[R] using edit to extract codes from vignette failed
Dear expeRts, When i using the following code, i get a error as follows: edit(file=vignette(grobs,package = grid)) Error in edit.vignette(file = vignette(grobs, package = grid)) : argument name is missing, with no default I investigated edit function, but still can't get codes from a vignette, May you help me? -- PO SU mail: desolato...@163.com Majored in Statistics from SJTU __ R-help@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.
Re: [R] Defining vectors with per-determined correlations
On 04 Sep 2014, at 19:32 , Ista Zahn istaz...@gmail.com wrote:
See ?mvrnorm in the MASS package.
... and in particular, notice its empirical=TRUE argument.
Also, notice that the 3rd correlation (corr(x, z)=r3, say) can't be set
arbitrarily: if r1=r2=0.99, r3 cannot be zero.
Best,
Ista
On Thu, Sep 4, 2014 at 12:04 PM, John Sorkin jsor...@grecc.umaryland.edu
wrote:
I need to define three vectors x, y, z (each of length 100) such that the
pair-wise correlations of the vectors have per-defined values r1 and r2.
More specifically I need to define x, y, and z so that:
corr(x,y) = r1
corr(y,z) = r2
Is there any easy way to accomplish this with R?
Thank you,
John
John David Sorkin M.D., Ph.D.
Professor of Medicine
Chief, Biostatistics and Informatics
University of Maryland School of Medicine Division of Gerontology and
Geriatric Medicine
Baltimore VA Medical Center
10 North Greene Street
GRECC (BT/18/GR)
Baltimore, MD 21201-1524
(Phone) 410-605-7119
(Fax) 410-605-7913 (Please call phone number above prior to faxing)
Confidentiality Statement:
This email message, including any attachments, is for ...{{dropped:18}}
__
R-help@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.
--
Peter Dalgaard, Professor,
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: pd@cbs.dk Priv: pda...@gmail.com
__
R-help@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.
Re: [R] using edit to extract codes from vignette failed
On 07.09.2014 11:06, PO SU wrote: Dear expeRts, When i using the following code, i get a error as follows: edit(file=vignette(grobs,package = grid)) I guess you want to edit(file = vignette(grobs, package = grid)[[file]]) ? Best, Uwe Ligges Error in edit.vignette(file = vignette(grobs, package = grid)) : argument name is missing, with no default I investigated edit function, but still can't get codes from a vignette, May you help me? -- PO SU mail: desolato...@163.com Majored in Statistics from SJTU __ R-help@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. __ R-help@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.
[R] Question about searchTwitter{twitteR}
Hello,
The function searchTwitter() with the arguments supplied as below would
give me a different number of results on different days I run this code.
Maybe it is my lack of understanding about what the date arguments are
supposed to do in this function, but I would think I should be getting the
same tweets?
tweets - searchTwitter('my text search',
n = 1000,
since = '2013-09-01',
until = '2014-08-31')
Thanks,
Axel.
[[alternative HTML version deleted]]
__
R-help@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.
[R] Solving equations
Hi, I code R to parse data but not for solving equations. So this is my first such problem. It is a programming puzzle. I have these two equations. 1)4x - 3w = 0 2)8x - 7w =0 I know the value of x and w for equation 1). x = 3 and w = 4 equation 2). x = 7 and w = 8 I also know how to write more equations based on data available in the puzzle. How do I solve a set of such equations ? I need to find out the values of x and w for each such equation. I know that here the equations are simple because the puzzle can be simplfied. Thanks, Mohan [[alternative HTML version deleted]] __ R-help@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.
Re: [R] Testing general hypotheses on regression coefficients
On 06 Sep 2014, at 12:24 , bonsxanco bonsxa...@yahoo.com wrote: 1) 8th grade algebra tells me B2/B1 == 0 == B2 =0; EViews (econometrics program) doesn't have the same opinion: Wald test on my real model (edited): * H0: B3/B2 = 0 - F-stat = 37.82497 * H0: B3 = 0- F-stat = 16.31689 And when the econometrics program contradicts what you learned in 8th grade, surely the latter is wrong and the former is right, because it is done by a computer and computers cannot be wrong? ;-) Probably what this shows most of all is a weakness of the Wald test approach: The s.e. of (b3hat/b2hat) will likely differ from s.e.(b3hat)/b2hat and hence the test statistics will differ even though they really test the same hypothesis. Actually, there are two generic weaknesses: (a) the somewhat arbitrary choice of test statistic and (b) the fact that the s.e. is not calculated at the null value of the parameter, but at the estimate. -- Peter Dalgaard, Professor, Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: pd@cbs.dk Priv: pda...@gmail.com __ R-help@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.
