Thanks a lot for the help, Ben Bolker and Chuck!
Chuck, it seems your version needs a little modification. Instead of this:
> xri <- matrix(rnorm(1)+1i*rnorm(1),nc=2)
> crossprod(xri-colMeans(xri))/(nrow(xri)-1)
it seems to me it should be this (maybe there is a more elegant
modification
Hans-Peter Suter wrote:
(emacs newb here)
After having made some changes in an \items paragraph of \arguments
the lines are no longer nicely wrapped. I was looking for a command to
reindent/rewrap/reformat the whole \items paragraph but couldn't find
anything.
The only way, I found, was to go t
Many thanks Peter and Berend.
I think I can make this work for my problem. Apologies for not giving an
example: I was a bit tired and frustrated when I posted to R-help and
only on later reflection realised that I didn't really follow the
posting guidelines.
David
Peter Ehlers wrote:
(Sorr
On Sat, 27 Mar 2010, Economics Guy wrote:
I am revising a program that I wrote when I was very new at R
(2007ish), and while I have been able to write very nice and fast code
for almost all of it, there is one issue that I cannot seem to do it
in less than 40 ugly and computationally expensive l
On 03/27/2010 03:23 AM, sdzhangping wrote:
Dear friends:
I'm interested to make a stacked plot of cumulative incidence.
that's, the cuminc model is fitted [fit=cuminc(time, relapse)] and cumulative
incidence is in place. I'd like to stack the cuminc plots (relapse of luekemia
and dea
On Sat, 27 Mar 2010, Gang Chen wrote:
Anybody knows what functions can be used to calculate
variance/covariance with complex numbers? var and cov don't seem to
work:
How about?
xri <- matrix(rnorm(1)+1i*rnorm(1),nc=2)
crossprod(xri-colMeans(xri))/(nrow(xri)-1)
HTH,
Chuck
a
Daniel Barton umontana.edu> writes:
>
> Hello All,
> I am looking for an R library/function that allows the specification
> of a custom link function in a linear mixed model.
You might want to try on the r-sig-mixed-mod...@r-project.org list.
I would probably call this a *G*LMM becaus
Gang Chen gmail.com> writes:
>
> Anybody knows what functions can be used to calculate
> variance/covariance with complex numbers? var and cov don't seem to
> work:
How about:
y <- complex(real=5:1,imag=2:6)
z <- complex(real=1:5,imag=6:10)
complex.var <- function(x) {
mx <- mean(x)
n <-
I am revising a program that I wrote when I was very new at R
(2007ish), and while I have been able to write very nice and fast code
for almost all of it, there is one issue that I cannot seem to do it
in less than 40 ugly and computationally expensive lines.
I have a data frame that contains one
hadley wickham wrote:
>
>> exp1^(a[case] * l * 10)
>>
>> would be better written out of the loop as
>>
>> b <- exp1^(a * l * 10)
>
> And even better as
>
> b <- exp(a * l * 10)
>
> Hadley
>
Aye, exp() functions tend to be heavily optimized compared to general
functions such as `^` even if
Hello everyone, I'm trying to build Levene's test. The below command is what
I used to do the test, I also included the error it prompts up and some data
example that I used when trying to build the test. Can someone please tell
me what did I do wrong? thanks in advance!
> res=lm(as.matrix(xx$B
On Mar 27, 2010, at 11:43 AM, ManInMoon wrote:
Hi,
I keep getting this error in console. but I have 30G of RAM:
Error: cannot allocate vector of size 154.3 Mb
Is there some way to tell it I have more memory available?
I am on Windows XP 64 bit
But you are probably using 32 bit R.
You co
Basically, R is telling you that the source code of the package you
are installing is troublesome.. It doesn't look like the codes is
"clean".. There are warnings.
Perhaps, you can try with a different version of the package?
-k
On Sat, Mar 27, 2010 at 12:27 PM, shruti wrote:
>
> Hi ,My name is
Hi ,My name is shruti,I'm new to R when i was checking my package i got a
error message saying Running Example in pkg-Ex.R failed.can any one help me
with this.I'm inserting command prompt reference for your reference.
Thank you, http://n4.nabble.com/file/n1693503/running_ex.jpg
--
View this mes
Hi,
I keep getting this error in console. but I have 30G of RAM:
Error: cannot allocate vector of size 154.3 Mb
Is there some way to tell it I have more memory available?
