From brian at braverock.com  Tue Sep  3 18:02:33 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Tue, 03 Sep 2013 11:02:33 -0500
Subject: [GSoC-PortA] R CMD check
Message-ID: <52260819.4010703@braverock.com>

I just ran R CMD check on current svn, and it's kind of a mess.

'R CMD build' runs fine, which is good.

The vignettes take over 100 minutes to build using only one core on my 8 
(physical) core desktop.  CRAN won't like that, but I think it is 
necessary. I think we can make a case to CRAN that we need non-toy 
examples for everything, and they can get over it.

The rest of check is going to need some work.

By far the biggest thing is missing/incorrect parameters in the 
documentation.  This should all be worked out by making rure the roxygen 
comments are up to date and that the docs are regenerated.

Another big area of check wordiness is in the S3 methods (e.g. 
chart.Scatter, chart.Weights, extractStats) , which we had agreed should 
be collapsed into a single main entry as I had done with 
optimize.portfolio, etc.  We might need to add some @method tags to the 
roxygen comments.

I think it's rather important to start cleaning this stuff up, we've 
only got a few weeks left in GSoC.

Full results of 'R CMD check --no-vignettes' and the generated manual 
attached.

Regards,

Brian

-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 00check.log
Type: text/x-log
Size: 26874 bytes
Desc: not available
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130903/6d05b0b2/attachment-0001.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: PortfolioAnalytics-manual.pdf
Type: application/pdf
Size: 269272 bytes
Desc: not available
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130903/6d05b0b2/attachment-0001.pdf>

From rossbennett34 at gmail.com  Tue Sep  3 18:30:56 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Tue, 3 Sep 2013 09:30:56 -0700
Subject: [GSoC-PortA] R CMD check
In-Reply-To: <52260819.4010703@braverock.com>
References: <52260819.4010703@braverock.com>
Message-ID: <CAEESW=V6VqAYG3t=o3xx06x0FEDrbXCgxVjTe203VOyoGO7-Ew@mail.gmail.com>

Brian,

Thanks for the note.

Regarding the S3 generic methods. My intention with the chart.Weights.EF
function was that it would be a generic method for optimize.portfolio and
efficient.frontier objects. Since chart.Weights is already a generic method
for optimize.portfolio objects, I don't think chart.Weights can be used a
generic function to chart weights along the efficient frontier. I think I
should just rename chart.Weights.EF to chart.WeightsEF.

Regarding the other documentation issues, I'll get to work on cleaning
those up.

Thanks,
Ross


On Tue, Sep 3, 2013 at 9:02 AM, Brian G. Peterson <brian at braverock.com>wrote:

> I just ran R CMD check on current svn, and it's kind of a mess.
>
> 'R CMD build' runs fine, which is good.
>
> The vignettes take over 100 minutes to build using only one core on my 8
> (physical) core desktop.  CRAN won't like that, but I think it is
> necessary. I think we can make a case to CRAN that we need non-toy examples
> for everything, and they can get over it.
>
> The rest of check is going to need some work.
>
> By far the biggest thing is missing/incorrect parameters in the
> documentation.  This should all be worked out by making rure the roxygen
> comments are up to date and that the docs are regenerated.
>
> Another big area of check wordiness is in the S3 methods (e.g.
> chart.Scatter, chart.Weights, extractStats) , which we had agreed should be
> collapsed into a single main entry as I had done with optimize.portfolio,
> etc.  We might need to add some @method tags to the roxygen comments.
>
> I think it's rather important to start cleaning this stuff up, we've only
> got a few weeks left in GSoC.
>
> Full results of 'R CMD check --no-vignettes' and the generated manual
> attached.
>
> Regards,
>
> Brian
>
> --
> Brian G. Peterson
> http://braverock.com/brian/
> Ph: 773-459-4973
> IM: bgpbraverock
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130903/79192a53/attachment.html>

From brian at braverock.com  Tue Sep  3 19:26:59 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Tue, 03 Sep 2013 12:26:59 -0500
Subject: [GSoC-PortA] R CMD check
In-Reply-To: <CAEESW=V6VqAYG3t=o3xx06x0FEDrbXCgxVjTe203VOyoGO7-Ew@mail.gmail.com>
References: <52260819.4010703@braverock.com>
 <CAEESW=V6VqAYG3t=o3xx06x0FEDrbXCgxVjTe203VOyoGO7-Ew@mail.gmail.com>
Message-ID: <52261BE3.5040500@braverock.com>

On 09/03/2013 11:30 AM, Ross Bennett wrote:
>
> Regarding the S3 generic methods. My intention with the chart.Weights.EF
> function was that it would be a generic method for optimize.portfolio
> and efficient.frontier objects. Since chart.Weights is already a generic
> method for optimize.portfolio objects, I don't think chart.Weights can
> be used a generic function to chart weights along the efficient
> frontier. I think I should just rename chart.Weights.EF to chart.WeightsEF.

Can the efficient.frontier opbjects be subclassed from the 
optimize.portfolio objects?  (I haven't looked closely at the structure 
there, so I don't know)

-- 
Brian

From rossbennett34 at gmail.com  Wed Sep  4 06:53:40 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Tue, 3 Sep 2013 21:53:40 -0700
Subject: [GSoC-PortA] R CMD check
In-Reply-To: <52261BE3.5040500@braverock.com>
References: <52260819.4010703@braverock.com>
 <CAEESW=V6VqAYG3t=o3xx06x0FEDrbXCgxVjTe203VOyoGO7-Ew@mail.gmail.com>
 <52261BE3.5040500@braverock.com>
Message-ID: <CAEESW=UKNNY_iZkKEA3a89MwysF7xigYE5WJx-EkVde9VLEHYg@mail.gmail.com>

Brian,

I'm not entirely sure how to do that or if it is doable with the structure
I have. If you have a minute and would be able to take a closer look to see
if that is possible would be greatly appreciated.

Maybe another option would be to remove chart.Weights.EF.optimize.portfolio
and change chart.Weights.EF.efficient.frontier
to chart.Weights.efficient.frontier so chart.Weights is a generic function
for optimize.portfolio.* and efficient.frontier objects. Although we would
lose the ability to plot an efficient frontier directly from an
optimize.portfolio, the chart.Weights function would be more consistent.

Please advise what you think is the best way to proceed.

Thanks,
Ross


On Tue, Sep 3, 2013 at 10:26 AM, Brian G. Peterson <brian at braverock.com>wrote:

> On 09/03/2013 11:30 AM, Ross Bennett wrote:
>
>>
>> Regarding the S3 generic methods. My intention with the chart.Weights.EF
>> function was that it would be a generic method for optimize.portfolio
>> and efficient.frontier objects. Since chart.Weights is already a generic
>> method for optimize.portfolio objects, I don't think chart.Weights can
>> be used a generic function to chart weights along the efficient
>> frontier. I think I should just rename chart.Weights.EF to
>> chart.WeightsEF.
>>
>
> Can the efficient.frontier opbjects be subclassed from the
> optimize.portfolio objects?  (I haven't looked closely at the structure
> there, so I don't know)
>
> --
> Brian
>
> ______________________________**_________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-**project.org<GSoC-PortA at lists.r-forge.r-project.org>
> http://lists.r-forge.r-**project.org/cgi-bin/mailman/**listinfo/gsoc-porta<http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130903/473b834b/attachment.html>

From brian at braverock.com  Sun Sep  8 13:20:37 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Sun, 08 Sep 2013 06:20:37 -0500
Subject: [GSoC-PortA] testing scripts to demo ?
Message-ID: <522C5D85.6080908@braverock.com>

I'm wondering if many/most of the testing_* scripts should lose their 
testing_ prefix and get 'svn move'd to the demo/ directory.

Thoughts?


-- 
Brian

From rossbennett34 at gmail.com  Sun Sep  8 23:01:15 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Sun, 8 Sep 2013 14:01:15 -0700
Subject: [GSoC-PortA] testing scripts to demo ?
In-Reply-To: <522C5D85.6080908@braverock.com>
References: <522C5D85.6080908@braverock.com>
Message-ID: <CAEESW=U7hqmXH4FswihpKiZcBv5xvuvXr6N2DmS_rxy+CcFtTQ@mail.gmail.com>

Brian,

I agree that several of the testing scripts in the sandbox could be moved
to the demo directory. Some could probably be added to existing demos. I'll
move or add to existing demos where appropriate.

Thanks,
Ross


On Sun, Sep 8, 2013 at 4:20 AM, Brian G. Peterson <brian at braverock.com>wrote:

> I'm wondering if many/most of the testing_* scripts should lose their
> testing_ prefix and get 'svn move'd to the demo/ directory.
>
> Thoughts?
>
>
> --
> Brian
> ______________________________**_________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-**project.org<GSoC-PortA at lists.r-forge.r-project.org>
> http://lists.r-forge.r-**project.org/cgi-bin/mailman/**listinfo/gsoc-porta<http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130908/cdbf63ac/attachment.html>

From rossbennett34 at gmail.com  Mon Sep 16 23:53:00 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Mon, 16 Sep 2013 14:53:00 -0700
Subject: [GSoC-PortA] R CMD check info`
Message-ID: <CAEESW=U_xitGn=TBwcc6C6KqX1=7mzAAcXwDXkETbWc4aJ4phg@mail.gmail.com>

Brian and others,

I ran R CMD check and I only get 3 warnings and 3 notes. The log file is
attached.

Under the "checking R code for possible problems", there are several lines
with something like "no visible binding for global variable 'strategy' ".
Is this something that should be addressed? If so, what is the best way to
correct this?

On a side note, I have made multiple commits over the last two days, but
have not received any [Returnanalytics-commits] emails from r-forge.  The
last email I received was for commit r3107 and my latest commit is
r3125.Have any of you received the commit emails recently?

Thanks,
Ross
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130916/81ec01d1/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 00check.log
Type: application/octet-stream
Size: 5797 bytes
Desc: not available
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130916/81ec01d1/attachment.obj>

From brian at braverock.com  Tue Sep 17 21:29:22 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Tue, 17 Sep 2013 14:29:22 -0500
Subject: [GSoC-PortA] R CMD check info`
In-Reply-To: <CAEESW=U_xitGn=TBwcc6C6KqX1=7mzAAcXwDXkETbWc4aJ4phg@mail.gmail.com>
References: <CAEESW=U_xitGn=TBwcc6C6KqX1=7mzAAcXwDXkETbWc4aJ4phg@mail.gmail.com>
Message-ID: <cf916f66-61e8-4a37-a34a-877652a9e902@email.android.com>

Ross,

We should chase all warnings. I'll take a look at the log.

It looks like R-Forge just fixed their email listserv...

Regards,

Brian

Ross Bennett <rossbennett34 at gmail.com> wrote:
>Brian and others,
>
>I ran R CMD check and I only get 3 warnings and 3 notes. The log file
>is
>attached.
>
>Under the "checking R code for possible problems", there are several
>lines
>with something like "no visible binding for global variable 'strategy'
>".
>Is this something that should be addressed? If so, what is the best way
>to
>correct this?
>
>On a side note, I have made multiple commits over the last two days,
>but
>have not received any [Returnanalytics-commits] emails from r-forge. 
>The
>last email I received was for commit r3107 and my latest commit is
>r3125.Have any of you received the commit emails recently?
>
>Thanks,
>Ross
>
>
>------------------------------------------------------------------------
>
>_______________________________________________
>GSoC-PortA mailing list
>GSoC-PortA at lists.r-forge.r-project.org
>http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta

-- 
Sent from my Android phone with K-9 Mail. Please excuse my brevity.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130917/01a3cf79/attachment.html>

From peter at braverock.com  Wed Sep 18 03:53:02 2013
From: peter at braverock.com (Peter Carl)
Date: Tue, 17 Sep 2013 20:53:02 -0500
Subject: [GSoC-PortA] Error in plot method
Message-ID: <c5d2543e80c5335e3d315894d15d0185.squirrel@mail.braverock.com>

Ross,

You might already know about this, given that I'm a day behind on svn. 
Sorry for the lack of detail, I can do more debugging if you need.

> R = edhec[,c("Convertible Arbitrage", "Equity Market Neutral","Fixed
Income Arbitrage", "Event Driven", "CTA Global", "Global Macro",
"Long/Short Equity")]
> init.portf <- portfolio.spec(assets=colnames(R))
> init.portf <- add.constraint(portfolio=init.portf,
+                              type="leverage",
+                              min_sum=1,
+                              max_sum=1)
> # Add box constraint
> init.portf <- add.constraint(portfolio=init.portf,
+                              type="box",
+                              min=0.05,
+                              max=0.3)
>
> # Add group constraint
> init.portf <- add.constraint(portfolio=init.portf, type="group",
+                   groups=list(c(1:4),
+                               c(5:7)),
+                   group_min=c(0.1,.05),
+                   group_max=c(0.85,0.75)
+ )
> #Add measure 1, annualized return
> init.portf <- add.objective(portfolio=init.portf,
+                             type="return", # the kind of objective this is
+                             name="mean", # name of the function
+                             enabled=TRUE, # enable or disable the objective
+                             multiplier=0 # calculate it but don't use it
in the objective
+ )
>
> # Add measure 2, annualized standard deviation
> init.portf <- add.objective(portfolio=init.portf,
+                             type="risk", # the kind of objective this is
+                             name="var", # to minimize from the sample
+                             enabled=TRUE, # enable or disable the objective
+                             multiplier=0 # calculate it but don't use it
in the objective
+ )
>
> # Add measure 3, ES
> init.portf <- add.objective(portfolio=init.portf,
+                             type="risk", # the kind of objective this is
+                             name="ES", # the function to minimize
+                             enabled=FALSE, # enable or disable the
objective
+                             multiplier=0, # calculate it but don't use
it in the objective
+                             arguments=list(p=p)
+ )
> MeanVar.portf <- init.portf
# Turn back on the return and sd objectives
> MeanVar.portf$objectives[[1]]$multiplier = -1 # mean
> MeanVar.portf$objectives[[2]]$multiplier = 1 # var
> MeanVar.ROI<-optimize.portfolio(R=R,
+   portfolio=MeanVar.portf,
+   optimize_method='ROI'
+ )
> summary(MeanVar.ROI)
**************************************************
PortfolioAnalytics Optimization Summary
**************************************************

Call:
optimize.portfolio(R = R, portfolio = MeanVar.portf, optimize_method = "ROI")

Optimal Weights:
 Convertible Arbitrage  Equity Market Neutral Fixed Income Arbitrage      
    Event Driven             CTA Global           Global Macro
                0.0500                 0.0500                 0.0500      
          0.2134                 0.0500                
0.3000
     Long/Short Equity
                0.2866

Objective Measures:
    mean
0.007309


 StdDev
0.01561



Portfolio Assets and Initial Weights:
 Convertible Arbitrage  Equity Market Neutral Fixed Income Arbitrage      
    Event Driven             CTA Global           Global Macro
             0.1428571              0.1428571              0.1428571      
       0.1428571              0.1428571             
0.1428571
     Long/Short Equity
             0.1428571

**************************************************
PortfolioAnalytics Portfolio Specification
**************************************************

Call:
portfolio.spec(assets = colnames(R))

Assets
Number of assets: 7

Asset Names
[1] "Convertible Arbitrage"  "Equity Market Neutral"  "Fixed Income
Arbitrage" "Event Driven"           "CTA Global"
[6] "Global Macro"           "Long/Short Equity"

Constraints
Number of constraints: 3
Number of enabled constraints: 3
Enabled constraint types
		- leverage
		- box
		- group
Number of disabled constraints: 0

Objectives
Number of objectives: 3
Number of enabled objectives: 2
Enabled objective names
		- mean
		- var
Number of disabled objectives: 1
Disabled objective types
		- ES

****************************************
Constraints
****************************************
Leverage Constraint:
min_sum = 1
max_sum = 1

Box Constraints:
min:
 Convertible Arbitrage  Equity Market Neutral Fixed Income Arbitrage      
    Event Driven             CTA Global           Global Macro
                  0.05                   0.05                   0.05      
            0.05                   0.05                 
 0.05
     Long/Short Equity
                  0.05
max:
 Convertible Arbitrage  Equity Market Neutral Fixed Income Arbitrage      
    Event Driven             CTA Global           Global Macro
                   0.3                    0.3                    0.3      
             0.3                    0.3                
   0.3
     Long/Short Equity
                   0.3

Group Constraints:
Groups:
$group1
[1] 1 2 3 4

$group2
[1] 5 6 7


Lower bound on group weights, group_min:
group1 group2
  0.10   0.05

Upper bound on group weights, group_max:
group1 group2
  0.85   0.75

Group position limits, group_pos:
NULL

Group Weights:
   group1    group2
0.3633993 0.6366007

Position Limit Constraints:
Maximum number of non-zero weights, max_pos:
NULL
Realized number of non-zero weights (i.e. positions):
[1] 7

Maximum number of long positions, max_pos_long:
NULL
Realized number of long positions:
[1] 7

Maximum number of short positions, max_pos_short:
NULL
Realized number of short positions:
[1] 0


Diversification Target Constraint:
NULL

Realized diversification:
[1] 0.7723208

Turnover Target Constraint:
NULL

Realized turnover from initial weights:
[1] 0.1061224

****************************************
Objectives
****************************************

Objective: return_objective
$name
[1] "mean"

$target
NULL

$arguments
list()

$enabled
[1] TRUE

$multiplier
[1] -1

$call
add.objective(portfolio = init.portf, type = "return", name = "mean",
    enabled = TRUE, multiplier = 0)

attr(,"class")
[1] "return_objective" "objective"

****************************************
Objective: portfolio_risk_objective
$name
[1] "var"

$target
NULL

$arguments
$arguments$portfolio_method
[1] "single"


$enabled
[1] TRUE

$multiplier
[1] 1

$call
add.objective(portfolio = init.portf, type = "risk", name = "var",
    enabled = TRUE, multiplier = 0)

attr(,"class")
[1] "portfolio_risk_objective" "objective"

****************************************
Objective: portfolio_risk_objective
$name
[1] "ES"

$target
NULL

$arguments
$arguments$p
[1] 0.9166667

$arguments$portfolio_method
[1] "single"


$enabled
[1] FALSE

$multiplier
[1] 0

$call
add.objective(portfolio = init.portf, type = "risk", name = "ES",
    arguments = list(p = p), enabled = FALSE, multiplier = 0)

attr(,"class")
[1] "portfolio_risk_objective" "objective"

****************************************

Elapsed Time:
Time difference of 0.5688059 secs

> plot(MeanVar.ROI)
Error in apply(R, 2, "mean") : dim(X) must have a positive length
> traceback()
10: stop("dim(X) must have a positive length")
9: apply(R, 2, "mean")
8: as.vector(apply(R, 2, "mean"))
7: matrix(as.vector(apply(R, 2, "mean")), ncol = 1)
6: moments(R)
5: applyFUN(R = R, weights = rp, FUN = return.col, ... = ...)
4: chart.Scatter.ROI(object = ROI, rp = rp, return.col = return.col,
       risk.col = risk.col, ..., chart.assets = chart.assets,
element.color = element.color,
       cex.axis = cex.axis, main = main, xlim = xlim, ylim = ylim)
3: charts.ROI(ROI = x, rp = rp, risk.col = risk.col, return.col = return.col,
       chart.assets = chart.assets, main = main, xlim = xlim, ylim = ylim,
       ...)
2: plot.optimize.portfolio.ROI(MeanVar.ROI)
1: plot(MeanVar.ROI)

pcc
-- 
Peter Carl
http://www.braverock.com/peter



From rossbennett34 at gmail.com  Wed Sep 18 04:01:26 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Tue, 17 Sep 2013 19:01:26 -0700
Subject: [GSoC-PortA] Error in plot method
In-Reply-To: <c5d2543e80c5335e3d315894d15d0185.squirrel@mail.braverock.com>
References: <c5d2543e80c5335e3d315894d15d0185.squirrel@mail.braverock.com>
Message-ID: <CAEESW=XPbJk=M5wvt_LjP62=Q6PaS4Fdie-SJoK+FwriOVexFA@mail.gmail.com>

Peter,

Thanks for the note. The error is because you ran optimize.portfolio
without trace=TRUE so the returns object, R, is not available. I'll add a
check to the function that will throw an error with a more informative
message if the R object is missing.

