> Le 24 oct. 2014 à 09:23, Sarah <sarahschmi...@gmail.com> a écrit :
>
> Thank you very much, it helped a lot!
>
> I just have another question know. I want to make plot for every species. I
> just add the function « plot correlog » to the previous function and I have
> now the following script:
>
> ddeg.correlog.list <- lapply(9:20, function(p)
> plot.correlog(correlog(plant[plant[,p]=="1", 2], plant[plant[,p]=="1", 3],
> plant[plant[,p]=="1", 4],increment=2500)))
>
> It’s working, but I wanted to know if there is a way to save each plot. I
> found that I can use the dev.off function or the ggplot function of the
> package ggplot2, but I can’t figure out how to use it within the lapply
> function. Do you think there is a way?
>
> Thank you for your help!
>
> Sarah
>
>> Le 23 oct. 2014 à 17:49, Rui Barradas <ruipbarra...@sapo.pt
>> <mailto:ruipbarra...@sapo.pt>> a écrit :
>>
>> Hello,
>>
>> Yes, you can use lapply. Maybe something like the following. Note that the
>> result is a list with one member per species. (Untested).
>>
>> ddeg.correlog.list <- lapply(9:11, function(p)
>> correlog(plant[plant[,p]=="1", 2], plant[plant[,p]=="1", 3],
>> plant[plant[,p]=="1", 4]))
>>
>>
>> Hope this helps,
>>
>> Rui Barradas
>>
>> Em 23-10-2014 16:06, Sarah escreveu:
>>> Hello List,
>>>
>>> I have a database which consist of 912 plots. For each plot, I have the
>>> presence/absence information of 260 species of plants and also 5 different
>>> environmental variables (ddeg, mind, srad, slp, topo).
>>>
>>> The dataframe looks like this:
>>>
>>> Plot_Number X Y ddeg mind srad slp topo
>>> Galium_mollugo Gentiana_nivalis
>>> 1 1 557747.6 149726.8 2598 -625 236363 8 176
>>> 0 0
>>> 2 2 572499.4 145503.5 2178 -176 161970 14 -137
>>> 0 0
>>> 3 3 579100.4 151800.4 1208 632 267572 33 129
>>> 0 0
>>> 4 4 581301.7 150300.1 1645 83 246633 15 -70
>>> 0 0
>>> 5 5 579838.7 124770.9 1102 1637 158300 2 -231
>>> 0 0
>>> 6 6 577011.1 121328.6 731 2223 180286 41 70
>>> 0 0
>>>
>>> Now, what I wanted to do is to calculate spatial autocorrelation of each
>>> environmental variable for each species, but only for the plots where the
>>> species is present.
>>>
>>> I will use the correlog function of the package ncf (doesn’t really
>>> matter). The correlog function work with an argument X which is the
>>> longitude, an argument Y which is the latitude and an argument Z which is
>>> the variable you want to test for autocorrelation (in my case, the
>>> different environmental variables).
>>>
>>> So, for the first species I have the following script:
>>>
>>> ddeg.correlog.9<-correlog(plant[plant[,9]=="1", 2], plant[plant[,9]=="1",
>>> 3], plant[plant[,9]=="1", 4])
>>>
>>> X = plant[plant[,9]=="1", 2] —> only the X coordinate where my species 9
>>> is present
>>> Y = plant[plant[,9]=="1", 3] —> only the Y coordinate where my species 9
>>> is present
>>> Z = plant[plant[,9]=="1", 4] —> only the value of the environmental
>>> variable where my species 9 is present
>>>
>>> plant: dataframe
>>> 9: column corresponding to the first species
>>> 2: column corresponding to the X coordinate
>>> 3: column correspondind to the Y coordinate
>>> 4: column corresponding to the first environmental variable
>>>
>>> So my question is: how do I repeat this script for every species
>>> (basically, I just have to change the number « 9 » into 10, 11 and so on) ?
>>>
>>> I try to write a function but I’m new in R and didn’t manage to do it. I
>>> was also considering to use the function « lapply », but I don’t think I
>>> can use it in this case, isn’t it?
>>>
>>> Thank you very much for your help !
>>>
>>> Sarah
>>> ______________________________________________
>>> R-help@r-project.org <mailto:R-help@r-project.org> mailing list
>>> https://stat.ethz.ch/mailman/listinfo/r-help
>>> <https://stat.ethz.ch/mailman/listinfo/r-help>
>>> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
>>> and provide commented, minimal, self-contained, reproducible code.
>>>
>
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