I am on Windows XP 64 bit
--
View this message in context:
http://n4.nabble.com/R-Cmdr-memory-tp1693483p1693483.html
Sent
See ?strwidth
On Sat, Mar 27, 2010 at 3:42 PM, Dennis Fisher wrote:
> Colleagues,
>
> I am trying to create a PDF document in which I use margin text with two
> different fonts. The resulting text might be:
> XyZZZ
> where X and Z are one font and Y is the other.
>
> My plan was to d
I have a matrix with 167 columns, each representing the y values of a
functional.
There are a few scattered NA's in each column.
I have been unable to create a useful fd object with any of the functions in
fda.
The resulting coefficients are all NA.
Is this a known limitation? Is there a workarou
On 23.03.2010 04:27, stephen sefick wrote:
I think you don't need to multiply... you need to figure out where
your NAs need to be and then index the vector and assign "NA" to it:
x[1:5]<- "NA"
... which would coerce x to be character while
x[1:5] <- NA
keeps the mode of x.
Uwe Ligges
On 03/27/2010 07:53 AM, dkStevens wrote:
>
> I'm searching for answers to four questions (I've been searching the net for
> hours...)
>
> In Windows XP, is it possible to call R functions from a c program? (I've
> found examples for Linux/Unix but not Windows)
>
> If so, is there a simple exampl
Colleagues,
I am trying to create a PDF document in which I use margin text with two
different fonts. The resulting text might be:
XyZZZ
where X and Z are one font and Y is the other.
My plan was to do this in the following manner:
mtext("X ZZZ", cex=2, adj=0.5, family=S
David,
On 27 March 2010 at 10:08, dkStevens wrote:
| Thanks for your prompt response. Apparently my problem is with my R or
| Windows setup. When I followed the advice in your return email, here's
| the result.
I will eat my hat. What you show I had too -- you need to define
the environment v
FAQ 7.31
Follow the link to what you should know about floating point numbers.
On Fri, Mar 26, 2010 at 5:05 PM, JustinNabble wrote:
>
> Can anyone explain this?
>
> I have a matrix with double components. It's taking up a lot of memory, so
> I
> want to multiply then turn it to integers. I'm pre
(emacs newb here)
After having made some changes in an \items paragraph of \arguments
the lines are no longer nicely wrapped. I was looking for a command to
reindent/rewrap/reformat the whole \items paragraph but couldn't find
anything.
The only way, I found, was to go to the end of the first lin
The script you sent seems to be too large for me to spend time debugging,
plus it seems that there are files being read that are not part of the
data. I would suggest that if you have a long running program that you put
messages (cat('reached part 1\n')) throughout the program so you can trace
wha
Thanks for your prompt response. Apparently my problem is with my R or
Windows setup. When I followed the advice in your return email, here's
the result. I've been an R user for a number of years and have
installed/uninstalled several versions, plus I've installed MinGW,
RTools, gcc/gfortran,
thank you! (I was on the wrong track, and thinking these would
be "levels".)
Oliver
> In this case where the is only one dimension, the table object is more
> like a named vector. The first "vector" in your terminology (but would
> be more accurately called "labels") can be accessed with:
>
On 27 March 2010 at 09:02, dkStevens wrote:
| This may simply expose my ignorance in this type of coding, but,
| unfortunately it's not that simple because I did using the RInside.h and
| received several screens of error messages from gcc telling me that it
| couldn't find the include file and th
> exp1^(a[case] * l * 10)
>
> would be better written out of the loop as
>
> b <- exp1^(a * l * 10)
And even better as
b <- exp(a * l * 10)
Hadley
--
Assistant Professor / Dobelman Family Junior Chair
Department of Statistics / Rice University
http://had.co.nz/
> # Set up the ratio variables
> system.time({
> temp <- cbind(data, do.call(cbind, lapply(names(data)[3:4], function(.x)
> {
> unlist(by(data, data$group, function(.y) .y[,.x] /
> max(.y[,.x])))
> })))
> colnames(temp)[5:6] <- paste(colnames(data)[3:4], 'ind.to.max',
On 27 March 2010 at 11:50, Khanh Nguyen wrote:
| What examples are you talking about. You only need to include
| ... More information is here
| http://dirk.eddelbuettel.com/code/rinside.html
Khanh is quite correct: RInside is self-contained. It also doesn't get much
simpler than the examples we s
Here is a comparison of the speed of the solutions so far plus one
based on cumsum. It seems that cumsum was the fastest and is 26x
faster than the slowest solution.