Thanks,
Ross


On Tue, Sep 17, 2013 at 6:53 PM, Peter Carl <peter at braverock.com> wrote:

> Ross,
>
> You might already know about this, given that I'm a day behind on svn.
> Sorry for the lack of detail, I can do more debugging if you need.
>
> > R = edhec[,c("Convertible Arbitrage", "Equity Market Neutral","Fixed
> Income Arbitrage", "Event Driven", "CTA Global", "Global Macro",
> "Long/Short Equity")]
> > init.portf <- portfolio.spec(assets=colnames(R))
> > init.portf <- add.constraint(portfolio=init.portf,
> +                              type="leverage",
> +                              min_sum=1,
> +                              max_sum=1)
> > # Add box constraint
> > init.portf <- add.constraint(portfolio=init.portf,
> +                              type="box",
> +                              min=0.05,
> +                              max=0.3)
> >
> > # Add group constraint
> > init.portf <- add.constraint(portfolio=init.portf, type="group",
> +                   groups=list(c(1:4),
> +                               c(5:7)),
> +                   group_min=c(0.1,.05),
> +                   group_max=c(0.85,0.75)
> + )
> > #Add measure 1, annualized return
> > init.portf <- add.objective(portfolio=init.portf,
> +                             type="return", # the kind of objective this
> is
> +                             name="mean", # name of the function
> +                             enabled=TRUE, # enable or disable the
> objective
> +                             multiplier=0 # calculate it but don't use it
> in the objective
> + )
> >
> > # Add measure 2, annualized standard deviation
> > init.portf <- add.objective(portfolio=init.portf,
> +                             type="risk", # the kind of objective this is
> +                             name="var", # to minimize from the sample
> +                             enabled=TRUE, # enable or disable the
> objective
> +                             multiplier=0 # calculate it but don't use it
> in the objective
> + )
> >
> > # Add measure 3, ES
> > init.portf <- add.objective(portfolio=init.portf,
> +                             type="risk", # the kind of objective this is
> +                             name="ES", # the function to minimize
> +                             enabled=FALSE, # enable or disable the
> objective
> +                             multiplier=0, # calculate it but don't use
> it in the objective
> +                             arguments=list(p=p)
> + )
> > MeanVar.portf <- init.portf
> # Turn back on the return and sd objectives
> > MeanVar.portf$objectives[[1]]$multiplier = -1 # mean
> > MeanVar.portf$objectives[[2]]$multiplier = 1 # var
> > MeanVar.ROI<-optimize.portfolio(R=R,
> +   portfolio=MeanVar.portf,
> +   optimize_method='ROI'
> + )
> > summary(MeanVar.ROI)
> **************************************************
> PortfolioAnalytics Optimization Summary
> **************************************************
>
> Call:
> optimize.portfolio(R = R, portfolio = MeanVar.portf, optimize_method =
> "ROI")
>
> Optimal Weights:
>  Convertible Arbitrage  Equity Market Neutral Fixed Income Arbitrage
>     Event Driven             CTA Global           Global Macro
>                 0.0500                 0.0500                 0.0500
>           0.2134                 0.0500
> 0.3000
>      Long/Short Equity
>                 0.2866
>
> Objective Measures:
>     mean
> 0.007309
>
>
>  StdDev
> 0.01561
>
>
>
> Portfolio Assets and Initial Weights:
>  Convertible Arbitrage  Equity Market Neutral Fixed Income Arbitrage
>     Event Driven             CTA Global           Global Macro
>              0.1428571              0.1428571              0.1428571
>        0.1428571              0.1428571
> 0.1428571
>      Long/Short Equity
>              0.1428571
>
> **************************************************
> PortfolioAnalytics Portfolio Specification
> **************************************************
>
> Call:
> portfolio.spec(assets = colnames(R))
>
> Assets
> Number of assets: 7
>
> Asset Names
> [1] "Convertible Arbitrage"  "Equity Market Neutral"  "Fixed Income
> Arbitrage" "Event Driven"           "CTA Global"
> [6] "Global Macro"           "Long/Short Equity"
>
> Constraints
> Number of constraints: 3
> Number of enabled constraints: 3
> Enabled constraint types
>                 - leverage
>                 - box
>                 - group
> Number of disabled constraints: 0
>
> Objectives
> Number of objectives: 3
> Number of enabled objectives: 2
> Enabled objective names
>                 - mean
>                 - var
> Number of disabled objectives: 1
> Disabled objective types
>                 - ES
>
> ****************************************
> Constraints
> ****************************************
> Leverage Constraint:
> min_sum = 1
> max_sum = 1
>
> Box Constraints:
> min:
>  Convertible Arbitrage  Equity Market Neutral Fixed Income Arbitrage
>     Event Driven             CTA Global           Global Macro
>                   0.05                   0.05                   0.05
>             0.05                   0.05
>  0.05
>      Long/Short Equity
>                   0.05
> max:
>  Convertible Arbitrage  Equity Market Neutral Fixed Income Arbitrage
>     Event Driven             CTA Global           Global Macro
>                    0.3                    0.3                    0.3
>              0.3                    0.3
>    0.3
>      Long/Short Equity
>                    0.3
>
> Group Constraints:
> Groups:
> $group1
> [1] 1 2 3 4
>
> $group2
> [1] 5 6 7
>
>
> Lower bound on group weights, group_min:
> group1 group2
>   0.10   0.05
>
> Upper bound on group weights, group_max:
> group1 group2
>   0.85   0.75
>
> Group position limits, group_pos:
> NULL
>
> Group Weights:
>    group1    group2
> 0.3633993 0.6366007
>
> Position Limit Constraints:
> Maximum number of non-zero weights, max_pos:
> NULL
> Realized number of non-zero weights (i.e. positions):
> [1] 7
>
> Maximum number of long positions, max_pos_long:
> NULL
> Realized number of long positions:
> [1] 7
>
> Maximum number of short positions, max_pos_short:
> NULL
> Realized number of short positions:
> [1] 0
>
>
> Diversification Target Constraint:
> NULL
>
> Realized diversification:
> [1] 0.7723208
>
> Turnover Target Constraint:
> NULL
>
> Realized turnover from initial weights:
> [1] 0.1061224
>
> ****************************************
> Objectives
> ****************************************
>
> Objective: return_objective
> $name
> [1] "mean"
>
> $target
> NULL
>
> $arguments
> list()
>
> $enabled
> [1] TRUE
>
> $multiplier
> [1] -1
>
> $call
> add.objective(portfolio = init.portf, type = "return", name = "mean",
>     enabled = TRUE, multiplier = 0)
>
> attr(,"class")
> [1] "return_objective" "objective"
>
> ****************************************
> Objective: portfolio_risk_objective
> $name
> [1] "var"
>
> $target
> NULL
>
> $arguments
> $arguments$portfolio_method
> [1] "single"
>
>
> $enabled
> [1] TRUE
>
> $multiplier
> [1] 1
>
> $call
> add.objective(portfolio = init.portf, type = "risk", name = "var",
>     enabled = TRUE, multiplier = 0)
>
> attr(,"class")
> [1] "portfolio_risk_objective" "objective"
>
> ****************************************
> Objective: portfolio_risk_objective
> $name
> [1] "ES"
>
> $target
> NULL
>
> $arguments
> $arguments$p
> [1] 0.9166667
>
> $arguments$portfolio_method
> [1] "single"
>
>
> $enabled
> [1] FALSE
>
> $multiplier
> [1] 0
>
> $call
> add.objective(portfolio = init.portf, type = "risk", name = "ES",
>     arguments = list(p = p), enabled = FALSE, multiplier = 0)
>
> attr(,"class")
> [1] "portfolio_risk_objective" "objective"
>
> ****************************************
>
> Elapsed Time:
> Time difference of 0.5688059 secs
>
> > plot(MeanVar.ROI)
> Error in apply(R, 2, "mean") : dim(X) must have a positive length
> > traceback()
> 10: stop("dim(X) must have a positive length")
> 9: apply(R, 2, "mean")
> 8: as.vector(apply(R, 2, "mean"))
> 7: matrix(as.vector(apply(R, 2, "mean")), ncol = 1)
> 6: moments(R)
> 5: applyFUN(R = R, weights = rp, FUN = return.col, ... = ...)
> 4: chart.Scatter.ROI(object = ROI, rp = rp, return.col = return.col,
>        risk.col = risk.col, ..., chart.assets = chart.assets,
> element.color = element.color,
>        cex.axis = cex.axis, main = main, xlim = xlim, ylim = ylim)
> 3: charts.ROI(ROI = x, rp = rp, risk.col = risk.col, return.col =
> return.col,
>        chart.assets = chart.assets, main = main, xlim = xlim, ylim = ylim,
>        ...)
> 2: plot.optimize.portfolio.ROI(MeanVar.ROI)
> 1: plot(MeanVar.ROI)
>
> pcc
> --
> Peter Carl
> http://www.braverock.com/peter
>
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130917/4f75e501/attachment-0001.html>

From rossbennett34 at gmail.com  Wed Sep 18 07:46:45 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Tue, 17 Sep 2013 22:46:45 -0700
Subject: [GSoC-PortA] R CMD check info`
In-Reply-To: <cf916f66-61e8-4a37-a34a-877652a9e902@email.android.com>
References: <CAEESW=U_xitGn=TBwcc6C6KqX1=7mzAAcXwDXkETbWc4aJ4phg@mail.gmail.com>
 <cf916f66-61e8-4a37-a34a-877652a9e902@email.android.com>
Message-ID: <CAEESW=Xg0Kh2ZyJssErHo-9MU6ewtVNXigFwsx3PNSUm0BSTpg@mail.gmail.com>

Brian,

See updated log file attached. Only 1 warning for checking package
vignettes in ?inst/doc?, but there is no inst folder.

Ross


On Tue, Sep 17, 2013 at 12:29 PM, Brian G. Peterson <brian at braverock.com>wrote:

> Ross,
>
> We should chase all warnings. I'll take a look at the log.
>
> It looks like R-Forge just fixed their email listserv...
>
> Regards,
>
> Brian
>
> Ross Bennett <rossbennett34 at gmail.com> wrote:
>>
>> Brian and others,
>>
>> I ran R CMD check and I only get 3 warnings and 3 notes. The log file is
>> attached.
>>
>> Under the "checking R code for possible problems", there are several
>> lines with something like "no visible binding for global variable
>> 'strategy' ". Is this something that should be addressed? If so, what is
>> the best way to correct this?
>>
>> On a side note, I have made multiple commits over the last two days, but
>> have not received any [Returnanalytics-commits] emails from r-forge.  The
>> last email I received was for commit r3107 and my latest commit is
>> r3125.Have any of you received the commit emails recently?
>>
>> Thanks,
>> Ross
>>
>> ------------------------------
>>
>> GSoC-PortA mailing list
>> GSoC-PortA at lists.r-forge.r-project.org
>> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>>
>>
> --
> Sent from my Android phone with K-9 Mail. Please excuse my brevity.
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130917/79b14fbf/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 00check.log
Type: application/octet-stream
Size: 5473 bytes
Desc: not available
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130917/79b14fbf/attachment.obj>

From brian at braverock.com  Wed Sep 18 16:54:33 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Wed, 18 Sep 2013 09:54:33 -0500
Subject: [GSoC-PortA] error in demo_efficient_frontier
Message-ID: <5239BEA9.5010909@braverock.com>

I see:

 > # mean-var efficient frontier
 > meanvar.ef <- create.EfficientFrontier(R=R, portfolio=meanvar.portf, 
type="mean-StdDev")
Error in (dir == "<=") | (dir = q = "<") :
   operations are possible only for numeric, logical or complex types
 > traceback()
13: which((dir == "<=") | (dir = q = "<"))
12: .quadprog_solve_QP(Q = terms(objective(x))$Q, L = 
terms(objective(x))$L,
         mat = constraints(x)$L, dir = constraints(x)$dir, rhs = 
constraints(x)$rhs,
         max = x$maximum)
11: SOLVE(x, control)
10: ROI_solve(x = opt.prob, solver = "quadprog")
9: gmv_opt(R = R, constraints = constraints, moments = moments,
        lambda = lambda, target = target, lambda_hhi = lambda_hhi,
        conc_groups = conc_groups)
8: optimize.portfolio(R = R, portfolio = portfolio, optimize_method = "ROI")
7: meanvar.efficient.frontier(portfolio = portfolio, R = R, n.portfolios 
= n.portfolios,
        risk_aversion = risk_aversion)
6: create.EfficientFrontier(R = R, portfolio = meanvar.portf, type = 
"mean-StdDev") at demo_efficient_frontier.R#42
5: eval(expr, envir, enclos)
4: eval(ei, envir)
3: withVisible(eval(ei, envir))
2: source(available, echo = echo, max.deparse.length = Inf, keep.source 
= TRUE,
        encoding = encoding)
1: demo("demo_efficient_frontier", ask = FALSE)

I'm pretty sure this is current code.

Thoughts?

-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock

From rossbennett34 at gmail.com  Wed Sep 18 17:07:24 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Wed, 18 Sep 2013 08:07:24 -0700
Subject: [GSoC-PortA] error in demo_efficient_frontier
In-Reply-To: <5239BEA9.5010909@braverock.com>
References: <5239BEA9.5010909@braverock.com>
Message-ID: <CAEESW=Wv6EtGcT+dtyrwQS+xdyDmY-AFsj197oET4Apv8_iN0A@mail.gmail.com>

Brian,

That is an error with ROI. The ROI.plugin.quadprog version on CRAN is
broken, the version on R-forge works correctly.

Ross


On Wed, Sep 18, 2013 at 7:54 AM, Brian G. Peterson <brian at braverock.com>wrote:

> I see:
>
> > # mean-var efficient frontier
> > meanvar.ef <- create.EfficientFrontier(R=R, portfolio=meanvar.portf,
> type="mean-StdDev")
> Error in (dir == "<=") | (dir = q = "<") :
>   operations are possible only for numeric, logical or complex types
> > traceback()
> 13: which((dir == "<=") | (dir = q = "<"))
> 12: .quadprog_solve_QP(Q = terms(objective(x))$Q, L =
> terms(objective(x))$L,
>         mat = constraints(x)$L, dir = constraints(x)$dir, rhs =
> constraints(x)$rhs,
>         max = x$maximum)
> 11: SOLVE(x, control)
> 10: ROI_solve(x = opt.prob, solver = "quadprog")
> 9: gmv_opt(R = R, constraints = constraints, moments = moments,
>        lambda = lambda, target = target, lambda_hhi = lambda_hhi,
>        conc_groups = conc_groups)
> 8: optimize.portfolio(R = R, portfolio = portfolio, optimize_method =
> "ROI")
> 7: meanvar.efficient.frontier(**portfolio = portfolio, R = R,
> n.portfolios = n.portfolios,
>        risk_aversion = risk_aversion)
> 6: create.EfficientFrontier(R = R, portfolio = meanvar.portf, type =
> "mean-StdDev") at demo_efficient_frontier.R#42
> 5: eval(expr, envir, enclos)
> 4: eval(ei, envir)
> 3: withVisible(eval(ei, envir))
> 2: source(available, echo = echo, max.deparse.length = Inf, keep.source =
> TRUE,
>        encoding = encoding)
> 1: demo("demo_efficient_frontier"**, ask = FALSE)
>
> I'm pretty sure this is current code.
>
> Thoughts?
>
> --
> Brian G. Peterson
> http://braverock.com/brian/
> Ph: 773-459-4973
> IM: bgpbraverock
> ______________________________**_________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-**project.org<GSoC-PortA at lists.r-forge.r-project.org>
> http://lists.r-forge.r-**project.org/cgi-bin/mailman/**listinfo/gsoc-porta<http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130918/9f13743d/attachment.html>

From martinrd at comcast.net  Wed Sep 18 18:01:37 2013
From: martinrd at comcast.net (Doug Martin)
Date: Wed, 18 Sep 2013 09:01:37 -0700
Subject: [GSoC-PortA] error in demo_efficient_frontier
In-Reply-To: <CAEESW=Wv6EtGcT+dtyrwQS+xdyDmY-AFsj197oET4Apv8_iN0A@mail.gmail.com>
References: <5239BEA9.5010909@braverock.com>
 <CAEESW=Wv6EtGcT+dtyrwQS+xdyDmY-AFsj197oET4Apv8_iN0A@mail.gmail.com>
Message-ID: <002a01ceb488$64b46920$2e1d3b60$@comcast.net>

Brian,

 

Do I recall correctly that this is an old problem from last year that
Theussel, etc., was informed about but never fixed?

 

Doug

 

 

From: gsoc-porta-bounces at lists.r-forge.r-project.org
[mailto:gsoc-porta-bounces at lists.r-forge.r-project.org] On Behalf Of Ross
Bennett
Sent: Wednesday, September 18, 2013 8:07 AM
To: PortfolioAnalytics
Subject: Re: [GSoC-PortA] error in demo_efficient_frontier

 

Brian,

 

That is an error with ROI. The ROI.plugin.quadprog version on CRAN is
broken, the version on R-forge works correctly.