Re: [R] Solving equations
In my education this was 9th or 10th grade (US) math. The r-help mailing list is not set up for providing mini-tutorials on R programming. Please read the Posting Guide, do the expected self-eduction in R programming, do the requested searching on your remaining questions in the Archives or StackOverflow and then in a few weeks considered reposting. Before doing so ... learn to post in plain text as as the Guide request. -- David. On Sep 7, 2014, at 1:54 AM, Mohan Radhakrishnan wrote: Hi, I code R to parse data but not for solving equations. So this is my first such problem. It is a programming puzzle. I have these two equations. 1)4x - 3w = 0 2)8x - 7w =0 I know the value of x and w for equation 1). x = 3 and w = 4 equation 2). x = 7 and w = 8 I also know how to write more equations based on data available in the puzzle. How do I solve a set of such equations ? I need to find out the values of x and w for each such equation. I know that here the equations are simple because the puzzle can be simplfied. Thanks, Mohan [[alternative HTML version deleted]] -- David Winsemius Alameda, CA, USA __ R-help@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.
Re: [R] Solving equations
Hello, Inline. Em 07-09-2014 09:54, Mohan Radhakrishnan escreveu: Hi, I code R to parse data but not for solving equations. So this is my first such problem. It is a programming puzzle. I have these two equations. 1)4x - 3w = 0 2)8x - 7w =0 I know the value of x and w for equation 1). x = 3 and w = 4 equation 2). x = 7 and w = 8 Why? Any of those equations defines a straight line, not a point. Those two points are just one of the infinitely many solutions. Your equations are equivalent to eq1) w = 4/3x eq2) w = 8/7x the equations of straight lines passing through the origin (no independent term). I also know how to write more equations based on data available in the puzzle. How do I solve a set of such equations ? I need to find out the values of x and w for each such equation. There are packages to solve simultaneous equations but I've never used them. Hope this helps, Rui Barradas I know that here the equations are simple because the puzzle can be simplfied. Thanks, Mohan [[alternative HTML version deleted]] __ R-help@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. __ R-help@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.
Re: [R] Question about searchTwitter{twitteR}
Twitter tweets aren't a stable database. I wouldn't expect the search results
to stay stable, as tweets are retweeted, deleted, accounts are closed, privacy
settings adjusted, etc. And if there are more than 1000 results, I don't know
that twitter is internally ordered so you'd get the same set of results each
time you run the same search.
On Sep 7, 2014, at 10:20 AM, Axel Urbiz axel.ur...@gmail.com wrote:
Hello,
The function searchTwitter() with the arguments supplied as below would
give me a different number of results on different days I run this code.
Maybe it is my lack of understanding about what the date arguments are
supposed to do in this function, but I would think I should be getting the
same tweets?
tweets - searchTwitter('my text search',
n = 1000,
since = '2013-09-01',
until = '2014-08-31')
Thanks,
Axel.
[[alternative HTML version deleted]]
__
R-help@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.
__
R-help@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.