The speed may not be so important here and readability might be key in
which case a good compromise might be match which was still p
Anybody knows what functions can be used to calculate
variance/covariance with complex numbers? var and cov don't seem to
work:
> a
1
V1 0.00810014+0.00169366i
V2 0.00813054+0.00158251i
V3 0.00805489+0.00163295i
V4 0.00809141+0.00159533i
V5 0.00813976+0.00161850i
> var(a)
This may simply expose my ignorance in this type of coding, but,
unfortunately it's not that simple because I did using the RInside.h and
received several screens of error messages from gcc telling me that it
couldn't find the include file and the scores of additional include files
that rinside.h
try this:
y <- c(4,4,4,2,45,12,12)
match(y, unique(y))
I hope it helps.
Best,
Dimitris
On 3/27/2010 4:42 PM, sun wrote:
Dear all,
I want to replace an (unsorted) id variable in a large dataset by a running
number without changing the order of the cases.
E.g.,
y<- c(4,4,4,2,45,12,12)
sho
Hi Martin,
The same happened to me a while ago, I changed the mirror to another country
and it worked for me.
Hope it will for you too.
Best,
Tal
Contact
Details:---
Contact me: tal.gal...@gmail.com | 972-52-7275845
Read me: www
Try this:
as.numeric(factor(y, levels = unique(y)))
On Sat, Mar 27, 2010 at 12:42 PM, sun wrote:
> Dear all,
>
> I want to replace an (unsorted) id variable in a large dataset by a running
> number without changing the order of the cases.
>
> E.g.,
>
> y <- c(4,4,4,2,45,12,12)
>
> should be rep
The rle (run length encoding) function is ideal for
problems like this:
y <- c(4,4,4,2,45,12,12)
rr = rle(y)
rep(seq(along=rr$values),rr$lengths)
[1] 1 1 1 2 3 4 4
- Phil Spector
Statistical Computing Facility
What examples are you talking about. You only need to include
... More information is here
http://dirk.eddelbuettel.com/code/rinside.html
The other external thing you need is the Rcpp package, which you can
do with install.packages('Rcpp')
On Sat, Mar 27, 2010 at 11:40 AM, dkStevens wrote:
>
>
Hello,
I am fitting data using different methods e.g. Local Polynomial and Smoothing
splines. The data is generated out of a true function model with added normally
distributed noise.
I would like to know "how often the confidence band for all points
simultaneously contain all true values". I
On 03/26/2010 06:40 PM, Dimitri Liakhovitski wrote:
> My sincere apologies if it looked large. Let me try again with less code.
> It's hard to do less than that. In fact - there is nothing in this
> code but 1 formula and many loops, which is the problem I am not sure
> how to solve.
> I also tried
Dear all,
I want to replace an (unsorted) id variable in a large dataset by a running
number without changing the order of the cases.
E.g.,
y <- c(4,4,4,2,45,12,12)
should be replaced by something like
x <- c(1,1,1,2,3,4,4)
Sorry for this simple question & thank you very much for your help!
I have - but when I tried their simple example no luck - too many missing
include files to chase down. I'm looking for something more direct, I guess,
that I have a little control over.
--
View this message in context:
http://n4.nabble.com/Calling-R-from-c-in-Windows-XP-tp1693440p1693478.html
Se
I've looked at this a bit and it seems ok, if not a little convoluted. We're
trying to stay away from com objects, so I was hoping for something more
direct. I've seen some examples (e.g. RInside) but can't get them to work
-too many include files, etc. that I can't find.
--
View this message in
Thanks everyone for the helpful ideas. It appears that this will be more
difficult than I thought. I don't necessary have an inclination toward
p-values, but many journals certainly do. I would be willing to try to
calculate the confidence intervals around the estimates, but I haven't
gotten an
On Mar 27, 2010, at 10:29 AM, arindam fadikar wrote:
I have to obtain an ANOVA table with "suitable p-values" for an glm of
binomial model with probit link function. I can fit the model but
how can i
get the anova table with suitable p values?
