[R-sig-Geo] calculating integral for spectral signatures

Mon Nov 24 05:50:36 CET 2008

Enrico,

I think something like this should work for your purpose:

x <- c(1,2,3,5,7,12,13)
y <- c(1,2,9,11,7,20,10)

y1 <- y[-length(y)]
y2 <- y[-1]
dy <- y2 - y1
dx <- x[-1] - x[-length(x)]
dxy <- dx * (y1 + 0.5 * dy)
integral <- sum(dxy)

Robert

> Today's Topics:
>
>   1.  calculating integral for spectral signatures (Enrico Guastaldi)
>   2. posting on behalf of Kevin, Yen (Roger Bivand)
>   3. Re: WMS, WFS, WCS an WPS for R (Roger Bivand)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Sat, 22 Nov 2008 12:59:51 +0100
> From: "Enrico Guastaldi" <enrico.guastaldi at gmail.com>
> Subject: [R-sig-Geo]  calculating integral for spectral signatures
> To: r-sig-geo at stat.math.ethz.ch
> Message-ID:
>        <7ce8d7d30811220359n755d2e22k488ca33c10a6d509 at mail.gmail.com>
> Content-Type: text/plain
>
> Dear list members,
> Does anyone know how to calculate in R integral of bivariate distribution of
> discrete points suche as the following
> x       y
> 1       1
> 2       2
> 3       9
> 5       11
> 7       7
> 12      20
> 13      10
> But I've thousands of x,y points with x always increasing: I'm talking about
> spectral signature.
> I think I need some function that "constructs" (not interpolates) a polyline
> from these x,y points and then calculate the underlying area, because I've
> to compare several distributions.
>
> Could anyone help me?
>
> Thanks
>
> --
> Enrico Guastaldi
> Centro di GeoTecnologie dell'Università degli Studi Siena,
> Via Vetri Vecchi, 34
> 52027 - San Giovanni Valdarno (AR)
> Italy
>
> Tel.   +39 349 4025017
> Fax.   +39 055 9119439
> url:   www.geotecnologie.unisi.it
>
> Io uso Linux!
> user #466775 counter.li.org
>
>
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> Please try to avoid to send me .dwg, .doc, .xls, .ppt files.
> I prefer free formats.
> http://en.wikipedia.org/wiki/Open_format
>
> Please consider the environment before printing this e-mail
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>
>        [[alternative HTML version deleted]]
>
>
>
> ------------------------------
>
> Message: 2
> Date: Sat, 22 Nov 2008 13:42:39 +0100 (CET)
> From: Roger Bivand <Roger.Bivand at nhh.no>
> Subject: [R-sig-Geo] posting on behalf of Kevin, Yen
> To: r-sig-geo at stat.math.ethz.ch
> Message-ID: <alpine.LRH.2.00.0811221337310.7189 at reclus.nhh.no>
> Content-Type: text/plain; charset="iso-8859-15"; Format="flowed"
>
> I'm posting this on behalf Kevin, Yen - the same text was trapped
> yesterday as spam, so this is also a technical issue, and the reason for
> helping in this way:
> -----------------------
> Hi, lists,
>
> I am reading meterials about GWR, but there are some problems puzzling me
> very much:
>
> If there are N observations at N locations g(g1,????gn),the dependent and
> independent variables are Y(y1,...yn) and X(x1,...xn). The formula for the
> regression is Y=X*Beta, where Beta is the function of location g.
>
> My questions are as follows:
>   1.How many groups should be grouped for regressing? N groups for the N
> locations or M groups (M is a arbitrary number less than N)?
>   2.When the parameter beta(gi) at location gi is estimated, weight Wi is
> used. So how is W used? Are the neighboring k(with in the bandwidth h)
> observations used for calculation?
>   3.Beta is the function of location. Is Beta same as W or expressed as a
> function including W like Beta=W*f(g)?
>
> Many thanks and best wishes
>
> Kevin,Yen
> LIESMARS,Wuhan University,China
>
> --
> Roger Bivand
> Economic Geography Section, Department of Economics, Norwegian School of
> Economics and Business Administration, Helleveien 30, N-5045 Bergen,
> Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
> e-mail: Roger.Bivand at nhh.no
>
> ------------------------------
>
> Message: 3
> Date: Sat, 22 Nov 2008 14:01:16 +0100 (CET)
> From: Roger Bivand <Roger.Bivand at nhh.no>
> Subject: Re: [R-sig-Geo] WMS, WFS, WCS an WPS for R
> To: Barry Rowlingson <b.rowlingson at lancaster.ac.uk>
> Cc: r-sig-geo at stat.math.ethz.ch
> Message-ID: <alpine.LRH.2.00.0811221357040.7189 at reclus.nhh.no>
> Content-Type: text/plain; charset="iso-8859-15"; Format="flowed"
>
> On Sat, 22 Nov 2008, Barry Rowlingson wrote:
>
>> 2008/11/22 Hisaji ONO <hi_ono2001 at ybb.ne.jp>:
>>> Hello.
>>>
>>>  There are lots of services of OGC(Open Geospatial
>>> Consortium:http://www.opengeospatial.org/)'s standard
>>> based Geo-Web ervices incluing WMS(Web Map Service),
>>> WFS(Web Feature Service), WCS(Web Coverage Service) and
>>> WPS(Web Processing Service) all over the world.
>>>
>>>  Does anyone try to use these services from R?
>>
>> Any access to WMS and WFS would probably be best done using GDAL and
>> OGR via the rgdal package.... Let's see...
>>
>> GDAL has a WMS driver, but it seems you do have to create a 'local
>> service description' file. www.gdal.org seems down at the moment, so
>> here's a google cache link:
>>
>> http://216.239.59.132/search?q=cache:21OOLtr9yj0J:www.gdal.org/frmt_wms.html+gdal+wms&hl=en&ct=clnk&cd=1&gl=uk
>>
>> For WFS, there's some recent discussion on the gdal-dev list:
>>
>> http://www.nabble.com/OGR-WFS-driver-td20485363.html
>>
>> so it might be coming soon. Can you wait?
>>
>> To do WFS from scratch in R is probably going to need XML parsing,
>> and then it'll probably also need OGR too unless you want to hand-code
>> understanding the returned GML...
>
> Yes, so OGR needs to be built against the Xerces libraries. I agree that
> WMS and WFS are best handled by using work that is already going on in the
> OSGeo community. An example of R in a a WPS setting is:
>
> Katharina Henneb?hl, Edzer Pebesma:
> Providing R functionality through the OGC Web Processing Service
>
> given at useR! 2008 in Dortmund in August - there is an abstract on the
> conference website. I think that their trial site may be ready before
> long, together with the underlying software.
>
> Roger
>
>>
>> Barry
>>
>> _______________________________________________
>> R-sig-Geo mailing list
>> R-sig-Geo at stat.math.ethz.ch
>> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>>
>
> --
> Roger Bivand
> Economic Geography Section, Department of Economics, Norwegian School of
> Economics and Business Administration, Helleveien 30, N-5045 Bergen,
> Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
> e-mail: Roger.Bivand at nhh.no
>
> ------------------------------
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>
>
> End of R-sig-Geo Digest, Vol 63, Issue 20
> *****************************************
>