[R] CRAN (and crantastic) updates this week
CRAN (and crantastic) updates this week New packages * classyfire (0.1-0) Maintainer: Eleni Chatzimichali Author(s): Eleni Chatzimichali ea.chatzimich...@gmail.com and Conrad Bessant c.bess...@qmul.ac.uk License: GPL (= 2) http://crantastic.org/packages/classyfire A collection of functions for the creation and application of highly optimised, robustly evaluated ensembles of support vector machines (SVMs). The package takes care of training individual SVM classifiers using a fast parallel heuristic algorithm, and combines individual classifiers into ensembles. Robust metrics of classification performance are offered by bootstrap resampling and permutation testing. * cooptrees (1.0) Maintainer: Manuel Fontenla Author(s): Manuel Fontenla License: GPL-3 http://crantastic.org/packages/cooptrees Computes several cooperative games and allocation rules associated with minimum cost spanning tree problems and minimum cost arborescence problems. * coreTDT (1.0) Maintainer: Yu Jiang Author(s): Yu Jiang, Andrew S Allen License: GPL-3 http://crantastic.org/packages/coreTDT Use to analysis case-parent trio sequencing studies. Test the compound heterozygous and recessive disease models * descomponer (1.0) Maintainer: Francisco Parra Author(s): Francisco Parra parra...@cantabria.es License: GPL (= 2) http://crantastic.org/packages/descomponer Decompose a time series into seasonal, trend and irregular components using transformations to amplitude-frequency domain. * Frames2 (0.0.3) Maintainer: David Molina Author(s): Antonio Arcos ar...@ugr.es, Maria del Mar Rueda mru...@ugr.es, Maria Giovanna Ranalli giovanna.rana...@stat.unipg.it and David Molina dmoli...@ugr.es License: GPL (= 2) http://crantastic.org/packages/Frames2 Point and interval estimation in dual frame surveys. In contrast to classic sampling theory, where only one sampling frame is considered, dual frame methodology assumes that there are two frames available for sampling and that, overall, they cover the entire target population. Then, two probability samples (one from each frame) are drawn and information collected is suitably combined to get estimators of the parameter of interest. * GUILDS (1.2) Maintainer: Thijs Janzen Author(s): Thijs Janzen License: GPL-2 http://crantastic.org/packages/GUILDS The GUILDS package combines a range of sampling formulas for the unified neutral model of biogeography and biodiversity. Alongside the sampling formulas, it includes methods to perform maximum likelihood optimization of the sampling formulas, methods to generate data given the neutral model, and methods to estimate the expected species abundance distribution. Sampling formulas included in the GUILDS package are the Etienne Sampling Formula (Etienne 2005), the guild sampling formula, where guilds are assumed to differ in dispersal ability (Janzen 2014), and the guilds sampling formula conditioned on guild size (Janzen 2014). * iBATCGH (1.0) Maintainer: Alberto Cassese Author(s): Alberto Cassese License: GPL-2 http://crantastic.org/packages/iBATCGH Bayesian integrative models of gene expression and comparative genomic hybridization data. The package provides inference on copy number variations and their association with gene expression * ica (1.0-0) Maintainer: Nathaniel E. Helwig Author(s): Nathaniel E. Helwig hel...@umn.edu License: GPL (= 2) http://crantastic.org/packages/ica Independent Component Analysis (ICA) using various algorithms: FastICA, Information-Maximization (Infomax), and Joint Approximate Diagonalization of Eigenmatrices (JADE). * insuranceData (1.0) Maintainer: Alicja Wolny--Dominiak Author(s): Alicja Wolny--Dominiak and Michal Trzesiok License: GPL-2 http://crantastic.org/packages/insuranceData Insurance datasets, which are often used in claims severity and claims frequency modelling. It helps testing new regression models in those problems, such as GLM, GLMM, HGLM, non-linear mixed models etc. Most of the data sets are applied in the project quot;Mixed models in ratemakingquot; supported by grant NN 111461540 from Polish National Science Center. * JAGUAR (1.1) Maintainer: Chaitanya Acharya Author(s): Chaitanya R. Acharya and Andrew S. Allen License: GPL-2 http://crantastic.org/packages/JAGUAR Implements a 2 degree-of-freedom score test that measures 1) the overall shift in the gene expression due to genotype, and 2) group-specific changes in gene expression due to genotype (interaction term) in a mixed-effects model framework. * mpcv (1.0) Maintainer: Krzysztof Ciupke Author(s): Krzysztof Ciupke krzysztof.ciu...@polsl.pl License: GPL (= 2.0) http://crantastic.org/packages/mpcv Multivariate process capability analysis using the multivariate process capability vector. Allows to analyze a
Re: [R] Mixed sorting/ordering of strings acknowledging roman numerals?
Thank you David - it took me awhile to get back to this and dig into
it. It's clever to imitate gtools::mixedorder() as far as possible.