The manner in which this request is posed sugg
If you want to call R from within VB.NET you might want to look at
the statconnDCOM server (available at rcom.univie.ac.at)
It wraps R into a (D)COM server and therefore allows any (D)COM client
to access R on windows. VB.NET is a (D)COM client.
On 3/27/2010 3:53 PM, dkStevens wrote:
>
> I'm se
On Mar 26, 2010, at 11:08 AM, Filipe Cadete wrote:
Dear all,
I am trying represent a matrix of discrete values. At the moment I
am using levelplot from the lattice package, but it seems to only
work with numerical values. Is there an option in levelplot that
will allow me to assign a col
This was *very* useful for me when I dealt with a 1.5Gb text file
http://www.csc.fi/sivut/atcsc/arkisto/atcsc3_2007/ohjelmistot_html/R_and_large_data/
On Sat, Mar 27, 2010 at 5:19 AM, n.via...@libero.it wrote:
> Hi I have a question,
> as im not able to import a csv file which contains a big da
Have you looked at RInside ?
-k
On Sat, Mar 27, 2010 at 10:53 AM, dkStevens wrote:
>
> I'm searching for answers to four questions (I've been searching the net for
> hours...)
>
> In Windows XP, is it possible to call R functions from a c program? (I've
> found examples for Linux/Unix but not Wi
I'm searching for answers to four questions (I've been searching the net for
hours...)
In Windows XP, is it possible to call R functions from a c program? (I've
found examples for Linux/Unix but not Windows)
If so, is there a simple example to get started using gcc with R-2.10.0?
If so, is it p
Hello guys,
I'm trying to do a pairs trading cointegration analysis on two stocks (AXAP
and AXANY), but I get an error that I don't understand...
Here's my code:
setwd("S:/Users/Alexis/Desktop/Essai") #chemin du dossier contenant les
données
donnees <- read.csv("Data_R.csv", head=T, sep=";",
Peter Ehlers wrote:
>
> I think that David might have meant that the column order of the
> numbers in lookfor is unimportant. In that case, a simple fix would
> be either to check both lookfor and rev(lookfor) (since the
> matrix is nX2) or to sort before testing:
>
> vtest <- function(x, loo
On Mar 26, 2010, at 12:37 PM, Oliver Kullmann wrote:
Hello,
let me show you the following part of a session:
table(E$singles)
0 1 2 3 4 5 6 7 8
14 15
461752 5487 93224379658 1099 4053 2
1868 1
21
I have to obtain an ANOVA table with "suitable p-values" for an glm of
binomial model with probit link function. I can fit the model but how can i
get the anova table with suitable p values?
Ref: example in help(esoph)
-arindam fadikar
[[alternative HTML version deleted]]
__
On Mar 27, 2010, at 6:53 AM, Dennis Murphy wrote:
Hi:
Does this do what you want?
# Create some fake data...
df <- data.frame(id = factor(rep(c('cell1', 'cell2'), each = 10)),
cond = factor(rep(rep(c('A', 'B'), each = 5), 2)),
time = round(rnorm(20, 350, 10)
(Sorry, I think that I just hit a wrong button and managed
to send a non-reply.)
I think that David might have meant that the column order of the
numbers in lookfor is unimportant. In that case, a simple fix would
be either to check both lookfor and rev(lookfor) (since the
matrix is nX2) or to so
On 2010-03-27 2:46, Berend Hasselman wrote:
David Scott-6 wrote:
I am sure someone can come up with a clever way of doing what I want---I
don't seem to be able to.
I want to check if a pair of numbers occurs as one of the rows of an n
by 2 matrix. If I was only checking whether a single nu
On Mar 27, 2010, at 6:45 AM, Joshua Wiley wrote:
It is a bit of a side note really, but a convenient way to provide
data (particularly when it is complex) is via dput(). Not only is
this easier to read in, it preserves classes and other handy info.
