[R] screen resolution effects on graphics

Mon Aug 28 20:29:32 CEST 2006

Prof Brian Ripley a écrit :
> On Mon, 28 Aug 2006, Charles Annis, P.E. wrote:
>
>   
>> Greetings, R-Citizens:
>>
>> I have the good fortune of working with a 19" 1280 X 1024 pixel monitor.  My
>>     
>
> (Similar to our student lab has used for many years.)
>
>   
>> R-code produces nice-looking graphics on this machine but the same code
>> results in crowded plots on an older machine with 800 X 600 resolution.  In
>> hindsight this seems obvious, but I didn't anticipate it.
>>     
>
> It is not obvious to me: I have never experienced it.  What OS and 
> graphics device is this?
>
> Almost all of R's graphics is independent of the screen resolution (the 
> exception being the bitmapped devices such as jpeg), with things sized in 
> inches or points. My machines are 1600x1200 (apart from 1280x800 on my 
> laptop), so I meet a considerable reduction when using a computer 
> projector, and my plots do not look crowded.
>
> However, one issue is when the OS has a seriously incorrect setting for 
> the screen resolution and so does not give the sizes asked for by R.  We 
> have seen that on both Linux and Windows, and the windows() device has 
> arguments to set the correct values.  (On X11 you should be able to set 
> this in Xconfig files.)
>
> If this is Windows, check carefully the description of the initial screen 
> size in ?windows.  That can have unexpected effects on physically small 
> screens.
>
> At one time the X11() device was set up to assume 75dpi unless the 
> reported resolution was 100+/-0.5dpi.  My then monitor reported 99.2 dpi 
> and so things came out at 3/4 of the intended size.  We fixed that quite a 
> while back.
>
>   
>> My code will be used on machines with varying graphics (and memory)
>> capacity.  Is there a way I can check the native resolution of the machine
>> so that I can make adjustments to my code for the possible limitations of
>> the machine running it?
>>     
>
> Only via C code, which is how R does it.
Hi,

Javascript knows, can we ask him ?

I mean, if I do that in R :

a <- tempfile()
cat('<html><script type="text/javascript"> document.write(screen.width) 
;  </script></html>', file=a)
browseURL(a)

I get "1920" in my browser's window. Can R read it ?

Romain