A few comments:
1. It took me a while to understand why you picked 3899 in your
Roman-to-integer table; it's because roman(x) is NA for x 3899.
(BTW, in 'utils', there's utils:::.roman2numeric() which could be
utilized, but it's currently internal.)
2. I think you forgot D=500 and M=1000.
3. There was a typo in your code; I think you meant rank.roman instead
of rank.numeric in one place.
4. The idea behind nonnumeric() is to identify non-numeric substrings
by is.na(as.numeric()). Unfortunately, for romans that does not work.
Instead, we need to use is.na(numeric(x)) here, i.e.
nonnumeric - function(x) {
suppressWarnings(ifelse(is.na(numeric(x)), toupper(x), NA))
}
Actually, gtools::mixedorder() could use the same.
5. I undid your .numeric to .roman to minimize any differences to
gtools::mixedorder().
With the above fixes, we now have:
mixedorderRoman - function (x)
{
if (length(x) 1)
return(NULL)
else if (length(x) == 1)
return(1)
if (is.numeric(x))
return(order(x))
delim = \\$\\@\\$
# NOTE: Note that as.roman(x) is NA for x 3899
romanC - as.character( as.roman(1:3899) )
numeric - function(x) {
suppressWarnings(match(x, romanC))
}
nonnumeric - function(x) {
suppressWarnings(ifelse(is.na(numeric(x)), toupper(x),
NA))
}
x - as.character(x)
which.nas - which(is.na(x))
which.blanks - which(x == )
if (length(which.blanks) 0)
x[which.blanks] - -Inf
if (length(which.nas) 0)
x[which.nas] - Inf
delimited - gsub(([IVXCLM]+),
paste(delim, \\1, delim, sep = ), x)
step1 - strsplit(delimited, delim)
step1 - lapply(step1, function(x) x[x ])
step1.numeric - lapply(step1, numeric)
step1.character - lapply(step1, nonnumeric)
maxelem - max(sapply(step1, length))
step1.numeric.t - lapply(1:maxelem, function(i) sapply(step1.numeric,
function(x) x[i]))
step1.character.t - lapply(1:maxelem, function(i) sapply(step1.character,
function(x) x[i]))
rank.numeric - sapply(step1.numeric.t, rank)
rank.character - sapply(step1.character.t, function(x)
as.numeric(factor(x)))
rank.numeric[!is.na(rank.character)] - 0
rank.character - t(t(rank.character) + apply(matrix(rank.numeric),
2, max, na.rm = TRUE))
rank.overall - ifelse(is.na(rank.character), rank.numeric,
rank.character)
order.frame - as.data.frame(rank.overall)
if (length(which.nas) 0)
order.frame[which.nas, ] - Inf
retval - do.call(order, order.frame)
return(retval)
}
The difference to gtools::mixedorder() is minimal:
romanC - as.character( as.roman(1:3899) )
21c11
suppressWarnings(match(x, romanC))
---
suppressWarnings(as.numeric(x))
24c14
suppressWarnings(ifelse(is.na(numeric(x)), toupper(x),
---
suppressWarnings(ifelse(is.na(as.numeric(x)), toupper(x),
34c24
delimited - gsub(([IVXCLDM]+),
---
delimited -
gsub(([+-]{0,1}[0-9]+\\.{0,1}[0-9]*([eE][\\+\\-]{0,1}[0-9]+\\.{0,1}[0-9]*){0,1}),
59,62d48
This difference is so small that the above could now be an option to
mixedorder() with minimal overhead added, e.g. mixedorder(y,
type=c(decimal, roman)). One could even imagine adding support
for binary, octal and hexadecimal (not done).
Greg (maintainer of gtools; cc:ed), is this something you would
consider adding to gtools? I've modified the gtools source code
available on CRAN (that's the only source I found), added package
tests, updated the Rd and verified it passes R CMD check. If
interested, please find the updates at:
https://github.com/HenrikBengtsson/gtools/compare/cran:master...master
Thanks
Henrik
On Tue, Aug 26, 2014 at 6:46 PM, David Winsemius dwinsem...@comcast.net wrote:
On Aug 26, 2014, at 5:24 PM, Henrik Bengtsson wrote:
Hi,
does anyone know of an implementation/function that sorts strings that
*contain* roman numerals (I, II, III, IV, V, ...) which are treated as
numbers. In 'gtools' there is mixedsort() which does this for strings
that contains (decimal) numbers. I'm looking for a mixedsortroman()
function that does the same but with roman numbers, e.g.