For instance, once I had played around to get
Perhaps slightly off topic but there is a faster alternative to combn() called
combnPrim() in the gRbase package:
> library(gRbase)
> system.time({for (ii in 1:1) combn(1:6,3)})
user system elapsed
4.020.004.02
> system.time({for (ii in 1:1) combnPrim(1:6,3)})
user sy
Try using read.csv.sql in sqldfSee example 13 on the sqldf home page:
http://code.google.com/p/sqldf/#Example_13._read.csv.sql_and_read.csv2.sql
Also read ?read.csv.sql
On Sat, Mar 27, 2010 at 5:19 AM, n.via...@libero.it wrote:
> Hi I have a question,
> as im not able to import a csv file whi
A little more information would help, such as the number of columns? I
imagine it must
be large, because 100,000 rows isn't overwhelming. Second, does the
read.csv() fail,
or does it work but only after a long time? And third, how much RAM do you
have
available?
R Core provides some guidelines
On Mar 27, 2010, at 6:35 AM, arindam fadikar wrote:
I have a vector with entries 0 and 1. I want the positions for
which the
entries are 1.
?which
- arindam fadikar
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing
OK, can't help you then sorry. Sometimes folk are confused between install
and attach when they're complete beginners so it's worth checking. You're
obviously not.
andydol...@gmail.com
On 25 March 2010 10:40, Martin Valere wrote:
> Dear Andrew,
>
> thanks for our interesrt.
>
> yes I mean f
Dear all, thank you so much for your advice, and special thanks to
you, Jim, for digging into my code (which was too long).
I'll dig into yours now - it definitely looks very fast - and it's a
lot of great learning for me. Because you can see - I am just a
rudimentary programmer.
Thank you very-ver
Hello all,
I'd like some advise on this. When I read my files, I pass the argument,
skip=6, to skip 6 lines of header information. After performing the
desired calculations, I have the output. Now I want to copy the 6 lines
of skipped information to the output.
What I've been doing so far is
Dear all, is there any package/function available which simulates a
co-integrating VAR model once the model parameters are input over some
arbitrary horizon? Please let me know anyone aware of that.
Thanks
--
View this message in context:
http://n4.nabble.com/Simulation-of-VAR-tp1693295p1693295
Dear addresses, I need perform a batch of 10 000 simulations for each of
4 options considered. (The idea is to obtain the parameter estimates in
a heteroskedastic linear regression model - with additive or mixed
heteroskedasticity - via the Kenward-Roger small-sample adjusted
covariance matrix of d
Hi:
Does this do what you want?
# Create some fake data...
df <- data.frame(id = factor(rep(c('cell1', 'cell2'), each = 10)),
cond = factor(rep(rep(c('A', 'B'), each = 5), 2)),
time = round(rnorm(20, 350, 10), 2))
# Create a function to subtract each element
It is a bit of a side note really, but a convenient way to provide
data (particularly when it is complex) is via dput(). Not only is
this easier to read in, it preserves classes and other handy info.
For instance, once I had played around to get "Cook" and "Islands"
into one column (since there wa
I have a vector with entries 0 and 1. I want the positions for which the
entries are 1.
- arindam fadikar
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the
Aha! I see now! thanks guys! really helpful!
--
View this message in context:
http://n4.nabble.com/producing-a-QQ-plot-tp1693228p1693259.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.org mailing list
https://stat.et
Am 27.03.2010 10:19, schrieb n.via...@libero.it:
> What im facing when i try to import the file is that R generates more than
> 100.000 records and is very slow...
> thanks a lot!!!
>
>
Maybe your physical memory is too limited. R uses this and if your data
are to large Linux and windows start
Am 27.03.2010 10:45, schrieb Philip Wong:
>
>> mah=mahalanobis(data,apply(data,2,mean),var(data))
>>
>
>> mah=mahalanobis(data,apply(data,2,mean),var(no_fisher))
>>
> qqplot(qchisq(ppoints(data),ncol(data),data)
>
As Joshua already pointed out: you are trying mathematical functions
Hello, this is the first 10 data of the population.
country village group av_expenP2ary_edno_fisher B_Leth
B_LutjanWt_Leth
Wt_Lutjan
Cook IslandsAitutakiD 5239.127472 0.7
666.9998558 3.286283997
1.971519001 520.6454552
Dear Philip,
It is difficult to tell what is wrong without a reproducible example.
It would be very helpful if you would provide sample data. That said,
the most obvious issue from what you have provided is that some of
your data is character. mean() and var() will not work with character
data.
