<div>Dear Roger and Micha,</div>
<div> </div>
<div>Thank you for the reply. I will read carefully your coments, and write back again.</div>
<div>Both you clarified some interesting points to me. </div>
<div> </div>
<div>cheers,</div>
<div> </div>
<div>milton</div>
<div>brazil=toronto<br><br></div>
<div class="gmail_quote">2009/6/10 Micha Silver <span dir="ltr"><<a href="mailto:micha@arava.co.il">micha@arava.co.il</a>></span><br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">Hello Milton<br><br>Roger's answer was, as always, both complete and to the point.<br><br>As a further exercise, I took a small region of 540000 cells with floating point values, and using the "feature=area" option to r.to.vect I created a vector map of polygons. It produced over 360000 polygons. Most will be polygons of 1 cell in size (from the original raster). I assume that's *not* what you're looking for...<br>
<br>-- <br><font color="#888888"><br>Micha</font>
<div>
<div></div>
<div class="h5"><br><br><br>Roger Bivand wrote:<br><br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">I think that r.to.vect wants to build a line structure, like river channels,<br>but sees all the raster cells occupied, so no linear structure, and the<br>
advice to thin first is then appropriate. If this is connected to your<br>question about calculating a measure of spatial autocorrelation for the<br>raster data, then I suspect that you do not need polygons but rather points,<br>
where r.out.xyz may be helpful, followed by v.in.ascii if you will be using<br>GRASS downstream, or if you want to emit a shapefile for GeoDa (another<br>posting).<br><br>If you really want to calculate a measure of spatial autocorrelation for<br>
your raster, I suggest copying the raster to R with readRAST6, creating the<br>neighbour list with dnearneigh() with max. distance the greater of ewres and<br>nsres, and proceeding from there in the usual way. But please consider the<br>
inevitable fact that unless the resolution of your raster matches the<br>"natural" support of the phenomenon of interest, the observed<br>autocorrelation will certainly be driven by your having multiple<br>neighbouring "observations" of each "entity", in addition to not having<br>
demeaned (detrended) the data. This means that any results will almost<br>certainly be spurious.<br><br>Hope this helps,<br><br>Roger<br><br><br>Milton Cezar Ribeiro wrote:<br> <br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">Dear Grass-Gurus,<br><br>I have a 2400x2200 raster image with values ranging<br>from 0.1 to 42, in float format. Now I need<br>
vetororize the image, on the way that each pixel<br>come to be a polygon and the pixel value be stored as<br>attribute.<br><br>I am trying to do this using:<br>r.to.vect input=temp71.img output=temp71_img_integer_vect_200m --o -b<br>
<br>but grass return the following error messages:<br><br>GRASS 6.4.0svn (newLocation):C:/GRASS-6-SVN/msys/home/mjfortin > r.to.vect<br>inpu<br>t=temp71.img output=temp71_img_integer_vect_200m --o -b<br>WARNING: Vector map <temp71_img_integer_vect_200m> already exists and will<br>
be overwritten<br>WARNING: Table <temp71_img_integer_vect_200m> linked to vector map<br> <temp71_img_integer_vect_200m> does not exist<br>Extracting lines...<br>ERROR: Raster map is not thinned properly.<br>
Please run r.thin.<br>By the way, I am running grass under a WinXp 64bit.<br>Any help are welcome.<br><br>Cheers<br><br>milton<br>brazil=toronto<br><br>_______________________________________________<br>grass-user mailing list<br>
<a href="mailto:grass-user@lists.osgeo.org" target="_blank">grass-user@lists.osgeo.org</a><br><a href="http://lists.osgeo.org/mailman/listinfo/grass-user" target="_blank">http://lists.osgeo.org/mailman/listinfo/grass-user</a><br>
<br><br> <br></blockquote><br><br>-----<br>Roger Bivand<br>Economic Geography Section<br>Department of Economics<br>Norwegian School of Economics and Business Administration<br>Helleveien 30<br>N-5045 Bergen, Norway<br>
<br> <br></blockquote><br></div></div></blockquote></div><br>