It's pretty easy to sort something you know to be congruent with the existing
roman class:
romanC - as.character( as.roman(1:3899) )
match(c(I, II, III,X,V), romanC)
#[1] 1 2 3 10 5
But I guess you already know that, so you want a regex approach to parsing.
Looking at the path taken by Warnes, it would involve doing something like
his regex based insertion of a delimiter for Roman numeral but simpler
because he needed to deal with decimal points and signs and exponent
notation, none of which you appear to need. If you only need to consider
character and Roman, then this hack of Warnes tools succeeds:
Re: [R] Mixed sorting/ordering of strings acknowledging roman numerals?
On Sep 7, 2014, at 7:40 PM, Henrik Bengtsson wrote:
Thank you David - it took me awhile to get back to this and dig into
it. It's clever to imitate gtools::mixedorder() as far as possible.
A few comments:
1. It took me a while to understand why you picked 3899 in your
Roman-to-integer table; it's because roman(x) is NA for x 3899.
(BTW, in 'utils', there's utils:::.roman2numeric() which could be
utilized, but it's currently internal.)
Yes, that was the reason. I didn't think I needed a Roman-to-numeric function
because I discovered the roman numbers were actually simple numeric vectors to
which a class had been assigned and that it was the class-facilities that did
all the work. The standard Ops functions were just acting on numeric vectors.
If one doesn't take care, their romanity can be lost:
R - as.roman(10^(0:4))
R
[1] IXCMNA
unclass(R)
[1]1 10 100 1000 NA
sum(R, na.rm=TRUE)
[1]
as.roman(sum(R, na.rm=TRUE))
[1] MCXI
2. I think you forgot D=500 and M=1000.
Quite possible. I suspect Greg will have corrected the omission, but if not,
this will be helpful to him.
3. There was a typo in your code; I think you meant rank.roman instead
of rank.numeric in one place.
I understood Greg's intention to wrap this into the mixedorder and mixed sort
duo.
Best;
David.
4. The idea behind nonnumeric() is to identify non-numeric substrings
by is.na(as.numeric()). Unfortunately, for romans that does not work.
Instead, we need to use is.na(numeric(x)) here, i.e.
nonnumeric - function(x) {
suppressWarnings(ifelse(is.na(numeric(x)), toupper(x), NA))
}
Actually, gtools::mixedorder() could use the same.
5. I undid your .numeric to .roman to minimize any differences to
gtools::mixedorder().
With the above fixes, we now have:
mixedorderRoman - function (x)
{
if (length(x) 1)
return(NULL)
else if (length(x) == 1)
return(1)
if (is.numeric(x))
return(order(x))
delim = \\$\\@\\$
# NOTE: Note that as.roman(x) is NA for x 3899
romanC - as.character( as.roman(1:3899) )
numeric - function(x) {
suppressWarnings(match(x, romanC))
}
nonnumeric - function(x) {
suppressWarnings(ifelse(is.na(numeric(x)), toupper(x),
NA))
}
x - as.character(x)
which.nas - which(is.na(x))
which.blanks - which(x == )
if (length(which.blanks) 0)
x[which.blanks] - -Inf
if (length(which.nas) 0)
x[which.nas] - Inf
delimited - gsub(([IVXCLM]+),
paste(delim, \\1, delim, sep = ), x)
step1 - strsplit(delimited, delim)
step1 - lapply(step1, function(x) x[x ])
step1.numeric - lapply(step1, numeric)
step1.character - lapply(step1, nonnumeric)
maxelem - max(sapply(step1, length))
step1.numeric.t - lapply(1:maxelem, function(i) sapply(step1.numeric,
function(x) x[i]))
step1.character.t - lapply(1:maxelem, function(i) sapply(step1.character,
function(x) x[i]))
rank.numeric - sapply(step1.numeric.t, rank)
rank.character - sapply(step1.character.t, function(x)
as.numeric(factor(x)))
rank.numeric[!is.na(rank.character)] - 0
rank.character - t(t(rank.character) + apply(matrix(rank.numeric),
2, max, na.rm = TRUE))
rank.overall - ifelse(is.na(rank.character), rank.numeric,
rank.character)
order.frame - as.data.frame(rank.overall)