 

Ross

 

On Wed, Sep 18, 2013 at 7:54 AM, Brian G. Peterson <brian at braverock.com>
wrote:

I see:

> # mean-var efficient frontier
> meanvar.ef <- create.EfficientFrontier(R=R, portfolio=meanvar.portf,
type="mean-StdDev")
Error in (dir == "<=") | (dir = q = "<") :
  operations are possible only for numeric, logical or complex types
> traceback()
13: which((dir == "<=") | (dir = q = "<"))
12: .quadprog_solve_QP(Q = terms(objective(x))$Q, L = terms(objective(x))$L,
        mat = constraints(x)$L, dir = constraints(x)$dir, rhs =
constraints(x)$rhs,
        max = x$maximum)
11: SOLVE(x, control)
10: ROI_solve(x = opt.prob, solver = "quadprog")
9: gmv_opt(R = R, constraints = constraints, moments = moments,
       lambda = lambda, target = target, lambda_hhi = lambda_hhi,
       conc_groups = conc_groups)
8: optimize.portfolio(R = R, portfolio = portfolio, optimize_method = "ROI")
7: meanvar.efficient.frontier(portfolio = portfolio, R = R, n.portfolios =
n.portfolios,
       risk_aversion = risk_aversion)
6: create.EfficientFrontier(R = R, portfolio = meanvar.portf, type =
"mean-StdDev") at demo_efficient_frontier.R#42
5: eval(expr, envir, enclos)
4: eval(ei, envir)
3: withVisible(eval(ei, envir))
2: source(available, echo = echo, max.deparse.length = Inf, keep.source =
TRUE,
       encoding = encoding)
1: demo("demo_efficient_frontier", ask = FALSE)

I'm pretty sure this is current code.

Thoughts?

-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock
_______________________________________________
GSoC-PortA mailing list
GSoC-PortA at lists.r-forge.r-project.org
http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130918/a51de872/attachment.html>

From brian at braverock.com  Wed Sep 18 18:34:50 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Wed, 18 Sep 2013 11:34:50 -0500
Subject: [GSoC-PortA] error in demo_efficient_frontier
In-Reply-To: <002a01ceb488$64b46920$2e1d3b60$@comcast.net>
References: <5239BEA9.5010909@braverock.com>
 <CAEESW=Wv6EtGcT+dtyrwQS+xdyDmY-AFsj197oET4Apv8_iN0A@mail.gmail.com>
 <002a01ceb488$64b46920$2e1d3b60$@comcast.net>
Message-ID: <5239D62A.5010305@braverock.com>

Thanks Ross.

Fixed but not pushed to CRAN.

I'll open the conversation with Stefan and Kurt about pushing an updated 
version to CRAN.

On 09/18/2013 11:01 AM, Doug Martin wrote:
> Do I recall correctly that this is an old problem from last year that
> Theussel, etc., was informed about but never fixed?
>
> Doug
>
> *From:*gsoc-porta-bounces at lists.r-forge.r-project.org
> [mailto:gsoc-porta-bounces at lists.r-forge.r-project.org] *On Behalf Of
> *Ross Bennett
> *Sent:* Wednesday, September 18, 2013 8:07 AM
> *To:* PortfolioAnalytics
> *Subject:* Re: [GSoC-PortA] error in demo_efficient_frontier
>
> Brian,
>
> That is an error with ROI. The ROI.plugin.quadprog version on CRAN is
> broken, the version on R-forge works correctly.
>


-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock

From martinrd at comcast.net  Wed Sep 18 18:51:24 2013
From: martinrd at comcast.net (Doug Martin)
Date: Wed, 18 Sep 2013 09:51:24 -0700
Subject: [GSoC-PortA] error in demo_efficient_frontier
In-Reply-To: <5239D62A.5010305@braverock.com>
References: <5239BEA9.5010909@braverock.com>
 <CAEESW=Wv6EtGcT+dtyrwQS+xdyDmY-AFsj197oET4Apv8_iN0A@mail.gmail.com>
 <002a01ceb488$64b46920$2e1d3b60$@comcast.net>
 <5239D62A.5010305@braverock.com>
Message-ID: <005301ceb48f$58d15580$0a740080$@comcast.net>

Just a reminder that I will be in Vienna in late October and Bernd is going
to arrange a meeting time with Kurt.

Doug


-----Original Message-----
From: gsoc-porta-bounces at lists.r-forge.r-project.org
[mailto:gsoc-porta-bounces at lists.r-forge.r-project.org] On Behalf Of Brian
G. Peterson
Sent: Wednesday, September 18, 2013 9:35 AM
To: gsoc-porta at r-forge.wu-wien.ac.at
Subject: Re: [GSoC-PortA] error in demo_efficient_frontier

Thanks Ross.

Fixed but not pushed to CRAN.

I'll open the conversation with Stefan and Kurt about pushing an updated
version to CRAN.

On 09/18/2013 11:01 AM, Doug Martin wrote:
> Do I recall correctly that this is an old problem from last year that 
> Theussel, etc., was informed about but never fixed?
>
> Doug
>
> *From:*gsoc-porta-bounces at lists.r-forge.r-project.org
> [mailto:gsoc-porta-bounces at lists.r-forge.r-project.org] *On Behalf Of 
> *Ross Bennett
> *Sent:* Wednesday, September 18, 2013 8:07 AM
> *To:* PortfolioAnalytics
> *Subject:* Re: [GSoC-PortA] error in demo_efficient_frontier
>
> Brian,
>
> That is an error with ROI. The ROI.plugin.quadprog version on CRAN is 
> broken, the version on R-forge works correctly.
>


--
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock
_______________________________________________
GSoC-PortA mailing list
GSoC-PortA at lists.r-forge.r-project.org
http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta


From brian at braverock.com  Wed Sep 18 21:16:53 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Wed, 18 Sep 2013 14:16:53 -0500
Subject: [GSoC-PortA] error in demo_efficient_frontier
In-Reply-To: <CAEESW=Wv6EtGcT+dtyrwQS+xdyDmY-AFsj197oET4Apv8_iN0A@mail.gmail.com>
References: <5239BEA9.5010909@braverock.com>
 <CAEESW=Wv6EtGcT+dtyrwQS+xdyDmY-AFsj197oET4Apv8_iN0A@mail.gmail.com>
Message-ID: <5239FC25.6040502@braverock.com>

On 09/18/2013 10:07 AM, Ross Bennett wrote:
> That is an error with ROI. The ROI.plugin.quadprog version on CRAN is
> broken, the version on R-forge works correctly.
>

That was it, thanks.  I'm not sure why I had the CRAN version of that 
one on this machine...

We should update the Suggests to have the correct version of 
ROI.plugin.quadprog, so that the user will get a warning at install time 
or a failure at check time.

Regards,
-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock

From rossbennett34 at gmail.com  Wed Sep 18 23:05:40 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Wed, 18 Sep 2013 14:05:40 -0700
Subject: [GSoC-PortA] error in demo_efficient_frontier
In-Reply-To: <5239FC25.6040502@braverock.com>
References: <5239BEA9.5010909@braverock.com>
 <CAEESW=Wv6EtGcT+dtyrwQS+xdyDmY-AFsj197oET4Apv8_iN0A@mail.gmail.com>
 <5239FC25.6040502@braverock.com>
Message-ID: <CAEESW=XMd+ry+7ig8XmiSG1nPhxQPh9r+2C2omC9z229T-pAiQ@mail.gmail.com>

Got it. I just made a commit to update the suggests for
ROI.plugin.quadprog. The CRAN versions of ROI and ROI.plugin.glpk are
working correctly with the package.

Thanks,
Ross


On Wed, Sep 18, 2013 at 12:16 PM, Brian G. Peterson <brian at braverock.com>wrote:

> On 09/18/2013 10:07 AM, Ross Bennett wrote:
>
>> That is an error with ROI. The ROI.plugin.quadprog version on CRAN is
>> broken, the version on R-forge works correctly.
>>
>>
> That was it, thanks.  I'm not sure why I had the CRAN version of that one
> on this machine...
>
> We should update the Suggests to have the correct version of
> ROI.plugin.quadprog, so that the user will get a warning at install time or
> a failure at check time.
>
> Regards,
>
> --
> Brian G. Peterson
> http://braverock.com/brian/
> Ph: 773-459-4973
> IM: bgpbraverock
> ______________________________**_________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-**project.org<GSoC-PortA at lists.r-forge.r-project.org>
> http://lists.r-forge.r-**project.org/cgi-bin/mailman/**listinfo/gsoc-porta<http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130918/c64cdc91/attachment.html>

From rossbennett34 at gmail.com  Wed Sep 18 23:38:30 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Wed, 18 Sep 2013 14:38:30 -0700
Subject: [GSoC-PortA] Portfolio Vignette
Message-ID: <CAEESW=Vz=K6fO5m1Mn2RoCKO-5fYhhvCiR7Mp2M1FRWe+VyZWw@mail.gmail.com>

All,

In commit r3130, I added a lot of content and charts to the
portfolio_vignette. I'm still working on the placement and formatting of
some of the charts, but overall I think this is a pretty good introduction
to specify the portfolio object, add constraints and objectives, and run a
few example optimizations.

If anyone has a chance to read through it, I would appreciate any and all
feedback about existing content or any content that should be added.

The compiled pdf is in the vignettes folder as portfolio_vignette.pdf.

Thanks,
Ross
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130918/433c42ec/attachment.html>

From brian at braverock.com  Thu Sep 19 11:20:21 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Thu, 19 Sep 2013 04:20:21 -0500
Subject: [GSoC-PortA] Portfolio Vignette
In-Reply-To: <CAEESW=Vz=K6fO5m1Mn2RoCKO-5fYhhvCiR7Mp2M1FRWe+VyZWw@mail.gmail.com>
References: <CAEESW=Vz=K6fO5m1Mn2RoCKO-5fYhhvCiR7Mp2M1FRWe+VyZWw@mail.gmail.com>
Message-ID: <523AC1D5.1000208@braverock.com>

On 09/18/2013 04:38 PM, Ross Bennett wrote:
> All,
>
> In commit r3130, I added a lot of content and charts to the
> portfolio_vignette. I'm still working on the placement and formatting of
> some of the charts, but overall I think this is a pretty good
> introduction to specify the portfolio object, add constraints and
> objectives, and run a few example optimizations.
>
> If anyone has a chance to read through it, I would appreciate any and
> all feedback about existing content or any content that should be added.
>
> The compiled pdf is in the vignettes folder as portfolio_vignette.pdf.

Ross,

Thanks for doing this, it's looking very good.

I'm impressed by the comparison of the different random portfolio 
methods.  It's pretty clear that at fev=0.05 the simplex method will 
concentrate more towards the individual assets while the sample method 
will get a more even distribution in the interior and near the edges. 
It's key to note that depending on your objective, you may very well not 
have an optimal solution along the vertexes.  For example, risk 
contribution or risk budget objectives will likely place the optimal 
portfolio somewhere in the interior.  The min-ERC portfolio lies along a 
line between the minimum variance portfolio and the EW portfolio.

I wonder why you're using all the page space you are to separate the 
weights plot from the scatter plot.  Maybe once to demonstrate that they 
are separate functions, but it seems that when you want to display both 
right next to each other, just calling plot() on the output of 
optimize.portfolio would be s more efficient use of space.  e.g. Fig 
4/5, 6/7, 8/9, 10/11, 12/13, 15/16 etc.

I also wonder if most of section 5.2 could be separated into a separate 
vignette specifically discussing the different methods of doing random 
portfolios, the algorithms themselves, and more completely describing 
the differences, but that can always happen after GSoC.




-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock

From peter at braverock.com  Thu Sep 19 15:58:57 2013
From: peter at braverock.com (=?utf-8?B?UGV0ZXIgQ2FybA==?=)
Date: Thu, 19 Sep 2013 08:58:57 -0500
Subject: [GSoC-PortA] =?utf-8?q?Portfolio_Vignette?=
Message-ID: <201309191358.r8JDwflh006753@ethos.braverock.com>

Ross, this looks fantastic.  I'll follow up with some thoughts, but I think this is very impressive overall.  You've had a great summer! pcc

Sent from my HTC Inspire? 4G on AT&T

----- Reply message -----
From: "Brian G. Peterson" <brian at braverock.com>
To: "PortfolioAnalytics" <gsoc-porta at r-forge.wu-wien.ac.at>
Subject: [GSoC-PortA] Portfolio Vignette
Date: Thu, Sep 19, 2013 4:20 am


On 09/18/2013 04:38 PM, Ross Bennett wrote:
> All,
>
> In commit r3130, I added a lot of content and charts to the
> portfolio_vignette. I'm still working on the placement and formatting of
> some of the charts, but overall I think this is a pretty good
> introduction to specify the portfolio object, add constraints and
> objectives, and run a few example optimizations.
>
> If anyone has a chance to read through it, I would appreciate any and
> all feedback about existing content or any content that should be added.
>
> The compiled pdf is in the vignettes folder as portfolio_vignette.pdf.

Ross,

Thanks for doing this, it's looking very good.

I'm impressed by the comparison of the different random portfolio 
methods.  It's pretty clear that at fev=0.05 the simplex method will 
concentrate more towards the individual assets while the sample method 
will get a more even distribution in the interior and near the edges. 
It's key to note that depending on your objective, you may very well not 
have an optimal solution along the vertexes.  For example, risk 
contribution or risk budget objectives will likely place the optimal 
portfolio somewhere in the interior.  The min-ERC portfolio lies along a 
line between the minimum variance portfolio and the EW portfolio.

I wonder why you're using all the page space you are to separate the 
weights plot from the scatter plot.  Maybe once to demonstrate that they 
are separate functions, but it seems that when you want to display both 
right next to each other, just calling plot() on the output of 
optimize.portfolio would be s more efficient use of space.  e.g. Fig 
4/5, 6/7, 8/9, 10/11, 12/13, 15/16 etc.

I also wonder if most of section 5.2 could be separated into a separate 
vignette specifically discussing the different methods of doing random 
portfolios, the algorithms themselves, and more completely describing 
the differences, but that can always happen after GSoC.




-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock
_______________________________________________
GSoC-PortA mailing list
GSoC-PortA at lists.r-forge.r-project.org
http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130919/71a02035/attachment.html>

From rossbennett34 at gmail.com  Thu Sep 19 17:43:06 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Thu, 19 Sep 2013 08:43:06 -0700
Subject: [GSoC-PortA] Portfolio Vignette
In-Reply-To: <523AC1D5.1000208@braverock.com>
References: <CAEESW=Vz=K6fO5m1Mn2RoCKO-5fYhhvCiR7Mp2M1FRWe+VyZWw@mail.gmail.com>
 <523AC1D5.1000208@braverock.com>
Message-ID: <CAEESW=UZAj5bb+NNiKVEyb1w6tj5T8-q3tyd=dWAezM3kukSFA@mail.gmail.com>

On Thu, Sep 19, 2013 at 2:20 AM, Brian G. Peterson <brian at braverock.com>wrote:
>
>
> Ross,
>
> Thanks for doing this, it's looking very good.
>
> I'm impressed by the comparison of the different random portfolio methods.
>  It's pretty clear that at fev=0.05 the simplex method will concentrate
> more towards the individual assets while the sample method will get a more
> even distribution in the interior and near the edges. It's key to note that
> depending on your objective, you may very well not have an optimal solution
> along the vertexes.  For example, risk contribution or risk budget
> objectives will likely place the optimal portfolio somewhere in the
> interior.  The min-ERC portfolio lies along a line between the minimum
> variance portfolio and the EW portfolio.
>

Agreed, I think it is very interesting to look at the feasible space with
different values for the fev biasing. Good point about the portfolios with
risk budget objectives being on the interior. I'll add that to the vignette.


>
> I wonder why you're using all the page space you are to separate the
> weights plot from the scatter plot.  Maybe once to demonstrate that they
> are separate functions, but it seems that when you want to display both
> right next to each other, just calling plot() on the output of
> optimize.portfolio would be s more efficient use of space.  e.g. Fig 4/5,
> 6/7, 8/9, 10/11, 12/13, 15/16 etc.
>

I did it once to show that they can be plotted separately, but then got a
little carried away with copy/paste. I'll edit and just use the plot
function.


>
> I also wonder if most of section 5.2 could be separated into a separate
> vignette specifically discussing the different methods of doing random
> portfolios, the algorithms themselves, and more completely describing the
> differences, but that can always happen after GSoC.


This would be interesting to expand on the material in this section
including some benchmarking, looking at different constraints, impact of
handling constraints by elimination, etc.

Thanks,
Ross


>
>
>
>
>
> --
> Brian G. Peterson
> http://braverock.com/brian/
> Ph: 773-459-4973
> IM: bgpbraverock
> ______________________________**_________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-**project.org<GSoC-PortA at lists.r-forge.r-project.org>
> http://lists.r-forge.r-**project.org/cgi-bin/mailman/**listinfo/gsoc-porta<http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130919/a38facf7/attachment.html>

From peter at braverock.com  Mon Sep 23 01:41:35 2013
From: peter at braverock.com (Peter Carl)
Date: Sun, 22 Sep 2013 18:41:35 -0500
Subject: [GSoC-PortA] Some feedback...
Message-ID: <6077558330b1a022003470c2092bae1b.squirrel@mail.braverock.com>

Ross,

I've been working through your vignette to hopefully give you some more
detailed feedback, including on your questions from a few days ago.  Sorry
this has taken so long, but I wanted to spend some focused time on the
package.

