j))
user system elapsed
----- ------- 16
But when I run my data in bigkmeans
>ans <- bigkmeans(data,200,nstart=5,iter.max=20)
I see only one R process in system monitor, and only one CPU usage is high.
I guess it's not really parallel.
I also tried DoSNOW, though it's used for multi clusters.
>cl <- makeCluster(8,type="SOCK")
>registerDoSNOW(cl)
>ans <- bigkmeans(data,200...
2012 Feb 20
1
bigmemory not really parallel
Hi, all,
I have a really big matrix that I want to run k-means on.
I tried:
>data <-
read.big.memory('mydata.csv',type='double',backingfile='mydata.bin',descriptorfile='mydata.desc')
I'm using doMC to register multicore.
>library(doMC)
>registerDoMC(cores=8)
>ans<-bigkmeans(data,k)
In system monitor, it seems only one thread running R. Is
2004 Jul 21
0
loglin( tab, margin, start = bad.start ) kills R (PR#7123)
..."This should not happen"), stop("This
should not happen"), :
Incorrect specification of 'table' or 'start'
appl/loglin.c assumes that start (aka 'fit') has enough memory allocated.
Possible fix in stats/R/loglin.R :
ntab <- length(table)
+ nstart <- length( start )
+ if (nstart != ntab ) stop(" start and table must be same length " )
> version
_
platform sparc-unknown-linux-gnu
arch sparc
os linux-gnu
system sparc, linux-gnu
status...
2014 Jun 30
0
convergence warning in betamix()
Hi, I am running some rather complex mixtures of beta regressions using the
betamix() command from the betareg package (V. 3.0-4). If I am doing
exploratory regressions with only one random starting value (nstart=1) I
obtain results which converge after about 100 iterations. However, if I run
regressions with nstart=100 random starting values I obtain solutions
amended with a warning that no convergence resulted after 200 iterations. I
conclude that 1) the initial regression converges to a local optimum, 2)...
2013 Aug 21
2
Perl interface isn't working in 1.2.x
...;get_doccount();
# $qp->set_stemmer(new Search::Xapian::Stem("english"));
# $qp->set_stemming_strategy(STEM_SOME);
# $qp->set_default_op($defaultop);
my $par = $qp->parse_query($query);
my $enq = $db->enquire( $par );
my @matches = $enq->matches($nstart,$nrecords);
my $mset = $enq->get_mset($nstart,$nrecords);
my $est = $mset->get_matches_estimated();
my $totTime=0;
foreach my $match ( @matches ) {
my $doc = $match->get_document();
my $id = $match->get_docid();
my $eterm = $enq->get_mat...