if (length(which.nas) 0)
order.frame[which.nas, ] - Inf
retval - do.call(order, order.frame)
return(retval)
}
The difference to gtools::mixedorder() is minimal:
romanC - as.character( as.roman(1:3899) )
21c11
suppressWarnings(match(x, romanC))
---
suppressWarnings(as.numeric(x))
24c14
suppressWarnings(ifelse(is.na(numeric(x)), toupper(x),
---
suppressWarnings(ifelse(is.na(as.numeric(x)), toupper(x),
34c24
delimited - gsub(([IVXCLDM]+),
---
delimited -
gsub(([+-]{0,1}[0-9]+\\.{0,1}[0-9]*([eE][\\+\\-]{0,1}[0-9]+\\.{0,1}[0-9]*){0,1}),
59,62d48
This difference is so small that the above could now be an option to
mixedorder() with minimal overhead added, e.g. mixedorder(y,
type=c(decimal, roman)). One could even imagine adding support
for binary, octal and hexadecimal (not done).
Greg (maintainer of gtools; cc:ed), is this something you would
consider adding to gtools? I've modified the gtools source code
available on CRAN (that's the only source I found), added package
tests, updated the Rd and verified it passes R CMD check. If
interested, please find the updates at:
https://github.com/HenrikBengtsson/gtools/compare/cran:master...master
Thanks
Henrik
On Tue, Aug 26, 2014 at 6:46 PM, David Winsemius dwinsem...@comcast.net
wrote:
On Aug 26, 2014, at 5:24 PM, Henrik Bengtsson wrote:
Hi,
does anyone know of an implementation/function that sorts strings that
*contain* roman numerals (I, II, III, IV, V,
[R] Psych package
Hi Team,
I tried using fa.ply function for a dataset with ordinal and nominal
variables.Its giving the following Warning.Is it a bug?Or we need to use some
other procedure for factor analysis of ordinal/nominal data?
Code:-
faPCdirect - fa.poly(mydata, nfactors=12, rotate=varimax)
Warning:-
The items do not have an equal number of response alternatives, global set to
FALSE
The items do not have an equal number of response alternatives, global set to
FALSE
The estimated weights for the factor scores are probably incorrect. Try a
different factor extraction method.
There were 35 warnings (use warnings() to see them)
Regards
Sarbani
This message is for the designated recipient only and ma...{{dropped:16}}
__
R-help@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.
Re: [R] Solving equations
No. I was not looking for an answer to that question. I wasn't clear :-) I already code using Octave and R to solve ML algorithms. I am trying to understand how R packages can help us to solve such equations using LU decomposition etc. The question was about using R with these math algorithms. Mohan On Mon, Sep 8, 2014 at 12:31 AM, Rui Barradas ruipbarra...@sapo.pt wrote: Hello, Inline. Em 07-09-2014 09:54, Mohan Radhakrishnan escreveu: Hi, I code R to parse data but not for solving equations. So this is my first such problem. It is a programming puzzle. I have these two equations. 1)4x - 3w = 0 2)8x - 7w =0 I know the value of x and w for equation 1). x = 3 and w = 4 equation 2). x = 7 and w = 8 Why? Any of those equations defines a straight line, not a point. Those two points are just one of the infinitely many solutions. Your equations are equivalent to eq1) w = 4/3x eq2) w = 8/7x the equations of straight lines passing through the origin (no independent term). I also know how to write more equations based on data available in the puzzle. How do I solve a set of such equations ? I need to find out the values of x and w for each such equation. There are packages to solve simultaneous equations but I've never used them. Hope this helps, Rui Barradas I know that here the equations are simple because the puzzle can be simplfied. Thanks, Mohan [[alternative HTML version deleted]] __ R-help@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. [[alternative HTML version deleted]] __ R-help@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.