I realize that you've got different plot methods for each type, and I
appreciate what a hassle it is to keep such methods relatively consistent.
 In chart.RiskReturn.DE, when the function doesn't find anything that fits
its defaults:
> plot(RiskBudget.DE)
Error in plot.window(...) : need finite 'xlim' values
In addition: Warning messages:
1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
return.col,  :
  mean or ES do  not match extractStats output of $objective_measures slot
2: In min(x) : no non-missing arguments to min; returning Inf
3: In max(x) : no non-missing arguments to max; returning -Inf

It's a risk budget on ETL, so if I tell it that, it works:
> plot(RiskBudget.DE, risk.col="ETL", return.col="mean")

...but it doesn't recover well when I try to plot the results in variance
space:
> plot(RiskBudget.DE, risk.col="StdDev", return.col="mean")
Error in plot.window(...) : need finite 'xlim' values
In addition: Warning messages:
1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
return.col,  :
  mean or StdDev do  not match extractStats output of $objective_measures
slot
2: In min(x) : no non-missing arguments to min; returning Inf
3: In max(x) : no non-missing arguments to max; returning -Inf


I'm not exactly sure what the issue is here, but maybe it's related:
> chart.RiskBudget(RiskBudget.DE, risk.type="percentage", neighbors=5)
Error in subsetx[i, riskcols] : incorrect number of dimensions
> traceback()
3: points(subsetx[i, riskcols], type = "b", col = "lightblue")
2: chart.RiskBudget.optimize.portfolio(RiskBudget.DE, risk.type =
"percentage",
       neighbors = 5)
1: chart.RiskBudget(RiskBudget.DE, risk.type = "percentage", neighbors = 5)

In chart.RiskReturnScatter.RP, it looks like 'rp' is being passed into
plot through dots.
> plot(EqmETL.RND, risk.col="StdDev", return.col="mean", rp=1000,
chart.assets=TRUE)
There were 13 warnings (use warnings() to see them)
> warnings()
Warning messages:
1: "rp" is not a graphical parameter
2: "rp" is not a graphical parameter
3: "rp" is not a graphical parameter


> extractWeights(buoys)
         Convertible Arbitrage Equity Market Neutral Fixed Income
Arbitrage Event Driven CTA Global Global Macro Long/Short Equity
MeanSD              0.05000000                 0.050                 
0.050   0.30000000  0.0500000    0.2000000             0.300
MeanmETL            0.05000000                 0.300                 
0.050   0.05000000  0.2000000    0.3000000             0.050
MinSD               0.06042904                 0.300                 
0.300   0.05234676  0.1735858    0.0636384             0.050
MinmETL             0.05000000                 0.300                 
0.050   0.05000000  0.2000000    0.3000000             0.050
EqSD                0.12500000                 0.240                 
0.200   0.08500000  0.1050000    0.1700000             0.075
EqmETL              0.06000000                 0.265                 
0.165   0.09000000  0.2050000    0.1300000             0.080
RB                  0.05200000                 0.410                 
0.060   0.05200000  0.1438995    0.2220000             0.058

...but this doesn't:
> extractObjectiveMeasures(buoys)
                mean     StdDev         ES StdDev.contribution1
StdDev.contribution2 StdDev.contribution3
StdDev.contribution4
MeanSD   0.006782814 0.01546759         NA                   NA           
       NA                   NA                   NA
MeanmETL 0.005897789         NA 0.01505626                   NA           
       NA                   NA                   NA
MinSD             NA 0.01009001         NA                   NA           
       NA                   NA                   NA
MinmETL           NA         NA 0.01505626                   NA           
       NA                   NA                   NA
EqSD              NA 0.01113716         NA          0.001763096         
0.001565752          0.001886988          0.001258567
EqmETL            NA         NA 0.01646509                   NA           
       NA                   NA                   NA
RB       0.005812997         NA         NA                   NA           
       NA                   NA                   NA
         StdDev.contribution5 StdDev.contribution6 StdDev.contribution7
StdDev.pct_contrib_StdDev1 StdDev.pct_contrib_StdDev2
MeanSD                     NA                   NA                   NA   
                     NA                         NA
MeanmETL                   NA                   NA                   NA   
                     NA                         NA
MinSD                      NA                   NA                   NA   
                     NA                         NA
MinmETL                    NA                   NA                   NA   
                     NA                         NA
EqSD              0.001039908          0.002296903          0.001325947   
              0.1583075                  0.1405881
EqmETL                     NA                   NA                   NA   
                     NA                         NA
RB                         NA                   NA                   NA   
                     NA                         NA
...snip...

As a consequence, only one portfolio appears in the following plot (MeanSD):
> chart.RiskReward(buoys)

All in all, this is all looking good.  I've got some scripts checked in
under sandbox/symposium2013 if you want to follow along.

pcc
-- 
Peter Carl
http://www.braverock.com/peter



From peter at braverock.com  Mon Sep 23 01:46:21 2013
From: peter at braverock.com (Peter Carl)
Date: Sun, 22 Sep 2013 18:46:21 -0500
Subject: [GSoC-PortA] Some feedback...
In-Reply-To: <6077558330b1a022003470c2092bae1b.squirrel@mail.braverock.com>
References: <6077558330b1a022003470c2092bae1b.squirrel@mail.braverock.com>
Message-ID: <dddf4a88eda5db709eba6783b81e4204.squirrel@mail.braverock.com>

Sorry, prior to the
> extractWeights(buoys)
line below, I should have said that combining the portfolios isn't quite
going smoothly yet.

I can get the weights out fine...
(as shown)
...but not the objective measures
(as shown).

pcc
-- 
Peter Carl
http://www.braverock.com/peter

> Ross,
>
> I've been working through your vignette to hopefully give you some more
> detailed feedback, including on your questions from a few days ago.  Sorry
> this has taken so long, but I wanted to spend some focused time on the
> package.
>
> I realize that you've got different plot methods for each type, and I
> appreciate what a hassle it is to keep such methods relatively consistent.
>  In chart.RiskReturn.DE, when the function doesn't find anything that fits
> its defaults:
>> plot(RiskBudget.DE)
> Error in plot.window(...) : need finite 'xlim' values
> In addition: Warning messages:
> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
> return.col,  :
>   mean or ES do  not match extractStats output of $objective_measures slot
> 2: In min(x) : no non-missing arguments to min; returning Inf
> 3: In max(x) : no non-missing arguments to max; returning -Inf
>
> It's a risk budget on ETL, so if I tell it that, it works:
>> plot(RiskBudget.DE, risk.col="ETL", return.col="mean")
>
> ...but it doesn't recover well when I try to plot the results in variance
> space:
>> plot(RiskBudget.DE, risk.col="StdDev", return.col="mean")
> Error in plot.window(...) : need finite 'xlim' values
> In addition: Warning messages:
> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
> return.col,  :
>   mean or StdDev do  not match extractStats output of $objective_measures
> slot
> 2: In min(x) : no non-missing arguments to min; returning Inf
> 3: In max(x) : no non-missing arguments to max; returning -Inf
>
>
> I'm not exactly sure what the issue is here, but maybe it's related:
>> chart.RiskBudget(RiskBudget.DE, risk.type="percentage", neighbors=5)
> Error in subsetx[i, riskcols] : incorrect number of dimensions
>> traceback()
> 3: points(subsetx[i, riskcols], type = "b", col = "lightblue")
> 2: chart.RiskBudget.optimize.portfolio(RiskBudget.DE, risk.type =
> "percentage",
>        neighbors = 5)
> 1: chart.RiskBudget(RiskBudget.DE, risk.type = "percentage", neighbors =
> 5)
>
> In chart.RiskReturnScatter.RP, it looks like 'rp' is being passed into
> plot through dots.
>> plot(EqmETL.RND, risk.col="StdDev", return.col="mean", rp=1000,
> chart.assets=TRUE)
> There were 13 warnings (use warnings() to see them)
>> warnings()
> Warning messages:
> 1: "rp" is not a graphical parameter
> 2: "rp" is not a graphical parameter
> 3: "rp" is not a graphical parameter
>
>
>> extractWeights(buoys)
>          Convertible Arbitrage Equity Market Neutral Fixed Income
> Arbitrage Event Driven CTA Global Global Macro Long/Short Equity
> MeanSD              0.05000000                 0.050
> 0.050   0.30000000  0.0500000    0.2000000             0.300
> MeanmETL            0.05000000                 0.300
> 0.050   0.05000000  0.2000000    0.3000000             0.050
> MinSD               0.06042904                 0.300
> 0.300   0.05234676  0.1735858    0.0636384             0.050
> MinmETL             0.05000000                 0.300
> 0.050   0.05000000  0.2000000    0.3000000             0.050
> EqSD                0.12500000                 0.240
> 0.200   0.08500000  0.1050000    0.1700000             0.075
> EqmETL              0.06000000                 0.265
> 0.165   0.09000000  0.2050000    0.1300000             0.080
> RB                  0.05200000                 0.410
> 0.060   0.05200000  0.1438995    0.2220000             0.058
>
> ...but this doesn't:
>> extractObjectiveMeasures(buoys)
>                 mean     StdDev         ES StdDev.contribution1
> StdDev.contribution2 StdDev.contribution3
> StdDev.contribution4
> MeanSD   0.006782814 0.01546759         NA                   NA
>        NA                   NA                   NA
> MeanmETL 0.005897789         NA 0.01505626                   NA
>        NA                   NA                   NA
> MinSD             NA 0.01009001         NA                   NA
>        NA                   NA                   NA
> MinmETL           NA         NA 0.01505626                   NA
>        NA                   NA                   NA
> EqSD              NA 0.01113716         NA          0.001763096
> 0.001565752          0.001886988          0.001258567
> EqmETL            NA         NA 0.01646509                   NA
>        NA                   NA                   NA
> RB       0.005812997         NA         NA                   NA
>        NA                   NA                   NA
>          StdDev.contribution5 StdDev.contribution6 StdDev.contribution7
> StdDev.pct_contrib_StdDev1 StdDev.pct_contrib_StdDev2
> MeanSD                     NA                   NA                   NA
>                      NA                         NA
> MeanmETL                   NA                   NA                   NA
>                      NA                         NA
> MinSD                      NA                   NA                   NA
>                      NA                         NA
> MinmETL                    NA                   NA                   NA
>                      NA                         NA
> EqSD              0.001039908          0.002296903          0.001325947
>               0.1583075                  0.1405881
> EqmETL                     NA                   NA                   NA
>                      NA                         NA
> RB                         NA                   NA                   NA
>                      NA                         NA
> ...snip...
>
> As a consequence, only one portfolio appears in the following plot
> (MeanSD):
>> chart.RiskReward(buoys)
>
> All in all, this is all looking good.  I've got some scripts checked in
> under sandbox/symposium2013 if you want to follow along.
>
> pcc
> --
> Peter Carl
> http://www.braverock.com/peter
>
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>


From rossbennett34 at gmail.com  Mon Sep 23 03:16:12 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Sun, 22 Sep 2013 18:16:12 -0700
Subject: [GSoC-PortA] Some feedback...
In-Reply-To: <6077558330b1a022003470c2092bae1b.squirrel@mail.braverock.com>
References: <6077558330b1a022003470c2092bae1b.squirrel@mail.braverock.com>
Message-ID: <CAEESW=Vnm=gdrW-ZrNcs75PDMHjKQnoWjcQbbCXNvPtKyag6=A@mail.gmail.com>

Peter,

Thanks for the feedback, I really appreciate it.

see comments in line.


On Sun, Sep 22, 2013 at 4:41 PM, Peter Carl <peter at braverock.com> wrote:

> Ross,
>
> I've been working through your vignette to hopefully give you some more
> detailed feedback, including on your questions from a few days ago.  Sorry
> this has taken so long, but I wanted to spend some focused time on the
> package.
>
> I realize that you've got different plot methods for each type, and I
> appreciate what a hassle it is to keep such methods relatively consistent.
>  In chart.RiskReturn.DE, when the function doesn't find anything that fits
> its defaults:
> > plot(RiskBudget.DE)
> Error in plot.window(...) : need finite 'xlim' values
> In addition: Warning messages:
> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
> return.col,  :
>   mean or ES do  not match extractStats output of $objective_measures slot
> 2: In min(x) : no non-missing arguments to min; returning Inf
> 3: In max(x) : no non-missing arguments to max; returning -Inf
>
> It's a risk budget on ETL, so if I tell it that, it works:
> > plot(RiskBudget.DE, risk.col="ETL", return.col="mean")
>

The default is risk.col="ES". Because your objective name is "ETL", you
need to explicitly do risk.col="ETL".


>
> ...but it doesn't recover well when I try to plot the results in variance
> space:
> > plot(RiskBudget.DE, risk.col="StdDev", return.col="mean")
> Error in plot.window(...) : need finite 'xlim' values
> In addition: Warning messages:
> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
> return.col,  :
>   mean or StdDev do  not match extractStats output of $objective_measures
> slot
> 2: In min(x) : no non-missing arguments to min; returning Inf
> 3: In max(x) : no non-missing arguments to max; returning -Inf
>
>
> I'm not exactly sure what the issue is here, but maybe it's related:
> > chart.RiskBudget(RiskBudget.DE, risk.type="percentage", neighbors=5)
> Error in subsetx[i, riskcols] : incorrect number of dimensions
> > traceback()
> 3: points(subsetx[i, riskcols], type = "b", col = "lightblue")
> 2: chart.RiskBudget.optimize.portfolio(RiskBudget.DE, risk.type =
> "percentage",
>        neighbors = 5)
> 1: chart.RiskBudget(RiskBudget.DE, risk.type = "percentage", neighbors = 5)
>

Not sure either what the issue is, but I'll take a look.


> In chart.RiskReturnScatter.RP, it looks like 'rp' is being passed into
> plot through dots.
> > plot(EqmETL.RND, risk.col="StdDev", return.col="mean", rp=1000,
> chart.assets=TRUE)
> There were 13 warnings (use warnings() to see them)
> > warnings()
> Warning messages:
> 1: "rp" is not a graphical parameter
> 2: "rp" is not a graphical parameter
> 3: "rp" is not a graphical parameter
>

The 'rp' argument is meant for optimize.portfolio.ROI and
optimize.portfolio.GenSA objects. Since ROI and GenSA do not return trace
information like DEoptim or random portfolios, I added this as an option to
generate random portfolios to plot the feasible space. If you are already
passing in an optimize.portfolio.random object, there is no need to pass in
rp as an argument.


>
>
> > extractWeights(buoys)
>          Convertible Arbitrage Equity Market Neutral Fixed Income
> Arbitrage Event Driven CTA Global Global Macro Long/Short Equity
> MeanSD              0.05000000                 0.050
> 0.050   0.30000000  0.0500000    0.2000000             0.300
> MeanmETL            0.05000000                 0.300
> 0.050   0.05000000  0.2000000    0.3000000             0.050
> MinSD               0.06042904                 0.300
> 0.300   0.05234676  0.1735858    0.0636384             0.050
> MinmETL             0.05000000                 0.300
> 0.050   0.05000000  0.2000000    0.3000000             0.050
> EqSD                0.12500000                 0.240
> 0.200   0.08500000  0.1050000    0.1700000             0.075
> EqmETL              0.06000000                 0.265
> 0.165   0.09000000  0.2050000    0.1300000             0.080
> RB                  0.05200000                 0.410
> 0.060   0.05200000  0.1438995    0.2220000             0.058
>
> ...but this doesn't:
> > extractObjectiveMeasures(buoys)
>                 mean     StdDev         ES StdDev.contribution1
> StdDev.contribution2 StdDev.contribution3
> StdDev.contribution4
> MeanSD   0.006782814 0.01546759         NA                   NA
>        NA                   NA                   NA
> MeanmETL 0.005897789         NA 0.01505626                   NA
>        NA                   NA                   NA
> MinSD             NA 0.01009001         NA                   NA
>        NA                   NA                   NA
> MinmETL           NA         NA 0.01505626                   NA
>        NA                   NA                   NA
> EqSD              NA 0.01113716         NA          0.001763096
> 0.001565752          0.001886988          0.001258567
> EqmETL            NA         NA 0.01646509                   NA
>        NA                   NA                   NA
> RB       0.005812997         NA         NA                   NA
>        NA                   NA                   NA
>          StdDev.contribution5 StdDev.contribution6 StdDev.contribution7
> StdDev.pct_contrib_StdDev1 StdDev.pct_contrib_StdDev2
> MeanSD                     NA                   NA                   NA
>                      NA                         NA
> MeanmETL                   NA                   NA                   NA
>                      NA                         NA
> MinSD                      NA                   NA                   NA
>                      NA                         NA
> MinmETL                    NA                   NA                   NA
>                      NA                         NA
> EqSD              0.001039908          0.002296903          0.001325947
>               0.1583075                  0.1405881
> EqmETL                     NA                   NA                   NA
>                      NA                         NA
> RB                         NA                   NA                   NA
>                      NA                         NA
> ...snip...
>
>
It is tough to tell with the formatting on the email, but I'll take a
closer look at the script in the sandbox to see if I can tell what is going
on. The idea is that extractObjectiveMeasures will return a matrix of the
objective measures for all optimize.portfolio objects in the opt.list
object. For example, the meanSD row should have NAs under the ETL and ETL
component contribution columns. I am only stitching together the objective
measures, I do not re-calculate StdDev or component StdDev for the
portfolios with ETL as an objective. Basically, I just take whatever
objectives are in the $objective_measures slot of each optimize.portfolio
object. Should I be doing something such that all cells in the matrix have
values?


> As a consequence, only one portfolio appears in the following plot
> (MeanSD):
> > chart.RiskReward(buoys)
>

This relates to my comment above about how I am not recalculating anything.
Before the portfolios are plotted in risk-return space, I omit rows that
have NA values. For example, if you wanted to plot all the portfolios in
mean-ETL space, all portfolios should have mean and ETL as an objective.
You could set the multiplier to 0 so it does not affect the optimization,
but is returned in the $objective_measures slot.


>
> All in all, this is all looking good.  I've got some scripts checked in
> under sandbox/symposium2013 if you want to follow along.
>

I'll take a closer look and follow along, thanks!


>
> pcc
> --
> Peter Carl
> http://www.braverock.com/peter
>
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130922/1b0fafe8/attachment-0001.html>

From peter at braverock.com  Mon Sep 23 04:18:56 2013
From: peter at braverock.com (Peter Carl)
Date: Sun, 22 Sep 2013 21:18:56 -0500
Subject: [GSoC-PortA] RP issue?
Message-ID: <3c8573bd96cbcd6186f9060240b05a7d.squirrel@mail.braverock.com>

Ok, I'm now up to revision 3170.

### Construct BUOY 5: Constrained Equal Variance Contribution Portfolio -
using RP
EqSD.portf <- add.objective(portfolio=init.portf,
                            type="risk_budget",
                            name="StdDev",
                            enabled=TRUE,
                            min_concentration=TRUE,
                            arguments = list(p=(1-1/12), clean=clean)
                            )
# Without a sub-objective, we get a somewhat undefined result, since there
are (potentially) many Equal SD contribution portfolios.
EqSD.portf <- add.objective(portfolio=EqSD.portf,
                            type="risk",
                            name="StdDev"
                            )
EqSD.portf$constraints[[1]]$min_sum = 0.99 # set to speed up RP
EqSD.portf$constraints[[1]]$max_sum = 1.01


Now I'm evaluating it:
> EqSD.RND<-optimize.portfolio(R=R,
+   portfolio=EqSD.portf,
+   optimize_method='random',
+   search_size=1000, trace=TRUE
+   )
Warning message:
In constrained_objective(w = min_objective_weights, R = R, portfolio =
portfolio,  :
  some arguments stored for StdDev do not match

I'm not sure why I'd get that warning... or maybe I'm not understanding
the meaning of the message.

> plot(EqSD.RND, risk.col="StdDev", return.col="mean", rp=permutations,
chart.assets=TRUE, main="Equal Volatility Contribution Portfolio")
There were 13 warnings (use warnings() to see them)
> warnings()
Warning messages:
1: In chart.Scatter.RP(object = RP, risk.col = risk.col,  ... :
  mean or StdDev do  not match extractStats output of $objective_measures
slot

That's probably a repeat of the above message.