I do not know what is the limit for R. But on your problem you may try this:
- Install MySQL server (download somewhere on www.mysql.com)
- From inside MySQL you may import that CSV into a MySQL table
- Then using RMySQL or ROBDC you will choose the Fields to use and
import them to R.
Good luck
Ca
Hello everyone I'm a beginner in Stats and R, I'm using R 2.10.1. I need to
create a multivariate qq plot, there is 8 variable group with each has 55
number of input. An example of what I did so far, just to get my point out:
> data=read.csv(file.choose(),header=T)
> data
country
In December, the packages "miscTools" and "micEconAids" were separated
from the "micEcon" package. Now, two further packages have been
separated from the micEcon package: "micEconSNQP" and "micEconCES".
The "micEconSNQP" package (version 0.6-2) provides tools for
production analysis with the Symme
You seem to be in Circle 1 of 'The R Inferno'.
Your technique does work, just not the
way that you expect. Try doing:
range( (mat * 100) %% 1)
The 'zapsmall' function might be of interest
as well.
On 26/03/2010 21:05, JustinNabble wrote:
Can anyone explain this?
I have a matrix with double
Your question is ambiguous -- at least
to me. The posting guide:
http://www.r-project.org/posting-guide.html
suggests that examples can be helpful to
explain what you want.
From the main statement I think the answer
might be:
mymatrix[seq(1, nrow(mymatrix), by=8), ]
From the 'i.e.' clause I'm
Hi I have a question,
as im not able to import a csv file which contains a big dataset(100.000
records) someone knows how many records R can handle without giving problems?
What im facing when i try to import the file is that R generates more than
100.000 records and is very slow...
thanks a lot!
Hello everyone,
I have a matrix with 8000 rows. If I want to select every 8 rows, (i.e.
row1, row2, ..., row8), what should I do?
Appriciate for any hints!
Thanks a lot!
Leo
--
View this message in context:
http://n4.nabble.com/select-n-rows-tp1693136p1693136.html
Sent from the R help mailing li
An aside to the main question:
I don't think that
i+1:3
is doing what you think it is.
On 26/03/2010 23:01, casperyc wrote:
Hi,
I am tring to write a loop to compute this,
==
x1=c(
rep(-1,4),
rep(1,4)
)
x2=c(
rep(c(-1,-1,1,1),2)
Here's my first stab. It removes some of the typical redundencies in your
code (loops, building data frames by adding one column at a time) and
instead does what is probably more canonical R style (although I'm willing
to be corrected, as I suspect my code is a little suspect at times).
For this
Can anyone explain this?
I have a matrix with double components. It's taking up a lot of memory, so I
want to multiply then turn it to integers. I'm pretty certain that there are
only 2 decimal places, but I wanted to check by using modulo. E.g.
mat = matrix(11:50/100, ncol=4,nrow=10) #Matrix wi
I have a data frame containing the results of time measurements taken from
several cells. Each cell was measured in conditions A and B, and there are
an arbitrary number of measurements in each condition. I am trying to
calculate the difference of each measurement from the mean of a given cell
in
I am trying to load a package called Rmark, but when I run
library(Rmark)
I get the following:
> library(RMark)
Error in !character.only : invalid argument type
Error in library(RMark) : .First.lib failed for 'RMark'
When I try to load Rmark from the packages menu, I get:
> local({pkg <- sele
Your request might find better answers on the R-SIG-mixed-models
list ...
Anyway, some quick thoughts :
Le vendredi 26 mars 2010 à 15:20 -0800, dadrivr a écrit :
> By the way, my concern with lmer and glmer is that they don't produce
> p-values,
The argumentation of D. Bates is convincing ... A
David Scott-6 wrote:
>
> I am sure someone can come up with a clever way of doing what I want---I
> don't seem to be able to.
>
> I want to check if a pair of numbers occurs as one of the rows of an n
> by 2 matrix. If I was only checking whether a single number was in a
> vector of numbers
Le 25/03/2010 20:28, Laurent Rhelp a écrit :
Dear R-List,
I am working with binary data that I want to store in a PostgreSQL
DataBase. I decided to use a TXT field. I read my binary file with
readBin function, I succeed in my data storage in the database but I
have some trouble to extract
90 matches
Mail list logo
