[R] Mass 'identify' on 2d-plot

[Evgeniy Kachalin]

Duncan Temple Lang Ð¿Ð¸ÑˆÐµÑ‚:
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
> 
> 
> 
> 
> Barry Rowlingson wrote:
> 
>>Evgeniy Kachalin wrote:
>>
>>
>>
>>>What is ability in R to graphically (per mouse) define some area and to 
>>>select all the cases felt in it?
>>>
>>>'identify' is OK for 5-10 cases, but what if cases=1000?
>>
>>
>>  You can use 'locator' to let the user click a number of points to 
>>define a polygon, and then use one of the point-in-polygon functions 
>>provided by one of the spatial packages to work out whats in your polygon.
>>
>>  Look at splancs, spatstat, sp - pretty much anything beginning with 
>>'sp' - on CRAN.
>>
>>  In splancs you can just do:
>>
>>  poly = getpoly()
>>
>>  - which lets the user draw a polygon on screen, then:
>>
>>  inPoly = inpip(xypts,poly)
>>  points(xypts[inpip,], pch=19,col="red")
>>
>>  and that will plot the selected points in solid red dots.
>>
>>  I don't think there's a way to draw a freehand figure on an R plot, 
>>you have to go click, click, click, and draw straight lines.
> 
> 
> 
> FWIW, there is an "experimental" package on the
> Omegahat site (and repository) named
> 
>    RGtkIPrimitives
> 
> that works with the gtkDevice only to do
> rubber banding and free form region identification.
> 

Ho do I do GTK device on my WinXP? No way? ;)

-- 
Evgeniy