Then this chart broke:

> chart.RiskBudget(EqSD.RND)
Error in contrib[[idx[ii]]] : attempt to select less than one element

Thanks,

pcc
-- 
Peter Carl
http://www.braverock.com/peter



From rossbennett34 at gmail.com  Mon Sep 23 08:37:20 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Sun, 22 Sep 2013 23:37:20 -0700
Subject: [GSoC-PortA] RP issue?
In-Reply-To: <3c8573bd96cbcd6186f9060240b05a7d.squirrel@mail.braverock.com>
References: <3c8573bd96cbcd6186f9060240b05a7d.squirrel@mail.braverock.com>
Message-ID: <CAEESW=WfGuF-xR3obfHGnUWGBTj8E8esTJBzqZ--FJ6OtzXDeA@mail.gmail.com>

Peter,

See comments in line


On Sun, Sep 22, 2013 at 7:18 PM, Peter Carl <peter at braverock.com> wrote:

> Ok, I'm now up to revision 3170.
>
> ### Construct BUOY 5: Constrained Equal Variance Contribution Portfolio -
> using RP
> EqSD.portf <- add.objective(portfolio=init.portf,
>                             type="risk_budget",
>                             name="StdDev",
>                             enabled=TRUE,
>                             min_concentration=TRUE,
>                             arguments = list(p=(1-1/12), clean=clean)
>                             )
> # Without a sub-objective, we get a somewhat undefined result, since there
> are (potentially) many Equal SD contribution portfolios.
> EqSD.portf <- add.objective(portfolio=EqSD.portf,
>                             type="risk",
>                             name="StdDev"
>                             )
> EqSD.portf$constraints[[1]]$min_sum = 0.99 # set to speed up RP
> EqSD.portf$constraints[[1]]$max_sum = 1.01
>
>
> Now I'm evaluating it:
> > EqSD.RND<-optimize.portfolio(R=R,
> +   portfolio=EqSD.portf,
> +   optimize_method='random',
> +   search_size=1000, trace=TRUE
> +   )
> Warning message:
> In constrained_objective(w = min_objective_weights, R = R, portfolio =
> portfolio,  :
>   some arguments stored for StdDev do not match
>
> I'm not sure why I'd get that warning... or maybe I'm not understanding
> the meaning of the message.
>

I believe you are getting that warning because p is not a formal argument
for StdDev.


>
> > plot(EqSD.RND, risk.col="StdDev", return.col="mean", rp=permutations,
> chart.assets=TRUE, main="Equal Volatility Contribution Portfolio")
> There were 13 warnings (use warnings() to see them)
> > warnings()
> Warning messages:
> 1: In chart.Scatter.RP(object = RP, risk.col = risk.col,  ... :
>   mean or StdDev do  not match extractStats output of $objective_measures
> slot
>

You are getting this message because mean is not an objective, so we are
calculating mean to plot in mean-StdDev space.


>
> That's probably a repeat of the above message.
>
> Then this chart broke:
>
> > chart.RiskBudget(EqSD.RND)
> Error in contrib[[idx[ii]]] : attempt to select less than one element
>

I ran the script and noticed that EqSD.RND does not have the component
StdDev in the $objective_measures slot. I'm not sure why this is, but I'll
look into it tomorrow.


>
> Thanks,
>
> pcc
> --
> Peter Carl
> http://www.braverock.com/peter
>
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130922/b9f9616a/attachment.html>

From rossbennett34 at gmail.com  Mon Sep 23 16:32:48 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Mon, 23 Sep 2013 07:32:48 -0700
Subject: [GSoC-PortA] Odd Behavior Depending on Order of Objectives
Message-ID: <CAEESW=V9UNqDouSEpn3ktWiWKPrcP9mPQ=R24hFLCAf-wwxiqw@mail.gmail.com>

All,

After running Peter's script in the sandbox/symposium2013, I noticed that
portfolio component ES and component StdDev were not being returned in the
$objective_measures slot.

I did some testing and it appears that if a "risk" objective is added after
a "risk_budget" objective with the same name (e.g. "ES" or "StdDev"), the
portfolio component contribution is not returned. This seems odd to me
because constrained_objective loops through the objectives and calculates
each one separately.

I attached an example script to demonstrate this.

Any thoughts on what is going on here?

Thanks,
Ross
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130923/87948c3b/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: objective_order.R
Type: application/octet-stream
Size: 1145 bytes
Desc: not available
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130923/87948c3b/attachment.obj>

From brian at braverock.com  Mon Sep 23 16:38:34 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Mon, 23 Sep 2013 09:38:34 -0500
Subject: [GSoC-PortA] Odd Behavior Depending on Order of Objectives
In-Reply-To: <CAEESW=V9UNqDouSEpn3ktWiWKPrcP9mPQ=R24hFLCAf-wwxiqw@mail.gmail.com>
References: <CAEESW=V9UNqDouSEpn3ktWiWKPrcP9mPQ=R24hFLCAf-wwxiqw@mail.gmail.com>
Message-ID: <5240526A.1070403@braverock.com>

On 09/23/2013 09:32 AM, Ross Bennett wrote:
> After running Peter's script in the sandbox/symposium2013, I noticed
> that portfolio component ES and component StdDev were not being returned
> in the $objective_measures slot.
>
> I did some testing and it appears that if a "risk" objective is added
> after a "risk_budget" objective with the same name (e.g. "ES" or
> "StdDev"), the portfolio component contribution is not returned. This
> seems odd to me because constrained_objective loops through the
> objectives and calculates each one separately.
>
> I attached an example script to demonstrate this.
>
> Any thoughts on what is going on here?

The returned object is a named list.

As such, the second objective with the same name overwrites the first. 
Both are calculated, but only one will get written.

Dealing with this could be tricky.

On the one hand, the component risk measures *do* calculate the 
univariate portfolio risk too.  So if we know that they have the same 
name, we can just get the correct info from the slots.

On the other hand, it may make for simpler code to rename the second 
defined objective, or to rename all objectives to be objectivetype.name 
e.g. risk_budget.ETL, risk.ETL or alternately, making the list 
multi-level, with objective types being a heirarchy above the individual 
objectives.

Without spending time poking at it, I don't know which makes more sense, 
special-casing for the risk_budget functions which all have a common 
form, or trying to general-case the naming conventions inside the list.

-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock

From peter at braverock.com  Mon Sep 23 22:19:39 2013
From: peter at braverock.com (Peter Carl)
Date: Mon, 23 Sep 2013 15:19:39 -0500
Subject: [GSoC-PortA] Some feedback...
In-Reply-To: <CAEESW=Vnm=gdrW-ZrNcs75PDMHjKQnoWjcQbbCXNvPtKyag6=A@mail.gmail.com>
References: <6077558330b1a022003470c2092bae1b.squirrel@mail.braverock.com>
 <CAEESW=Vnm=gdrW-ZrNcs75PDMHjKQnoWjcQbbCXNvPtKyag6=A@mail.gmail.com>
Message-ID: <d8bde6de6669c505e939538fbec8aeca.squirrel@mail.braverock.com>

Here's your comment from below:

"It is tough to tell with the formatting on the email, but I'll take a
closer look at the script in the sandbox to see if I can tell what is
going on. The idea is that extractObjectiveMeasures will return a matrix
of the objective measures for all optimize.portfolio objects in the
opt.list object. For example, the meanSD row should have NAs under the ETL
and ETL component contribution columns. I am only stitching together the
objective measures, I do not re-calculate StdDev or component StdDev for
the portfolios with ETL as an objective. Basically, I just take whatever
objectives are in the $objective_measures slot of each optimize.portfolio
object. Should I be doing something such that all cells in the matrix have
values? "

I think so, although I doubt this has been well spelled out before.  The
question is: can we anticipate how to fill in these values given the
information in each object?

When I do this by hand, I'm just calculating for the list of optimal
weights of each objective for each measure.  At that point, I can make
comparisons I couldn't otherwise.

Note that the objectives can be vastly different, as long as the assets
are the same and the parameters for each of the metrics are the same.

Does that make sense?

pcc
-- 
Peter Carl
http://www.braverock.com/peter

> Peter,
>
> Thanks for the feedback, I really appreciate it.
>
> see comments in line.
>
>
> On Sun, Sep 22, 2013 at 4:41 PM, Peter Carl <peter at braverock.com> wrote:
>
>> Ross,
>>
>> I've been working through your vignette to hopefully give you some more
>> detailed feedback, including on your questions from a few days ago.
>> Sorry
>> this has taken so long, but I wanted to spend some focused time on the
>> package.
>>
>> I realize that you've got different plot methods for each type, and I
>> appreciate what a hassle it is to keep such methods relatively
>> consistent.
>>  In chart.RiskReturn.DE, when the function doesn't find anything that
>> fits
>> its defaults:
>> > plot(RiskBudget.DE)
>> Error in plot.window(...) : need finite 'xlim' values
>> In addition: Warning messages:
>> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
>> return.col,  :
>>   mean or ES do  not match extractStats output of $objective_measures
>> slot
>> 2: In min(x) : no non-missing arguments to min; returning Inf
>> 3: In max(x) : no non-missing arguments to max; returning -Inf
>>
>> It's a risk budget on ETL, so if I tell it that, it works:
>> > plot(RiskBudget.DE, risk.col="ETL", return.col="mean")
>>
>
> The default is risk.col="ES". Because your objective name is "ETL", you
> need to explicitly do risk.col="ETL".
>
>
>>
>> ...but it doesn't recover well when I try to plot the results in
>> variance
>> space:
>> > plot(RiskBudget.DE, risk.col="StdDev", return.col="mean")
>> Error in plot.window(...) : need finite 'xlim' values
>> In addition: Warning messages:
>> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
>> return.col,  :
>>   mean or StdDev do  not match extractStats output of
>> $objective_measures
>> slot
>> 2: In min(x) : no non-missing arguments to min; returning Inf
>> 3: In max(x) : no non-missing arguments to max; returning -Inf
>>
>>
>> I'm not exactly sure what the issue is here, but maybe it's related:
>> > chart.RiskBudget(RiskBudget.DE, risk.type="percentage", neighbors=5)
>> Error in subsetx[i, riskcols] : incorrect number of dimensions
>> > traceback()
>> 3: points(subsetx[i, riskcols], type = "b", col = "lightblue")
>> 2: chart.RiskBudget.optimize.portfolio(RiskBudget.DE, risk.type =
>> "percentage",
>>        neighbors = 5)
>> 1: chart.RiskBudget(RiskBudget.DE, risk.type = "percentage", neighbors =
>> 5)
>>
>
> Not sure either what the issue is, but I'll take a look.
>
>
>> In chart.RiskReturnScatter.RP, it looks like 'rp' is being passed into
>> plot through dots.
>> > plot(EqmETL.RND, risk.col="StdDev", return.col="mean", rp=1000,
>> chart.assets=TRUE)
>> There were 13 warnings (use warnings() to see them)
>> > warnings()
>> Warning messages:
>> 1: "rp" is not a graphical parameter
>> 2: "rp" is not a graphical parameter
>> 3: "rp" is not a graphical parameter
>>
>
> The 'rp' argument is meant for optimize.portfolio.ROI and
> optimize.portfolio.GenSA objects. Since ROI and GenSA do not return trace
> information like DEoptim or random portfolios, I added this as an option
> to
> generate random portfolios to plot the feasible space. If you are already
> passing in an optimize.portfolio.random object, there is no need to pass
> in
> rp as an argument.
>
>
>>
>>
>> > extractWeights(buoys)
>>          Convertible Arbitrage Equity Market Neutral Fixed Income
>> Arbitrage Event Driven CTA Global Global Macro Long/Short Equity
>> MeanSD              0.05000000                 0.050
>> 0.050   0.30000000  0.0500000    0.2000000             0.300
>> MeanmETL            0.05000000                 0.300
>> 0.050   0.05000000  0.2000000    0.3000000             0.050
>> MinSD               0.06042904                 0.300
>> 0.300   0.05234676  0.1735858    0.0636384             0.050
>> MinmETL             0.05000000                 0.300
>> 0.050   0.05000000  0.2000000    0.3000000             0.050
>> EqSD                0.12500000                 0.240
>> 0.200   0.08500000  0.1050000    0.1700000             0.075
>> EqmETL              0.06000000                 0.265
>> 0.165   0.09000000  0.2050000    0.1300000             0.080
>> RB                  0.05200000                 0.410
>> 0.060   0.05200000  0.1438995    0.2220000             0.058
>>
>> ...but this doesn't:
>> > extractObjectiveMeasures(buoys)
>>                 mean     StdDev         ES StdDev.contribution1
>> StdDev.contribution2 StdDev.contribution3
>> StdDev.contribution4
>> MeanSD   0.006782814 0.01546759         NA                   NA
>>        NA                   NA                   NA
>> MeanmETL 0.005897789         NA 0.01505626                   NA
>>        NA                   NA                   NA
>> MinSD             NA 0.01009001         NA                   NA
>>        NA                   NA                   NA
>> MinmETL           NA         NA 0.01505626                   NA
>>        NA                   NA                   NA
>> EqSD              NA 0.01113716         NA          0.001763096
>> 0.001565752          0.001886988          0.001258567
>> EqmETL            NA         NA 0.01646509                   NA
>>        NA                   NA                   NA
>> RB       0.005812997         NA         NA                   NA
>>        NA                   NA                   NA
>>          StdDev.contribution5 StdDev.contribution6 StdDev.contribution7
>> StdDev.pct_contrib_StdDev1 StdDev.pct_contrib_StdDev2
>> MeanSD                     NA                   NA                   NA
>>                      NA                         NA
>> MeanmETL                   NA                   NA                   NA
>>                      NA                         NA
>> MinSD                      NA                   NA                   NA
>>                      NA                         NA
>> MinmETL                    NA                   NA                   NA
>>                      NA                         NA
>> EqSD              0.001039908          0.002296903          0.001325947
>>               0.1583075                  0.1405881
>> EqmETL                     NA                   NA                   NA
>>                      NA                         NA
>> RB                         NA                   NA                   NA
>>                      NA                         NA
>> ...snip...
>>
>>
> It is tough to tell with the formatting on the email, but I'll take a
> closer look at the script in the sandbox to see if I can tell what is
> going
> on. The idea is that extractObjectiveMeasures will return a matrix of the
> objective measures for all optimize.portfolio objects in the opt.list
> object. For example, the meanSD row should have NAs under the ETL and ETL
> component contribution columns. I am only stitching together the objective
> measures, I do not re-calculate StdDev or component StdDev for the
> portfolios with ETL as an objective. Basically, I just take whatever
> objectives are in the $objective_measures slot of each optimize.portfolio
> object. Should I be doing something such that all cells in the matrix have
> values?
>
>
>> As a consequence, only one portfolio appears in the following plot
>> (MeanSD):
>> > chart.RiskReward(buoys)
>>
>
> This relates to my comment above about how I am not recalculating
> anything.
> Before the portfolios are plotted in risk-return space, I omit rows that
> have NA values. For example, if you wanted to plot all the portfolios in
> mean-ETL space, all portfolios should have mean and ETL as an objective.
> You could set the multiplier to 0 so it does not affect the optimization,
> but is returned in the $objective_measures slot.
>
>
>>
>> All in all, this is all looking good.  I've got some scripts checked in
>> under sandbox/symposium2013 if you want to follow along.
>>
>
> I'll take a closer look and follow along, thanks!
>
>
>>
>> pcc
>> --
>> Peter Carl
>> http://www.braverock.com/peter
>>
>>
>> _______________________________________________
>> GSoC-PortA mailing list
>> GSoC-PortA at lists.r-forge.r-project.org
>> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>>
>


From rossbennett34 at gmail.com  Tue Sep 24 05:28:26 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Mon, 23 Sep 2013 20:28:26 -0700
Subject: [GSoC-PortA] Odd Behavior Depending on Order of Objectives
In-Reply-To: <5240526A.1070403@braverock.com>
References: <CAEESW=V9UNqDouSEpn3ktWiWKPrcP9mPQ=R24hFLCAf-wwxiqw@mail.gmail.com>
 <5240526A.1070403@braverock.com>
Message-ID: <CAEESW=UyDGS2s38zMYWP0JFKmryUoScYvg7w9mqYYwPvo3YX3w@mail.gmail.com>

On Mon, Sep 23, 2013 at 7:38 AM, Brian G. Peterson <brian at braverock.com>wrote:
>
>
> The returned object is a named list.
>
> As such, the second objective with the same name overwrites the first.
> Both are calculated, but only one will get written.
>
> Dealing with this could be tricky.
>
> On the one hand, the component risk measures *do* calculate the univariate
> portfolio risk too.  So if we know that they have the same name, we can
> just get the correct info from the slots.
>
> On the other hand, it may make for simpler code to rename the second
> defined objective, or to rename all objectives to be objectivetype.namee.g. risk_budget.ETL, risk.ETL or alternately, making the list multi-level,
> with objective types being a heirarchy above the individual objectives.
>

I think that might be the best approach to rename the objectives to be
objectivetype.name. The main area that will be affected is the functions
that depend on the extractStats output, mainly the charting and generic
functions. I think we'll still want the user to specify risk.col="ES" and
not risk.col="risk.ES". A good solution might be to rename the objective as
suggested above and then deal with the column naming in extractStats.
Thoughts?
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130923/93d23259/attachment.html>

From rossbennett34 at gmail.com  Tue Sep 24 06:09:56 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Mon, 23 Sep 2013 21:09:56 -0700
Subject: [GSoC-PortA] Some feedback...
In-Reply-To: <d8bde6de6669c505e939538fbec8aeca.squirrel@mail.braverock.com>
References: <6077558330b1a022003470c2092bae1b.squirrel@mail.braverock.com>
 <CAEESW=Vnm=gdrW-ZrNcs75PDMHjKQnoWjcQbbCXNvPtKyag6=A@mail.gmail.com>
 <d8bde6de6669c505e939538fbec8aeca.squirrel@mail.braverock.com>
Message-ID: <CAEESW=XycK5GeBUvwdttkmwxtgcLvcLPTvjdjgurd5S9tpaLMA@mail.gmail.com>

On Mon, Sep 23, 2013 at 1:19 PM, Peter Carl <peter at braverock.com> wrote:

> Here's your comment from below:
>
> "It is tough to tell with the formatting on the email, but I'll take a
> closer look at the script in the sandbox to see if I can tell what is
> going on. The idea is that extractObjectiveMeasures will return a matrix
> of the objective measures for all optimize.portfolio objects in the
> opt.list object. For example, the meanSD row should have NAs under the ETL
> and ETL component contribution columns. I am only stitching together the
> objective measures, I do not re-calculate StdDev or component StdDev for
> the portfolios with ETL as an objective. Basically, I just take whatever
> objectives are in the $objective_measures slot of each optimize.portfolio
> object. Should I be doing something such that all cells in the matrix have
> values? "
>
> I think so, although I doubt this has been well spelled out before.  The
> question is: can we anticipate how to fill in these values given the
> information in each object?
>

I think we might be able to depending on how the objective measures are
calculated on the weights.

