if the files are supposed to be "1r.xlsx", "2r.xlsx" (etc) then you need to
ensure there's a "/" before it.
It's better to use `file.path()` to, well, build file paths since it will
help account for differences between directory separators on the various
operating systems out there.
On Wed, Aug
Hi,
Can someone please tell me the maximum number of independent variables
allowed in R for non linear regression.
I have 50 independent variables and want to calculate non linear models to
the power of 9 but R is unable to process it beyond to the power of 3 which
means its taking maximum 150
Also, the recommended way to build file paths is to use file.path(), i.e.
file.path("C:", "temp", filename)
rather than
paste0("C:/temp/", filename)
BTW, R provides tempdir() that gives you the temporary directory that
R prefers to use on your OS. So, you might want to consider using:
Inline.
-- Bert
Bert Gunter
"The trouble with having an open mind is that people keep coming along
and sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )
On Wed, Aug 31, 2016 at 10:03 AM, Anderson Eduardo
wrote:
> Hello
>
> I
Hi Kai,
Perhaps something like this:
kmdf<-data.frame(group=rep(c("exp","cont"),each=50),
time=factor(rep(1:5,20)),
condition=rep(rep(c("hot","cold"),each=25),2),
value=sample(100:200,100))
for(timeindx in levels(kmdf$time)) {
for(condindx in levels(kmdf$condition)) {
That
tmp1 - 30*60
can also be done as
tmp1 - as.difftime(30, units="mins")
so you don't have to remember that the internal representation of POSIXct
is seconds since the start of 1970. You can choose from the following
equivalent expressions.
tmp1 - as.difftime(0.5, units="hours")
tmp1 -
Try following this example:
mydf <- data.frame(t1=c('201112312230', '201112312330'))
tmp1 <- as.POSIXct(mydf$t1, format='%Y%m%d%H%M')
tmp2 <- tmp1 - 30*60
mydf$t2 <- format(tmp2, '%Y%m%d%H%M')
It can be made into a single line, but I used intermediate variables tmp1
and tmp2 so that it would be
Please show us your code and error messages. I suspect that what you
mean by "nonlinear models" may not be what the rest of us mean.
And please post in plain text, not HTML, as the latter tends to get
mangled on this plai text list.
Cheers,
Bert
Bert Gunter
"The trouble with having an open mind
Hi all,
I am having trouble wrapping my head around a probably simple issue:
After using the reshape package, I have a melted dataframe with the columns
group (factor), time (int), condition (factor), value(int).
These are experimental data. The data were obtained from different
treatment
Building on Don's example here is something that looks a lot like what I do
every day:
Sys.setenv(TZ="UTC")
mydf <- data.frame(t1=c('2011-12-31-22-30', '2011-12-31-23-30'))
library(lubridate)
mydf$timestamp = lubridate::ymd_hm(mydf$t1)
mydf$t2 = mydf$timestamp - period(minute=30)
On Wed, Aug
Kai:
1. I think that this is a very bad idea, statistically, if I
understand you correctly. Generally, your model should incorporate all
groups, time points, and conditions together, not individually.
2. But plotting results in "small multiples" -- aka "trellis plots"
may be useful. This is done
Hello Everyone,
I am trying a shift the time series in a dataframe (df) by 30 minutes . My
current format looks something like this :
*df$$Time 1*
*201112312230*
*201112312300*
*201112312330*
*I am trying to add an additional column of time (df$Time 2) next to Time
1 by lagging it by –
Hello
I have started to work with GLM and I am facing the following problem:
If I take:
y = c(0, 0, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0)
x = 1:18
model = y ~x + I(x^2)
GLM = glm(model, family=binamial(link = logit))
And use the parameters returned by GLM to contruct an equation for
Hi R users,
I have created four figures using ggplot2, but I am having trouble to add
"r2=XXX, p=XX" value on the upper left in each figure and also unit of X
axis of each figure are different. I was also trying to write following :
1. "rainfall (mm/year") on X axix for fig A.
2. "temp (degree
Greetings. A subset of a problem that the group I work with turns out to be
an optimization problem, in the sense of linear programming.
We've looked at several approaches to this but haven't found one that seems to
be the right fit. I'm looking for some guidance in finding an R package that
Thank you Mark & Dunlap,
Will make changes to the variable as suggested. Thank you for your time &
assistance.
On Wed, Aug 31, 2016 at 9:16 PM, Mark Sharp wrote:
> Shivi,
>
> Looking at the help from ?WOE, ?WOETable, and ?IV, your Y vector in all
> cases is to be
These are the packages i am using:
library(woe) #WEIGHT OF EVIDENCE
library(InformationValue) #INFORMATION VALUE
The syntax used is :
WOE(X=SFDC1$log_caseage, Y=SFDC1$survey)
WOETable(X=SFDC1$case_age, Y=SFDC1$survey)
IV(X=SFDC1$case_age, Y=SFDC1$survey)
On Wed, Aug 31, 2016 at 12:54 AM, Mark
Hi
Thanks for code.
see in line
> -Original Message-
> From: R-help [mailto:r-help-boun...@r-project.org] On Behalf Of li li
> Sent: Tuesday, August 30, 2016 5:07 PM
> To: r-help
> Subject: [R] plot.drm in "drc" package
>
> Hi all,
> I am trying to use the drc
Thanks,
The 'droplevels' statement works.
