我正在获取玉米产量和收获面积的 netcdf,将分辨率从 2.5 弧分缩小到 0.5 度,然后将整个数据转换为 XYZ 格式,这样我就可以更轻松地与我的数据“对话”有这种格式。(我想我可以将其他数据转换为矩阵形式,但我喜欢 xyz。)
数据在这里。
下面的代码定义了一些函数来计算收获面积和平均产量的总产量,然后它在查询 netcdf 时使用一些“馈线”数据,然后它使用 plyr 循环通过馈线,提取数据,应用函数,然后保存在 xyz 中。它可以工作,但只运行其中一个文件大约需要 30 分钟,而且我有 100 多个。任何有关优化此代码的方法的建议都会很棒。提取更大的数据块并将函数应用于它们会更快吗?就像,也许是地球的整个条纹?我怎么会先验地知道这是否会更快?
rm(list=ls())
library(ncdf)
library(reshape)
library(plyr)
library(sp)
library(maps)
library(rgeos)
library(maptools)
library(rworldmap)
getha = function(lat,size=lat[1]-lat[2]){
lat1 = (lat-size/2)*pi/180
lat2 = (lat+size/2)*pi/180
lon1 = (0-size/2)*pi/180 #lon doesn't come in because all longitudes are great circles
lon2 = (0+size/2)*pi/180
6371^2 * abs(sin(lat1)-sin(lat2))*abs(lon1-lon2)*100 #6371 is the radius of the earth and 100 is the number of ha in a km^2
}
gethamat = function(mat,latvec,blocksize=6){
a = getha(latvec)
areamat = matrix(rep(a,blocksize),blocksize)
area = t(mat)*areamat #The matrix is transposed because the dimensions of the Ramankutty's netcdf's are switched
area
}
getprod = function(yieldblock,areablock,latvec){
b = gethamat(areablock,latvec)
sum(t(yieldblock)*b,na.rm=TRUE)
}
lat = as.matrix(seq(from=89.75,to=-89.75,by=-.5))
lon = as.matrix(seq(from=-179.75,to=179.75,by=.5))
lon = seq.int(from=1,to=4320,by=6)
lat = seq.int(from=1,to=2160,by=6)
lat = rep(lat,720)
lon = t(matrix(lon,720,360))
lon = as.data.frame(lon)
l = reshape(lon,direction="long",varying=list(colnames(lon)),v.names = "V")
coords = data.frame(cbind(l[,2],lat))
colnames(coords) = c("lng","lat")
feeder = coords
head(feeder)
maize.nc = open.ncdf('maize_5min.nc')
getcrops = function(feed,netcdf,var="cropdata"){
yieldblock = get.var.ncdf(netcdf,varid=var,start = c(as.numeric(feed[1]),as.numeric(feed[2]),2,1),count = c(6,6,1,1))
areablock = get.var.ncdf(netcdf,varid=var,start = c(as.numeric(feed[1]),as.numeric(feed[2]),1,1),count = c(6,6,1,1))
lat = get.var.ncdf(netcdf,varid="latitude",start = feed[2],count = 6)
prod = getprod(yieldblock,areablock,lat)
lon = get.var.ncdf(netcdf,varid="longitude",start = feed[1],count = 6)
#print(c(mean(lat),mean(lon)))
data.frame(lat=mean(lat),lon = mean(lon),prod=prod)
}
out = adply(as.matrix(feeder),1,getcrops,netcdf=maize.nc,.parallel=FALSE)
提前致谢。