One way would be to pick out the objective names, match the name to the
function, and then calculate the objectives on the weights. The parameters
could be pulled from the $arguments list in each objective. This might be
tricky if there are multiple arguments with different arguments. This is
likely the simplest solution. If "ES" is an objective name, we could by
default calculate it with portfolio_method="component" since the univariate
ES also calculated.

Another way is to combine all the objectives from each object, try to
detect and remove duplicate objectives objects, then pass that portfolio
object to constrained_objective to calculate over the weights.

Not sure which way is better, I'll have to give this some thought and try
out a few things.


>
> When I do this by hand, I'm just calculating for the list of optimal
> weights of each objective for each measure.  At that point, I can make
> comparisons I couldn't otherwise.
>
> Note that the objectives can be vastly different, as long as the assets
> are the same and the parameters for each of the metrics are the same.
>

I could add a check to make sure that the assets and returns are the same
in each optimize.portfolio object. I think this will only work if that is
the case. It would be nice to have the flexibility to have different assets
and returns, but that may not be doable.


>
> Does that make sense?
>

It does make sense, thanks for the feedback.


>
> pcc
> --
> Peter Carl
> http://www.braverock.com/peter
>
> > Peter,
> >
> > Thanks for the feedback, I really appreciate it.
> >
> > see comments in line.
> >
> >
> > On Sun, Sep 22, 2013 at 4:41 PM, Peter Carl <peter at braverock.com> wrote:
> >
> >> Ross,
> >>
> >> I've been working through your vignette to hopefully give you some more
> >> detailed feedback, including on your questions from a few days ago.
> >> Sorry
> >> this has taken so long, but I wanted to spend some focused time on the
> >> package.
> >>
> >> I realize that you've got different plot methods for each type, and I
> >> appreciate what a hassle it is to keep such methods relatively
> >> consistent.
> >>  In chart.RiskReturn.DE, when the function doesn't find anything that
> >> fits
> >> its defaults:
> >> > plot(RiskBudget.DE)
> >> Error in plot.window(...) : need finite 'xlim' values
> >> In addition: Warning messages:
> >> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
> >> return.col,  :
> >>   mean or ES do  not match extractStats output of $objective_measures
> >> slot
> >> 2: In min(x) : no non-missing arguments to min; returning Inf
> >> 3: In max(x) : no non-missing arguments to max; returning -Inf
> >>
> >> It's a risk budget on ETL, so if I tell it that, it works:
> >> > plot(RiskBudget.DE, risk.col="ETL", return.col="mean")
> >>
> >
> > The default is risk.col="ES". Because your objective name is "ETL", you
> > need to explicitly do risk.col="ETL".
> >
> >
> >>
> >> ...but it doesn't recover well when I try to plot the results in
> >> variance
> >> space:
> >> > plot(RiskBudget.DE, risk.col="StdDev", return.col="mean")
> >> Error in plot.window(...) : need finite 'xlim' values
> >> In addition: Warning messages:
> >> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
> >> return.col,  :
> >>   mean or StdDev do  not match extractStats output of
> >> $objective_measures
> >> slot
> >> 2: In min(x) : no non-missing arguments to min; returning Inf
> >> 3: In max(x) : no non-missing arguments to max; returning -Inf
> >>
> >>
> >> I'm not exactly sure what the issue is here, but maybe it's related:
> >> > chart.RiskBudget(RiskBudget.DE, risk.type="percentage", neighbors=5)
> >> Error in subsetx[i, riskcols] : incorrect number of dimensions
> >> > traceback()
> >> 3: points(subsetx[i, riskcols], type = "b", col = "lightblue")
> >> 2: chart.RiskBudget.optimize.portfolio(RiskBudget.DE, risk.type =
> >> "percentage",
> >>        neighbors = 5)
> >> 1: chart.RiskBudget(RiskBudget.DE, risk.type = "percentage", neighbors =
> >> 5)
> >>
> >
> > Not sure either what the issue is, but I'll take a look.
> >
> >
> >> In chart.RiskReturnScatter.RP, it looks like 'rp' is being passed into
> >> plot through dots.
> >> > plot(EqmETL.RND, risk.col="StdDev", return.col="mean", rp=1000,
> >> chart.assets=TRUE)
> >> There were 13 warnings (use warnings() to see them)
> >> > warnings()
> >> Warning messages:
> >> 1: "rp" is not a graphical parameter
> >> 2: "rp" is not a graphical parameter
> >> 3: "rp" is not a graphical parameter
> >>
> >
> > The 'rp' argument is meant for optimize.portfolio.ROI and
> > optimize.portfolio.GenSA objects. Since ROI and GenSA do not return trace
> > information like DEoptim or random portfolios, I added this as an option
> > to
> > generate random portfolios to plot the feasible space. If you are already
> > passing in an optimize.portfolio.random object, there is no need to pass
> > in
> > rp as an argument.
> >
> >
> >>
> >>
> >> > extractWeights(buoys)
> >>          Convertible Arbitrage Equity Market Neutral Fixed Income
> >> Arbitrage Event Driven CTA Global Global Macro Long/Short Equity
> >> MeanSD              0.05000000                 0.050
> >> 0.050   0.30000000  0.0500000    0.2000000             0.300
> >> MeanmETL            0.05000000                 0.300
> >> 0.050   0.05000000  0.2000000    0.3000000             0.050
> >> MinSD               0.06042904                 0.300
> >> 0.300   0.05234676  0.1735858    0.0636384             0.050
> >> MinmETL             0.05000000                 0.300
> >> 0.050   0.05000000  0.2000000    0.3000000             0.050
> >> EqSD                0.12500000                 0.240
> >> 0.200   0.08500000  0.1050000    0.1700000             0.075
> >> EqmETL              0.06000000                 0.265
> >> 0.165   0.09000000  0.2050000    0.1300000             0.080
> >> RB                  0.05200000                 0.410
> >> 0.060   0.05200000  0.1438995    0.2220000             0.058
> >>
> >> ...but this doesn't:
> >> > extractObjectiveMeasures(buoys)
> >>                 mean     StdDev         ES StdDev.contribution1
> >> StdDev.contribution2 StdDev.contribution3
> >> StdDev.contribution4
> >> MeanSD   0.006782814 0.01546759         NA                   NA
> >>        NA                   NA                   NA
> >> MeanmETL 0.005897789         NA 0.01505626                   NA
> >>        NA                   NA                   NA
> >> MinSD             NA 0.01009001         NA                   NA
> >>        NA                   NA                   NA
> >> MinmETL           NA         NA 0.01505626                   NA
> >>        NA                   NA                   NA
> >> EqSD              NA 0.01113716         NA          0.001763096
> >> 0.001565752          0.001886988          0.001258567
> >> EqmETL            NA         NA 0.01646509                   NA
> >>        NA                   NA                   NA
> >> RB       0.005812997         NA         NA                   NA
> >>        NA                   NA                   NA
> >>          StdDev.contribution5 StdDev.contribution6 StdDev.contribution7
> >> StdDev.pct_contrib_StdDev1 StdDev.pct_contrib_StdDev2
> >> MeanSD                     NA                   NA                   NA
> >>                      NA                         NA
> >> MeanmETL                   NA                   NA                   NA
> >>                      NA                         NA
> >> MinSD                      NA                   NA                   NA
> >>                      NA                         NA
> >> MinmETL                    NA                   NA                   NA
> >>                      NA                         NA
> >> EqSD              0.001039908          0.002296903          0.001325947
> >>               0.1583075                  0.1405881
> >> EqmETL                     NA                   NA                   NA
> >>                      NA                         NA
> >> RB                         NA                   NA                   NA
> >>                      NA                         NA
> >> ...snip...
> >>
> >>
> > It is tough to tell with the formatting on the email, but I'll take a
> > closer look at the script in the sandbox to see if I can tell what is
> > going
> > on. The idea is that extractObjectiveMeasures will return a matrix of the
> > objective measures for all optimize.portfolio objects in the opt.list
> > object. For example, the meanSD row should have NAs under the ETL and ETL
> > component contribution columns. I am only stitching together the
> objective
> > measures, I do not re-calculate StdDev or component StdDev for the
> > portfolios with ETL as an objective. Basically, I just take whatever
> > objectives are in the $objective_measures slot of each optimize.portfolio
> > object. Should I be doing something such that all cells in the matrix
> have
> > values?
> >
> >
> >> As a consequence, only one portfolio appears in the following plot
> >> (MeanSD):
> >> > chart.RiskReward(buoys)
> >>
> >
> > This relates to my comment above about how I am not recalculating
> > anything.
> > Before the portfolios are plotted in risk-return space, I omit rows that
> > have NA values. For example, if you wanted to plot all the portfolios in
> > mean-ETL space, all portfolios should have mean and ETL as an objective.
> > You could set the multiplier to 0 so it does not affect the optimization,
> > but is returned in the $objective_measures slot.
> >
> >
> >>
> >> All in all, this is all looking good.  I've got some scripts checked in
> >> under sandbox/symposium2013 if you want to follow along.
> >>
> >
> > I'll take a closer look and follow along, thanks!
> >
> >
> >>
> >> pcc
> >> --
> >> Peter Carl
> >> http://www.braverock.com/peter
> >>
> >>
> >> _______________________________________________
> >> GSoC-PortA mailing list
> >> GSoC-PortA at lists.r-forge.r-project.org
> >> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
> >>
> >
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130923/917b58e7/attachment-0001.html>

From peter at braverock.com  Tue Sep 24 13:00:57 2013
From: peter at braverock.com (Peter Carl)
Date: Tue, 24 Sep 2013 06:00:57 -0500
Subject: [GSoC-PortA] Some feedback...
In-Reply-To: <CAEESW=XycK5GeBUvwdttkmwxtgcLvcLPTvjdjgurd5S9tpaLMA@mail.gmail.com>
References: <6077558330b1a022003470c2092bae1b.squirrel@mail.braverock.com>
 <CAEESW=Vnm=gdrW-ZrNcs75PDMHjKQnoWjcQbbCXNvPtKyag6=A@mail.gmail.com>
 <d8bde6de6669c505e939538fbec8aeca.squirrel@mail.braverock.com>
 <CAEESW=XycK5GeBUvwdttkmwxtgcLvcLPTvjdjgurd5S9tpaLMA@mail.gmail.com>
Message-ID: <30c9e004e0cf5f5dfda0cd17ef50ea01.squirrel@mail.braverock.com>

Now that I think about it a bit more, I think that returns and assets CAN
differ, as long as the measures are calculable at the portfolio level. 
I'm not sure which of the processes you outlined below are preferable, but
they are definitely in the right direction.

pcc
-- 
Peter Carl
http://www.braverock.com/peter

> On Mon, Sep 23, 2013 at 1:19 PM, Peter Carl <peter at braverock.com> wrote:
>
>> Here's your comment from below:
>>
>> "It is tough to tell with the formatting on the email, but I'll take a
>> closer look at the script in the sandbox to see if I can tell what is
>> going on. The idea is that extractObjectiveMeasures will return a matrix
>> of the objective measures for all optimize.portfolio objects in the
>> opt.list object. For example, the meanSD row should have NAs under the
>> ETL
>> and ETL component contribution columns. I am only stitching together the
>> objective measures, I do not re-calculate StdDev or component StdDev for
>> the portfolios with ETL as an objective. Basically, I just take whatever
>> objectives are in the $objective_measures slot of each
>> optimize.portfolio
>> object. Should I be doing something such that all cells in the matrix
>> have
>> values? "
>>
>> I think so, although I doubt this has been well spelled out before.  The
>> question is: can we anticipate how to fill in these values given the
>> information in each object?
>>
>
> I think we might be able to depending on how the objective measures are
> calculated on the weights.
>
> One way would be to pick out the objective names, match the name to the
> function, and then calculate the objectives on the weights. The parameters
> could be pulled from the $arguments list in each objective. This might be
> tricky if there are multiple arguments with different arguments. This is
> likely the simplest solution. If "ES" is an objective name, we could by
> default calculate it with portfolio_method="component" since the
> univariate
> ES also calculated.
>
> Another way is to combine all the objectives from each object, try to
> detect and remove duplicate objectives objects, then pass that portfolio
> object to constrained_objective to calculate over the weights.
>
> Not sure which way is better, I'll have to give this some thought and try
> out a few things.
>
>
>>
>> When I do this by hand, I'm just calculating for the list of optimal
>> weights of each objective for each measure.  At that point, I can make
>> comparisons I couldn't otherwise.
>>
>> Note that the objectives can be vastly different, as long as the assets
>> are the same and the parameters for each of the metrics are the same.
>>
>
> I could add a check to make sure that the assets and returns are the same
> in each optimize.portfolio object. I think this will only work if that is
> the case. It would be nice to have the flexibility to have different
> assets
> and returns, but that may not be doable.
>
>
>>
>> Does that make sense?
>>
>
> It does make sense, thanks for the feedback.
>
>
>>
>> pcc
>> --
>> Peter Carl
>> http://www.braverock.com/peter
>>
>> > Peter,
>> >
>> > Thanks for the feedback, I really appreciate it.
>> >
>> > see comments in line.
>> >
>> >
>> > On Sun, Sep 22, 2013 at 4:41 PM, Peter Carl <peter at braverock.com>
>> wrote:
>> >
>> >> Ross,
>> >>
>> >> I've been working through your vignette to hopefully give you some
>> more
>> >> detailed feedback, including on your questions from a few days ago.
>> >> Sorry
>> >> this has taken so long, but I wanted to spend some focused time on
>> the
>> >> package.
>> >>
>> >> I realize that you've got different plot methods for each type, and I
>> >> appreciate what a hassle it is to keep such methods relatively
>> >> consistent.
>> >>  In chart.RiskReturn.DE, when the function doesn't find anything that
>> >> fits
>> >> its defaults:
>> >> > plot(RiskBudget.DE)
>> >> Error in plot.window(...) : need finite 'xlim' values
>> >> In addition: Warning messages:
>> >> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
>> >> return.col,  :
>> >>   mean or ES do  not match extractStats output of $objective_measures
>> >> slot
>> >> 2: In min(x) : no non-missing arguments to min; returning Inf
>> >> 3: In max(x) : no non-missing arguments to max; returning -Inf
>> >>
>> >> It's a risk budget on ETL, so if I tell it that, it works:
>> >> > plot(RiskBudget.DE, risk.col="ETL", return.col="mean")
>> >>
>> >
>> > The default is risk.col="ES". Because your objective name is "ETL",
>> you
>> > need to explicitly do risk.col="ETL".
>> >
>> >
>> >>
>> >> ...but it doesn't recover well when I try to plot the results in
>> >> variance
>> >> space:
>> >> > plot(RiskBudget.DE, risk.col="StdDev", return.col="mean")
>> >> Error in plot.window(...) : need finite 'xlim' values
>> >> In addition: Warning messages:
>> >> 1: In chart.Scatter.DE(object = DE, risk.col = risk.col, return.col =
>> >> return.col,  :
>> >>   mean or StdDev do  not match extractStats output of
>> >> $objective_measures
>> >> slot
>> >> 2: In min(x) : no non-missing arguments to min; returning Inf
>> >> 3: In max(x) : no non-missing arguments to max; returning -Inf
>> >>
>> >>
>> >> I'm not exactly sure what the issue is here, but maybe it's related:
>> >> > chart.RiskBudget(RiskBudget.DE, risk.type="percentage",
>> neighbors=5)
>> >> Error in subsetx[i, riskcols] : incorrect number of dimensions
>> >> > traceback()
>> >> 3: points(subsetx[i, riskcols], type = "b", col = "lightblue")
>> >> 2: chart.RiskBudget.optimize.portfolio(RiskBudget.DE, risk.type =
>> >> "percentage",
>> >>        neighbors = 5)
>> >> 1: chart.RiskBudget(RiskBudget.DE, risk.type = "percentage",
>> neighbors =
>> >> 5)
>> >>
>> >
>> > Not sure either what the issue is, but I'll take a look.
>> >
>> >
>> >> In chart.RiskReturnScatter.RP, it looks like 'rp' is being passed
>> into
>> >> plot through dots.
>> >> > plot(EqmETL.RND, risk.col="StdDev", return.col="mean", rp=1000,
>> >> chart.assets=TRUE)
>> >> There were 13 warnings (use warnings() to see them)
>> >> > warnings()
>> >> Warning messages:
>> >> 1: "rp" is not a graphical parameter
>> >> 2: "rp" is not a graphical parameter
>> >> 3: "rp" is not a graphical parameter
>> >>
>> >
>> > The 'rp' argument is meant for optimize.portfolio.ROI and
>> > optimize.portfolio.GenSA objects. Since ROI and GenSA do not return
>> trace
>> > information like DEoptim or random portfolios, I added this as an
>> option
>> > to
>> > generate random portfolios to plot the feasible space. If you are
>> already
>> > passing in an optimize.portfolio.random object, there is no need to
>> pass
>> > in
>> > rp as an argument.
>> >
>> >
>> >>
>> >>
>> >> > extractWeights(buoys)
>> >>          Convertible Arbitrage Equity Market Neutral Fixed Income
>> >> Arbitrage Event Driven CTA Global Global Macro Long/Short Equity
>> >> MeanSD              0.05000000                 0.050
>> >> 0.050   0.30000000  0.0500000    0.2000000             0.300
>> >> MeanmETL            0.05000000                 0.300
>> >> 0.050   0.05000000  0.2000000    0.3000000             0.050
>> >> MinSD               0.06042904                 0.300
>> >> 0.300   0.05234676  0.1735858    0.0636384             0.050
>> >> MinmETL             0.05000000                 0.300
>> >> 0.050   0.05000000  0.2000000    0.3000000             0.050
>> >> EqSD                0.12500000                 0.240
>> >> 0.200   0.08500000  0.1050000    0.1700000             0.075
>> >> EqmETL              0.06000000                 0.265
>> >> 0.165   0.09000000  0.2050000    0.1300000             0.080
>> >> RB                  0.05200000                 0.410
>> >> 0.060   0.05200000  0.1438995    0.2220000             0.058
>> >>
>> >> ...but this doesn't:
>> >> > extractObjectiveMeasures(buoys)
>> >>                 mean     StdDev         ES StdDev.contribution1
>> >> StdDev.contribution2 StdDev.contribution3
>> >> StdDev.contribution4
>> >> MeanSD   0.006782814 0.01546759         NA                   NA
>> >>        NA                   NA                   NA
>> >> MeanmETL 0.005897789         NA 0.01505626                   NA
>> >>        NA                   NA                   NA
>> >> MinSD             NA 0.01009001         NA                   NA
>> >>        NA                   NA                   NA
>> >> MinmETL           NA         NA 0.01505626                   NA
>> >>        NA                   NA                   NA
>> >> EqSD              NA 0.01113716         NA          0.001763096
>> >> 0.001565752          0.001886988          0.001258567
>> >> EqmETL            NA         NA 0.01646509                   NA
>> >>        NA                   NA                   NA
>> >> RB       0.005812997         NA         NA                   NA
>> >>        NA                   NA                   NA
>> >>          StdDev.contribution5 StdDev.contribution6
>> StdDev.contribution7
>> >> StdDev.pct_contrib_StdDev1 StdDev.pct_contrib_StdDev2
>> >> MeanSD                     NA                   NA
>> NA
>> >>                      NA                         NA
>> >> MeanmETL                   NA                   NA
>> NA
>> >>                      NA                         NA
>> >> MinSD                      NA                   NA
>> NA
>> >>                      NA                         NA
>> >> MinmETL                    NA                   NA
>> NA
>> >>                      NA                         NA
>> >> EqSD              0.001039908          0.002296903
>> 0.001325947
>> >>               0.1583075                  0.1405881
>> >> EqmETL                     NA                   NA
>> NA
>> >>                      NA                         NA
>> >> RB                         NA                   NA
>> NA
>> >>                      NA                         NA
>> >> ...snip...
>> >>
>> >>
>> > It is tough to tell with the formatting on the email, but I'll take a
>> > closer look at the script in the sandbox to see if I can tell what is
>> > going
>> > on. The idea is that extractObjectiveMeasures will return a matrix of
>> the
>> > objective measures for all optimize.portfolio objects in the opt.list
>> > object. For example, the meanSD row should have NAs under the ETL and
>> ETL
>> > component contribution columns. I am only stitching together the
>> objective
>> > measures, I do not re-calculate StdDev or component StdDev for the
>> > portfolios with ETL as an objective. Basically, I just take whatever
>> > objectives are in the $objective_measures slot of each
>> optimize.portfolio
>> > object. Should I be doing something such that all cells in the matrix
>> have
>> > values?
>> >
>> >
>> >> As a consequence, only one portfolio appears in the following plot
>> >> (MeanSD):
>> >> > chart.RiskReward(buoys)
>> >>
>> >
>> > This relates to my comment above about how I am not recalculating
>> > anything.
>> > Before the portfolios are plotted in risk-return space, I omit rows
>> that
>> > have NA values. For example, if you wanted to plot all the portfolios
>> in
>> > mean-ETL space, all portfolios should have mean and ETL as an
>> objective.
>> > You could set the multiplier to 0 so it does not affect the
>> optimization,
>> > but is returned in the $objective_measures slot.
>> >
>> >
>> >>
>> >> All in all, this is all looking good.  I've got some scripts checked
>> in
>> >> under sandbox/symposium2013 if you want to follow along.
>> >>
>> >
>> > I'll take a closer look and follow along, thanks!
>> >
>> >
>> >>
>> >> pcc
>> >> --
>> >> Peter Carl
>> >> http://www.braverock.com/peter
>> >>
>> >>
>> >> _______________________________________________
>> >> GSoC-PortA mailing list
>> >> GSoC-PortA at lists.r-forge.r-project.org
>> >> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>> >>
>> >
>>
>> _______________________________________________
>> GSoC-PortA mailing list
>> GSoC-PortA at lists.r-forge.r-project.org
>> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>