Best regards,
James Henson
On Tue, Aug 30, 2016 at 5:34 PM, William Dunlap wrote:
> yuen does not work when there unused levels in the factors given to it.
>
>> yuen(GoalsGame ~ League, tr=0.2, data = SpainGer)
> Call:
> yuen(formula
If it doesn't do ANYTHING, you may have failed to save the file.
Unless that file contains a function, in which case it isn't supposed
to do anything except load the function into your global environment.
But it should have thrown an error in that case, as Duncan said.
On Wed, Aug 31, 2016 at
On 31/08/2016 11:05 AM, Doug Edmunds wrote:
I am trying to understand why "source" does not process
all the code in this R file.
1. I copied maCross.R from the quantstrat/demo directory
into my project area.
QuantStrat is available at
https://r-forge.r-project.org/R/?group_id=316
> On Aug 31, 2016, at 8:05 AM, Doug Edmunds wrote:
>
> I am trying to understand why "source" does not process
> all the code in this R file.
>
> 1. I copied maCross.R from the quantstrat/demo directory
> into my project area.
>
> QuantStrat is available at
>
1. File is (was) saved.
2. The added code is
t(tradeStats("macross"))
with 2 )'s.
I'd appreciate if someone with QuantStrat installed, to try this
and see if they get a different result. My R and RStudio and
QuantStrat libraries are all current.
I get the chart and this much output.
>
I have quantstrat installed and it works fine for me. If you're
asking why the output of t(tradeStats('macross')) isn't being printed,
that's because of what's described in the first paragraph in the
*Details* section of help("source"):
Note that running code via ‘source’ differs in a few
Thank you. That explains it (auto-printing is not done).
On 8/31/2016 8:35 AM, Joshua Ulrich wrote:
I have quantstrat installed and it works fine for me. If you're
asking why the output of t(tradeStats('macross')) isn't being printed,
that's because of what's described in the first paragraph
Hi,
I'm trying to reshape and output 8 simple tables into excel files. This is
the code I'm using
for (i in 1:8) {
count <- table(mydata$ctry, mydata[,paste0("q0",i,"r")])
dat <- as.data.frame(q01count)
wide <- reshape(dat,
timevar="Var2",
I see the printout (not an "error") that you describe on the 2nd example
you gave:
> t2 <- WOETable(X=SFDC1$case_age, Y=SFDC1$survey)
> print(t2)
[1] GOODS BADS TOTAL PCT_G PCT_B WOE IV
<0 rows> (or 0-length row.names)
The result of WOETable is perfectly legal - it is a data.frame with no
I am trying to understand why "source" does not process
all the code in this R file.
1. I copied maCross.R from the quantstrat/demo directory
into my project area.
QuantStrat is available at
https://r-forge.r-project.org/R/?group_id=316
install.packages("quantstrat",
On Wed, Aug 31, 2016 at 10:05 AM, Doug Edmunds wrote:
> I am trying to understand why "source" does not process
> all the code in this R file.
>
> 1. I copied maCross.R from the quantstrat/demo directory
> into my project area.
>
> QuantStrat is available at
>
On 31.08.2016 17:50, Leslie Rutkowski wrote:
Hi,
I'm trying to reshape and output 8 simple tables into excel files. This is
the code I'm using
for (i in 1:8) {
count <- table(mydata$ctry, mydata[,paste0("q0",i,"r")])
dat <- as.data.frame(q01count)
wide <- reshape(dat,
Shivi,
Looking at the help from ?WOE, ?WOETable, and ?IV, your Y vector in all cases
is to be categorical and it is numeric.
Mark
R. Mark Sharp, Ph.D.
Director of Primate Records Database
Southwest National Primate Research Center
Texas Biomedical Research Institute
P.O. Box 760549
San
Estimados
Microsoft R Open 3.3.1 me está dando problemas, por ejemplo rbind.
Los resultados son extraños, por ejemplo muchas columnas cuándo debería ser una
sola sonde tomo solamente la primer columna de varios data.frames, como un
arreglo de n x n donde los n son números “grandes”, cuándo
Hola,
Si la fecha tiene formato "d/m/y", entonces la función que hay que usar de
lubridate es "dmy()". No debiera de darte mayores problemas. Es lo
suficientemente versátil para diferenciar formatos de fecha de lo más
variados.
En estos caso de bloqueo, para que podamos ayudarte de una forma más
33 matches
Mail list logo