From peter at braverock.com  Tue Sep 24 16:28:07 2013
From: peter at braverock.com (Peter Carl)
Date: Tue, 24 Sep 2013 09:28:07 -0500
Subject: [GSoC-PortA] Random portfolios
Message-ID: <0219d0832454daa3b2ad9b43904f479f.squirrel@mail.braverock.com>

The random_portfolios function isn't generating the correct number of
permutations.

> random_portfolios(portfolio=init.portf, permutations=1000)

gives me a result with 317 weight vectors, rather than 1000.

I think that there's a loop missing: when the number of lines is less than
permutations, the function needs to generate more, check for unique
solutions, and repeat until there are (in this case) 1000 weight vectors.

Although (and it's difficult to tell), on their own the charts seem to
generate about the right number?  Or maybe not...

pcc
-- 
Peter Carl
http://www.braverock.com/peter




From brian at braverock.com  Tue Sep 24 16:33:07 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Tue, 24 Sep 2013 09:33:07 -0500
Subject: [GSoC-PortA] Random portfolios
In-Reply-To: <0219d0832454daa3b2ad9b43904f479f.squirrel@mail.braverock.com>
References: <0219d0832454daa3b2ad9b43904f479f.squirrel@mail.braverock.com>
Message-ID: <5241A2A3.60902@braverock.com>

On 09/24/2013 09:28 AM, Peter Carl wrote:
> The random_portfolios function isn't generating the correct number of
> permutations.
>
>> >random_portfolios(portfolio=init.portf, permutations=1000)
> gives me a result with 317 weight vectors, rather than 1000.
>
> I think that there's a loop missing: when the number of lines is less than
> permutations, the function needs to generate more, check for unique
> solutions, and repeat until there are (in this case) 1000 weight vectors.
>
> Although (and it's difficult to tell), on their own the charts seem to
> generate about the right number?  Or maybe not...

I suspect that given your constraints you're just hitting 
max_permutations.

All that code is still there, so it seems most likely that you just 
don't have max_permutations high enough, or that your granularity on the 
sequence is too high (e.g. you're using a step size of .01, and should 
try .005)

-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock

From peter at braverock.com  Tue Sep 24 17:02:58 2013
From: peter at braverock.com (Peter Carl)
Date: Tue, 24 Sep 2013 10:02:58 -0500
Subject: [GSoC-PortA] Random portfolios
In-Reply-To: <5241A2A3.60902@braverock.com>
References: <0219d0832454daa3b2ad9b43904f479f.squirrel@mail.braverock.com>
 <5241A2A3.60902@braverock.com>
Message-ID: <dd2e8933911a09cbd8d6130d47f4ad2c.squirrel@mail.braverock.com>

Fair point.  I get the same result when I use high values for
max_permutations.  That attribute should probably be referenced in the
function documentation under details, so that users know it can be passed
through dots.

Same result though.  When I call rp_sample directly:
rp_sample(init.portf, permutations=1000)
... I get 1000 rows back.

So something's happening in the dispatch code?

pcc
-- 
Peter Carl
http://www.braverock.com/peter

> On 09/24/2013 09:28 AM, Peter Carl wrote:
>> The random_portfolios function isn't generating the correct number of
>> permutations.
>>
>>> >random_portfolios(portfolio=init.portf, permutations=1000)
>> gives me a result with 317 weight vectors, rather than 1000.
>>
>> I think that there's a loop missing: when the number of lines is less
>> than
>> permutations, the function needs to generate more, check for unique
>> solutions, and repeat until there are (in this case) 1000 weight
>> vectors.
>>
>> Although (and it's difficult to tell), on their own the charts seem to
>> generate about the right number?  Or maybe not...
>
> I suspect that given your constraints you're just hitting
> max_permutations.
>
> All that code is still there, so it seems most likely that you just
> don't have max_permutations high enough, or that your granularity on the
> sequence is too high (e.g. you're using a step size of .01, and should
> try .005)
>
> --
> Brian G. Peterson
> http://braverock.com/brian/
> Ph: 773-459-4973
> IM: bgpbraverock
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>



From rossbennett34 at gmail.com  Tue Sep 24 17:15:27 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Tue, 24 Sep 2013 08:15:27 -0700
Subject: [GSoC-PortA] Random portfolios
In-Reply-To: <dd2e8933911a09cbd8d6130d47f4ad2c.squirrel@mail.braverock.com>
References: <0219d0832454daa3b2ad9b43904f479f.squirrel@mail.braverock.com>
 <5241A2A3.60902@braverock.com>
 <dd2e8933911a09cbd8d6130d47f4ad2c.squirrel@mail.braverock.com>
Message-ID: <CAEESW=UpNLWQCEqL4J6YpTa8HqVYnC_juGjyJNA=P9NVuEwBAQ@mail.gmail.com>

Thanks for making me aware of this. I'll take a closer look and try to
figure out what is going on.

Ross
On Sep 24, 2013 8:03 AM, "Peter Carl" <peter at braverock.com> wrote:

> Fair point.  I get the same result when I use high values for
> max_permutations.  That attribute should probably be referenced in the
> function documentation under details, so that users know it can be passed
> through dots.
>
> Same result though.  When I call rp_sample directly:
> rp_sample(init.portf, permutations=1000)
> ... I get 1000 rows back.
>
> So something's happening in the dispatch code?
>
> pcc
> --
> Peter Carl
> http://www.braverock.com/peter
>
> > On 09/24/2013 09:28 AM, Peter Carl wrote:
> >> The random_portfolios function isn't generating the correct number of
> >> permutations.
> >>
> >>> >random_portfolios(portfolio=init.portf, permutations=1000)
> >> gives me a result with 317 weight vectors, rather than 1000.
> >>
> >> I think that there's a loop missing: when the number of lines is less
> >> than
> >> permutations, the function needs to generate more, check for unique
> >> solutions, and repeat until there are (in this case) 1000 weight
> >> vectors.
> >>
> >> Although (and it's difficult to tell), on their own the charts seem to
> >> generate about the right number?  Or maybe not...
> >
> > I suspect that given your constraints you're just hitting
> > max_permutations.
> >
> > All that code is still there, so it seems most likely that you just
> > don't have max_permutations high enough, or that your granularity on the
> > sequence is too high (e.g. you're using a step size of .01, and should
> > try .005)
> >
> > --
> > Brian G. Peterson
> > http://braverock.com/brian/
> > Ph: 773-459-4973
> > IM: bgpbraverock
> > _______________________________________________
> > GSoC-PortA mailing list
> > GSoC-PortA at lists.r-forge.r-project.org
> > http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
> >
>
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130924/16d42391/attachment-0001.html>

From rossbennett34 at gmail.com  Tue Sep 24 18:17:19 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Tue, 24 Sep 2013 09:17:19 -0700
Subject: [GSoC-PortA] Random portfolios
In-Reply-To: <CAEESW=UpNLWQCEqL4J6YpTa8HqVYnC_juGjyJNA=P9NVuEwBAQ@mail.gmail.com>
References: <0219d0832454daa3b2ad9b43904f479f.squirrel@mail.braverock.com>
 <5241A2A3.60902@braverock.com>
 <dd2e8933911a09cbd8d6130d47f4ad2c.squirrel@mail.braverock.com>
 <CAEESW=UpNLWQCEqL4J6YpTa8HqVYnC_juGjyJNA=P9NVuEwBAQ@mail.gmail.com>
Message-ID: <CAEESW=V4u-DRdqtqpgG91KWmF9czgqSiwm3XvWxnBP2h3A8D-A@mail.gmail.com>

The reason for fewer random portfolios being generated is due to the
leverage constraints in init.portf. There is a block of code in
randomize_portfolio_v2 (which is called by rp_sample) that will check for a
difference in min_sum and max_sum. For example, if min_sum=1 and max_sum=1,
we temporarily modify min_sum=0.99 and max_sum=1.01 so that random
portfolios can be generated.

Then in random_portfolios, there is a block of code that eliminates
portfolios that do not satisfy the constraints with the check_constraints
function. This takes place for random portfolios generated by the sample,
simplex, and grid method. Because rp_sample will generate portfolios with
weights that sum from 0.99 to 1.01, there are several portfolios that
violate leverage constraints of min_sum=1 and max_sum=1 and therefore will
be eliminated.

If you change the init.portf leverage constraints to min_sum=0.99 and
max_sum=1.01 you should generate 1000 portfolios.

I'll add some of this content to the @details in random_portfolios to
explain how the function is sensitive to leverage constraints.

Thanks,
Ross




On Tue, Sep 24, 2013 at 8:15 AM, Ross Bennett <rossbennett34 at gmail.com>wrote:

> Thanks for making me aware of this. I'll take a closer look and try to
> figure out what is going on.
>
> Ross
> On Sep 24, 2013 8:03 AM, "Peter Carl" <peter at braverock.com> wrote:
>
>> Fair point.  I get the same result when I use high values for
>> max_permutations.  That attribute should probably be referenced in the
>> function documentation under details, so that users know it can be passed
>> through dots.
>>
>> Same result though.  When I call rp_sample directly:
>> rp_sample(init.portf, permutations=1000)
>> ... I get 1000 rows back.
>>
>> So something's happening in the dispatch code?
>>
>> pcc
>> --
>> Peter Carl
>> http://www.braverock.com/peter
>>
>> > On 09/24/2013 09:28 AM, Peter Carl wrote:
>> >> The random_portfolios function isn't generating the correct number of
>> >> permutations.
>> >>
>> >>> >random_portfolios(portfolio=init.portf, permutations=1000)
>> >> gives me a result with 317 weight vectors, rather than 1000.
>> >>
>> >> I think that there's a loop missing: when the number of lines is less
>> >> than
>> >> permutations, the function needs to generate more, check for unique
>> >> solutions, and repeat until there are (in this case) 1000 weight
>> >> vectors.
>> >>
>> >> Although (and it's difficult to tell), on their own the charts seem to
>> >> generate about the right number?  Or maybe not...
>> >
>> > I suspect that given your constraints you're just hitting
>> > max_permutations.
>> >
>> > All that code is still there, so it seems most likely that you just
>> > don't have max_permutations high enough, or that your granularity on the
>> > sequence is too high (e.g. you're using a step size of .01, and should
>> > try .005)
>> >
>> > --
>> > Brian G. Peterson
>> > http://braverock.com/brian/
>> > Ph: 773-459-4973
>> > IM: bgpbraverock
>> > _______________________________________________
>> > GSoC-PortA mailing list
>> > GSoC-PortA at lists.r-forge.r-project.org
>> > http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>> >
>>
>>
>> _______________________________________________
>> GSoC-PortA mailing list
>> GSoC-PortA at lists.r-forge.r-project.org
>> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130924/55226669/attachment.html>

From peter at braverock.com  Tue Sep 24 18:52:29 2013
From: peter at braverock.com (Peter Carl)
Date: Tue, 24 Sep 2013 11:52:29 -0500
Subject: [GSoC-PortA] Random portfolios
In-Reply-To: <CAEESW=V4u-DRdqtqpgG91KWmF9czgqSiwm3XvWxnBP2h3A8D-A@mail.gmail.com>
References: <0219d0832454daa3b2ad9b43904f479f.squirrel@mail.braverock.com>
 <5241A2A3.60902@braverock.com>
 <dd2e8933911a09cbd8d6130d47f4ad2c.squirrel@mail.braverock.com>
 <CAEESW=UpNLWQCEqL4J6YpTa8HqVYnC_juGjyJNA=P9NVuEwBAQ@mail.gmail.com>
 <CAEESW=V4u-DRdqtqpgG91KWmF9czgqSiwm3XvWxnBP2h3A8D-A@mail.gmail.com>
Message-ID: <92768f15249e53f2546f32e09f48d3b7.squirrel@mail.braverock.com>

Thanks, that does work.  Should the check done in randomize_portfolio_v2
be moved up the chain to catch that issue earlier?
-- 
Peter Carl
http://www.braverock.com/peter

> The reason for fewer random portfolios being generated is due to the
> leverage constraints in init.portf. There is a block of code in
> randomize_portfolio_v2 (which is called by rp_sample) that will check for
> a
> difference in min_sum and max_sum. For example, if min_sum=1 and
> max_sum=1,
> we temporarily modify min_sum=0.99 and max_sum=1.01 so that random
> portfolios can be generated.
>
> Then in random_portfolios, there is a block of code that eliminates
> portfolios that do not satisfy the constraints with the check_constraints
> function. This takes place for random portfolios generated by the sample,
> simplex, and grid method. Because rp_sample will generate portfolios with
> weights that sum from 0.99 to 1.01, there are several portfolios that
> violate leverage constraints of min_sum=1 and max_sum=1 and therefore will
> be eliminated.
>
> If you change the init.portf leverage constraints to min_sum=0.99 and
> max_sum=1.01 you should generate 1000 portfolios.
>
> I'll add some of this content to the @details in random_portfolios to
> explain how the function is sensitive to leverage constraints.
>
> Thanks,
> Ross
>
>
>
>
> On Tue, Sep 24, 2013 at 8:15 AM, Ross Bennett
> <rossbennett34 at gmail.com>wrote:
>
>> Thanks for making me aware of this. I'll take a closer look and try to
>> figure out what is going on.
>>
>> Ross
>> On Sep 24, 2013 8:03 AM, "Peter Carl" <peter at braverock.com> wrote:
>>
>>> Fair point.  I get the same result when I use high values for
>>> max_permutations.  That attribute should probably be referenced in the
>>> function documentation under details, so that users know it can be
>>> passed
>>> through dots.
>>>
>>> Same result though.  When I call rp_sample directly:
>>> rp_sample(init.portf, permutations=1000)
>>> ... I get 1000 rows back.
>>>
>>> So something's happening in the dispatch code?
>>>
>>> pcc
>>> --
>>> Peter Carl
>>> http://www.braverock.com/peter
>>>
>>> > On 09/24/2013 09:28 AM, Peter Carl wrote:
>>> >> The random_portfolios function isn't generating the correct number
>>> of
>>> >> permutations.
>>> >>
>>> >>> >random_portfolios(portfolio=init.portf, permutations=1000)
>>> >> gives me a result with 317 weight vectors, rather than 1000.
>>> >>
>>> >> I think that there's a loop missing: when the number of lines is
>>> less
>>> >> than
>>> >> permutations, the function needs to generate more, check for unique
>>> >> solutions, and repeat until there are (in this case) 1000 weight
>>> >> vectors.
>>> >>
>>> >> Although (and it's difficult to tell), on their own the charts seem
>>> to
>>> >> generate about the right number?  Or maybe not...
>>> >
>>> > I suspect that given your constraints you're just hitting
>>> > max_permutations.
>>> >
>>> > All that code is still there, so it seems most likely that you just
>>> > don't have max_permutations high enough, or that your granularity on
>>> the
>>> > sequence is too high (e.g. you're using a step size of .01, and
>>> should
>>> > try .005)
>>> >
>>> > --
>>> > Brian G. Peterson
>>> > http://braverock.com/brian/
>>> > Ph: 773-459-4973
>>> > IM: bgpbraverock
>>> > _______________________________________________
>>> > GSoC-PortA mailing list
>>> > GSoC-PortA at lists.r-forge.r-project.org
>>> > http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>>> >
>>>
>>>
>>> _______________________________________________
>>> GSoC-PortA mailing list
>>> GSoC-PortA at lists.r-forge.r-project.org
>>> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>>>
>>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>



From rossbennett34 at gmail.com  Tue Sep 24 19:59:19 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Tue, 24 Sep 2013 10:59:19 -0700
Subject: [GSoC-PortA] Random portfolios
In-Reply-To: <92768f15249e53f2546f32e09f48d3b7.squirrel@mail.braverock.com>
References: <0219d0832454daa3b2ad9b43904f479f.squirrel@mail.braverock.com>
 <5241A2A3.60902@braverock.com>
 <dd2e8933911a09cbd8d6130d47f4ad2c.squirrel@mail.braverock.com>
 <CAEESW=UpNLWQCEqL4J6YpTa8HqVYnC_juGjyJNA=P9NVuEwBAQ@mail.gmail.com>
 <CAEESW=V4u-DRdqtqpgG91KWmF9czgqSiwm3XvWxnBP2h3A8D-A@mail.gmail.com>
 <92768f15249e53f2546f32e09f48d3b7.squirrel@mail.braverock.com>
Message-ID: <CAEESW=Uj_k99HO=bxvjt2RMxCMdM2PC2-2KazQUae=adiB7Z3g@mail.gmail.com>

The check for min_sum and max_sum is done right away in
randomize_portfolio_v2. The main reason why I added this check and wiggle
room for min_sum and max_sum inside of the function is to speed up
generating the random portfolio and ensure that a reasonable number of
portfolios can be generated.

Another logical place for this check would be in the check_constraints
function, this would prevent portfolios being eliminated. Even if we do
this check here, constrained_objective will penalize a large number of sets
of weights that do not sum to exactly 1. I think it also might make sense
to add a check in optimize.portfolio and issue a warning to the user that
min_sum and max_sum may be too restrictive. This will apply to
optimize_method="random" and optimize_method="DEoptim" because we are using
logic from random portfolios as a mapping function in DEoptim.

Ross


On Tue, Sep 24, 2013 at 9:52 AM, Peter Carl <peter at braverock.com> wrote:

> Thanks, that does work.  Should the check done in randomize_portfolio_v2
> be moved up the chain to catch that issue earlier?
> --
> Peter Carl
> http://www.braverock.com/peter
>
> > The reason for fewer random portfolios being generated is due to the
> > leverage constraints in init.portf. There is a block of code in
> > randomize_portfolio_v2 (which is called by rp_sample) that will check for
> > a
> > difference in min_sum and max_sum. For example, if min_sum=1 and
> > max_sum=1,
> > we temporarily modify min_sum=0.99 and max_sum=1.01 so that random
> > portfolios can be generated.
> >
> > Then in random_portfolios, there is a block of code that eliminates
> > portfolios that do not satisfy the constraints with the check_constraints
> > function. This takes place for random portfolios generated by the sample,
> > simplex, and grid method. Because rp_sample will generate portfolios with
> > weights that sum from 0.99 to 1.01, there are several portfolios that
> > violate leverage constraints of min_sum=1 and max_sum=1 and therefore
> will
> > be eliminated.
> >
> > If you change the init.portf leverage constraints to min_sum=0.99 and
> > max_sum=1.01 you should generate 1000 portfolios.
> >
> > I'll add some of this content to the @details in random_portfolios to
> > explain how the function is sensitive to leverage constraints.
> >
> > Thanks,
> > Ross
> >
> >
> >
> >
> > On Tue, Sep 24, 2013 at 8:15 AM, Ross Bennett
> > <rossbennett34 at gmail.com>wrote:
> >
> >> Thanks for making me aware of this. I'll take a closer look and try to
> >> figure out what is going on.
> >>
> >> Ross
> >> On Sep 24, 2013 8:03 AM, "Peter Carl" <peter at braverock.com> wrote:
> >>
> >>> Fair point.  I get the same result when I use high values for
> >>> max_permutations.  That attribute should probably be referenced in the
> >>> function documentation under details, so that users know it can be
> >>> passed
> >>> through dots.
> >>>
> >>> Same result though.  When I call rp_sample directly:
> >>> rp_sample(init.portf, permutations=1000)
> >>> ... I get 1000 rows back.
> >>>
> >>> So something's happening in the dispatch code?
> >>>
> >>> pcc
> >>> --
> >>> Peter Carl
> >>> http://www.braverock.com/peter
> >>>
> >>> > On 09/24/2013 09:28 AM, Peter Carl wrote:
> >>> >> The random_portfolios function isn't generating the correct number
> >>> of
> >>> >> permutations.
> >>> >>
> >>> >>> >random_portfolios(portfolio=init.portf, permutations=1000)
> >>> >> gives me a result with 317 weight vectors, rather than 1000.
> >>> >>
> >>> >> I think that there's a loop missing: when the number of lines is
> >>> less
> >>> >> than
> >>> >> permutations, the function needs to generate more, check for unique
> >>> >> solutions, and repeat until there are (in this case) 1000 weight
> >>> >> vectors.
> >>> >>
> >>> >> Although (and it's difficult to tell), on their own the charts seem
> >>> to
> >>> >> generate about the right number?  Or maybe not...
> >>> >
> >>> > I suspect that given your constraints you're just hitting
> >>> > max_permutations.
> >>> >
> >>> > All that code is still there, so it seems most likely that you just
> >>> > don't have max_permutations high enough, or that your granularity on
> >>> the
> >>> > sequence is too high (e.g. you're using a step size of .01, and
> >>> should
> >>> > try .005)
> >>> >
> >>> > --
> >>> > Brian G. Peterson
> >>> > http://braverock.com/brian/
> >>> > Ph: 773-459-4973
> >>> > IM: bgpbraverock
> >>> > _______________________________________________
> >>> > GSoC-PortA mailing list
> >>> > GSoC-PortA at lists.r-forge.r-project.org
> >>> >
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
> >>> >
> >>>
> >>>
> >>> _______________________________________________
> >>> GSoC-PortA mailing list
> >>> GSoC-PortA at lists.r-forge.r-project.org
> >>> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
> >>>
> >>
> > _______________________________________________
> > GSoC-PortA mailing list
> > GSoC-PortA at lists.r-forge.r-project.org
> > http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
> >
>
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130924/c48a47d5/attachment-0001.html>

From brian at braverock.com  Tue Sep 24 21:02:11 2013
From: brian at braverock.com (Brian G. Peterson)
Date: Tue, 24 Sep 2013 14:02:11 -0500
Subject: [GSoC-PortA] Random portfolios
In-Reply-To: <CAEESW=Uj_k99HO=bxvjt2RMxCMdM2PC2-2KazQUae=adiB7Z3g@mail.gmail.com>
References: <0219d0832454daa3b2ad9b43904f479f.squirrel@mail.braverock.com>
 <5241A2A3.60902@braverock.com>
 <dd2e8933911a09cbd8d6130d47f4ad2c.squirrel@mail.braverock.com>
 <CAEESW=UpNLWQCEqL4J6YpTa8HqVYnC_juGjyJNA=P9NVuEwBAQ@mail.gmail.com>
 <CAEESW=V4u-DRdqtqpgG91KWmF9czgqSiwm3XvWxnBP2h3A8D-A@mail.gmail.com>
 <92768f15249e53f2546f32e09f48d3b7.squirrel@mail.braverock.com>
 <CAEESW=Uj_k99HO=bxvjt2RMxCMdM2PC2-2KazQUae=adiB7Z3g@mail.gmail.com>
Message-ID: <5241E1B3.2080704@braverock.com>

On 09/24/2013 12:59 PM, Ross Bennett wrote:
> The check for min_sum and max_sum is done right away in
> randomize_portfolio_v2. The main reason why I added this check and
> wiggle room for min_sum and max_sum inside of the function is to speed
> up generating the random portfolio and ensure that a reasonable number
> of portfolios can be generated.
>
> Another logical place for this check would be in the check_constraints
> function, this would prevent portfolios being eliminated. Even if we do
> this check here, constrained_objective will penalize a large number of
> sets of weights that do not sum to exactly 1. I think it also might make
> sense to add a check in optimize.portfolio and issue a warning to the
> user that min_sum and max_sum may be too restrictive. This will apply to
> optimize_method="random" and optimize_method="DEoptim" because we are
> using logic from random portfolios as a mapping function in DEoptim.
>

I think that when using random portfolios, the leverage constraint needs 
to be relaxed somewhat, or the generation just takes too long.

That's why those exist as parameters.  a 'full_investment' constraint is 
nice, but rather impractical when the time to generate gets to be very high.

I'd just expost the min_sum and max_sum anywhere they aren't already 
exposed, and I'd add a warning for the user if both are 1.

-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock

From peter at braverock.com  Sat Sep 28 20:53:24 2013
From: peter at braverock.com (Peter Carl)
Date: Sat, 28 Sep 2013 13:53:24 -0500
Subject: [GSoC-PortA] Problem with ROI solvers?
Message-ID: <772ebf549d1163e7e03e063f8f47621e.squirrel@mail.braverock.com>

I hit a bump in the road a couple of days ago when I looked at the two
attached charts.  One shows the mean-ETL of a set of different objectives
against a cloud of random portfolios.  The objectives that can be are
calculated through ROI; I used RP for most of the others and DE for the
risk budget objective.

Note that the cloud of RP portfolios shows portfolios with lower mETL than
the indicated MinmETL portfolio.  Well, maybe the mETL space isn't convex?
 Turns out, you can see the same issue in the attached mean-SD space with
the minSD portfolio.

I went back and re-calculated the RP portfolios to eliminate the wiggle we
usually give the boundaries (a two percent leeway to speed up portfolio
generation) reasoning that those might be the issue.  I generated 10K
RP's, of which about 3K summed exactly to 1.0 (which is plenty).  So I
know that it isn't that those portfolios are out of bounds relative to the
constraints objects.

I've tried to make sure that every objective is using the same
constraints, and I've double-checked my post processing to make sure I
wasn't damaging the output from the optimization runs to get things into
charts.

This suggests to me that it's a deeper problem, although there still just
might be an issue in my code somewhere.
-- 
Peter Carl
http://www.braverock.com/peter
-------------- next part --------------
A non-text attachment was scrubbed...
Name: RP-BUOYS-mETL-ExAnte.png
Type: image/png
Size: 143269 bytes
Desc: not available
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130928/08c8c1e8/attachment-0002.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: RP-BUOY-MeanSD-ExAnte.png
Type: image/png
Size: 145316 bytes
Desc: not available
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130928/08c8c1e8/attachment-0003.png>

From peter at braverock.com  Sat Sep 28 20:56:01 2013
From: peter at braverock.com (Peter Carl)
Date: Sat, 28 Sep 2013 13:56:01 -0500
Subject: [GSoC-PortA] Problem with ROI solvers?
Message-ID: <2c24f9bd6659bf416d8e8d995b10a6dc.squirrel@mail.braverock.com>

Whoops, I hit "send" too early.

That's the gist of the message, though.  I'll check in all my recent
changes and the RP result so that you can reproduce these results.  Let me
know if you have any other ideas or see issues in how I've laid out the
constraint objects.

Thanks in advance,

pcc
-- 
Peter Carl
http://www.braverock.com/peter

I hit a bump in the road a couple of days ago when I looked at the two
attached charts.  One shows the mean-ETL of a set of different objectives
against a cloud of random portfolios.  The objectives that can be are
calculated through ROI; I used RP for most of the others and DE for the
risk budget objective.

Note that the cloud of RP portfolios shows portfolios with lower mETL than
the indicated MinmETL portfolio.  Well, maybe the mETL space isn't convex?
 Turns out, you can see the same issue in the attached mean-SD space with
the minSD portfolio.

I went back and re-calculated the RP portfolios to eliminate the wiggle we
usually give the boundaries (a two percent leeway to speed up portfolio
generation) reasoning that those might be the issue.  I generated 10K
RP's, of which about 3K summed exactly to 1.0 (which is plenty).  So I
know that it isn't that those portfolios are out of bounds relative to the
constraints objects.

I've tried to make sure that every objective is using the same
constraints, and I've double-checked my post processing to make sure I
wasn't damaging the output from the optimization runs to get things into
charts.

This suggests to me that it's a deeper problem, although there still just
might be an issue in my code somewhere.
-- 
Peter Carl
http://www.braverock.com/peter

-------------- next part --------------
A non-text attachment was scrubbed...
Name: RP-BUOYS-mETL-ExAnte.png
Type: image/png
Size: 143269 bytes
Desc: not available
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130928/973763c9/attachment-0002.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: RP-BUOY-MeanSD-ExAnte.png
Type: image/png
Size: 145316 bytes
Desc: not available
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130928/973763c9/attachment-0003.png>

From peter at braverock.com  Sat Sep 28 22:04:48 2013
From: peter at braverock.com (Peter Carl)
Date: Sat, 28 Sep 2013 15:04:48 -0500
Subject: [GSoC-PortA] Problem with ROI solvers?
In-Reply-To: <2c24f9bd6659bf416d8e8d995b10a6dc.squirrel@mail.braverock.com>
References: <2c24f9bd6659bf416d8e8d995b10a6dc.squirrel@mail.braverock.com>
Message-ID: <02f235525a54cb5e17d11b037f1b4fd6.squirrel@mail.braverock.com>

I think I might have found the issue.  In the RP solvers, I was using
clean="boudt", but wasn't passing in anything into the ROI solvers.  That
would be a big difference...

I'll confirm that is the issue later, and come back if it wasn't.

Thanks for listening.

pcc
-- 
Peter Carl
http://www.braverock.com/peter

> Whoops, I hit "send" too early.
>
> That's the gist of the message, though.  I'll check in all my recent
> changes and the RP result so that you can reproduce these results.  Let me
> know if you have any other ideas or see issues in how I've laid out the
> constraint objects.
>
> Thanks in advance,
>
> pcc
> --
> Peter Carl
> http://www.braverock.com/peter
>
> I hit a bump in the road a couple of days ago when I looked at the two
> attached charts.  One shows the mean-ETL of a set of different objectives
> against a cloud of random portfolios.  The objectives that can be are
> calculated through ROI; I used RP for most of the others and DE for the
> risk budget objective.
>
> Note that the cloud of RP portfolios shows portfolios with lower mETL than
> the indicated MinmETL portfolio.  Well, maybe the mETL space isn't convex?
>  Turns out, you can see the same issue in the attached mean-SD space with
> the minSD portfolio.
>
> I went back and re-calculated the RP portfolios to eliminate the wiggle we
> usually give the boundaries (a two percent leeway to speed up portfolio
> generation) reasoning that those might be the issue.  I generated 10K
> RP's, of which about 3K summed exactly to 1.0 (which is plenty).  So I
> know that it isn't that those portfolios are out of bounds relative to the
> constraints objects.
>
> I've tried to make sure that every objective is using the same
> constraints, and I've double-checked my post processing to make sure I
> wasn't damaging the output from the optimization runs to get things into
> charts.
>
> This suggests to me that it's a deeper problem, although there still just
> might be an issue in my code somewhere.
> --
> Peter Carl
> http://www.braverock.com/peter
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>



From rossbennett34 at gmail.com  Sat Sep 28 22:54:10 2013
From: rossbennett34 at gmail.com (Ross Bennett)
Date: Sat, 28 Sep 2013 13:54:10 -0700
Subject: [GSoC-PortA] Problem with ROI solvers?
In-Reply-To: <02f235525a54cb5e17d11b037f1b4fd6.squirrel@mail.braverock.com>
References: <2c24f9bd6659bf416d8e8d995b10a6dc.squirrel@mail.braverock.com>
 <02f235525a54cb5e17d11b037f1b4fd6.squirrel@mail.braverock.com>
Message-ID: <CAEESW=XfT_gC-0v=u8VBUFhdjquTPV12wdXbCmxUivADKsJL=Q@mail.gmail.com>

Peter,

I suspected this might be the case and did confirm it for the results in
the mean-StdDev space. The plot is using the objective measures from the
extractStats output of the EqmETL.RND object and these are calculated with
clean="boudt" whereas the buoys.portfmeas as well as MinSD.ROI are
calculated with clean="none".

>From the graph, it looks like the minimum StdDev for the random portfolios
is 0.0095. This is close to the result I get with the following test:

> R.clean <- Return.clean(R=R, method="boudt")
>
> tmpSD <- vector("numeric", length=nrow(rp))
> tmpSDcleanR <- vector("numeric", length=nrow(rp))
> for(i in 1:nrow(rp)){
+   tmpSD[i] <- StdDev(R=R, weights=rp[i,])
+   tmpSDcleanR[i] <- StdDev(R=R.clean, weights=rp[i,])
+ }
>
> min(tmpSD)
[1] 0.01020511
> min(tmpSDcleanR)
[1] 0.009514874
> as.numeric(MinSD.ROI$objective_measures)
[1] 0.01009001

Ross

On Sat, Sep 28, 2013 at 1:04 PM, Peter Carl <peter at braverock.com> wrote:

> I think I might have found the issue.  In the RP solvers, I was using
> clean="boudt", but wasn't passing in anything into the ROI solvers.  That
> would be a big difference...
>
> I'll confirm that is the issue later, and come back if it wasn't.
>
> Thanks for listening.
>
> pcc
> --
> Peter Carl
> http://www.braverock.com/peter
>
> > Whoops, I hit "send" too early.
> >
> > That's the gist of the message, though.  I'll check in all my recent
> > changes and the RP result so that you can reproduce these results.  Let
> me
> > know if you have any other ideas or see issues in how I've laid out the
> > constraint objects.
> >
> > Thanks in advance,
> >
> > pcc
> > --
> > Peter Carl
> > http://www.braverock.com/peter
> >
> > I hit a bump in the road a couple of days ago when I looked at the two
> > attached charts.  One shows the mean-ETL of a set of different objectives
> > against a cloud of random portfolios.  The objectives that can be are
> > calculated through ROI; I used RP for most of the others and DE for the
> > risk budget objective.
> >
> > Note that the cloud of RP portfolios shows portfolios with lower mETL
> than
> > the indicated MinmETL portfolio.  Well, maybe the mETL space isn't
> convex?
> >  Turns out, you can see the same issue in the attached mean-SD space with
> > the minSD portfolio.
> >
> > I went back and re-calculated the RP portfolios to eliminate the wiggle
> we
> > usually give the boundaries (a two percent leeway to speed up portfolio
> > generation) reasoning that those might be the issue.  I generated 10K
> > RP's, of which about 3K summed exactly to 1.0 (which is plenty).  So I
> > know that it isn't that those portfolios are out of bounds relative to
> the
> > constraints objects.
> >
> > I've tried to make sure that every objective is using the same
> > constraints, and I've double-checked my post processing to make sure I
> > wasn't damaging the output from the optimization runs to get things into
> > charts.
> >
> > This suggests to me that it's a deeper problem, although there still just
> > might be an issue in my code somewhere.
> > --
> > Peter Carl
> > http://www.braverock.com/peter
> >
> > _______________________________________________
> > GSoC-PortA mailing list
> > GSoC-PortA at lists.r-forge.r-project.org
> > http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
> >
>
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/gsoc-porta/attachments/20130928/a4b21ff4/attachment.html>