Question

我正在尝试使用R包ncdf创建一个多维NetCDF文件。我正在进行一组1500点的气候日常观测，每个点的观测数量约为18250。问题是NetCDF文件的结构（ create.ncdf ）占用4Gb，每个点使文件的大小增加超过3 Gb（ put.var.ncdf ）

这是我正在使用的代码：

# Make a few dimensions we can use
dimX <- dim.def.ncdf( "Long", "degrees", Longvector )
dimY <- dim.def.ncdf( "LAT", "degrees", Latvector )
dimT <- dim.def.ncdf( "Time", "days", 1:18250, unlim=FALSE )

# Make varables of various dimensionality, for illustration purposes
mv <- -9999 # missing value to use
var1d <- var.def.ncdf( "var1d", "units", dimX, mv,prec="double" )
var2d <- var.def.ncdf( "var2d", "units", list(dimX,dimY), mv,prec="double" )
var3d <- var.def.ncdf( "var3d", "units", list(dimX,dimY,dimT), mv,prec="double" )

# Create the test file
nc <- create.ncdf( "writevals.nc", list(var1d,var2d,var3d) )
# !!Creates a nc file with + 4 Gb

# Adding the complete time series for one point (the first point in the list of the dataset)
put.var.ncdf( nc, var3d,dataset[[1]], start=c(Longvector[1],Latvector[1],1),         count=c(1,1,-1))

Longvector和Latvector是从矩阵中取出的向量，每个点都有Long和Lat。数据集是一种列表格式，对于每个点，我都有一个数值列表。

dataset[[1]]=c(0,0,0,9.7,0,7.5,3.6,2.9,0,0.5,....)

我错过了什么或者我应该尝试其他套餐吗？

Answer 1

您的不可重现代码中存在一些错误，通过我的计算，该文件为219Mb（1500 * 18250 * 8字节）。

library(ncdf)

提供前两个dims的向量和数据集以匹配至少一个切片

Longvector = seq(-180, 180, length = 50)
Latvector = seq(-90, 90, length = 30)
dataset <- list(1:18250)

dimX <- dim.def.ncdf("Long", "degrees", Longvector)
dimY <- dim.def.ncdf("LAT", "degrees", Latvector)
dimT <- dim.def.ncdf("Time", "days", 1:18250, unlim = FALSE)

mv <- -9999 
var1d <- var.def.ncdf( "var1d", "units", dimX, mv,prec="double")
var2d <- var.def.ncdf( "var2d", "units", list(dimX,dimY), mv,prec="double")
var3d <- var.def.ncdf( "var3d", "units", list(dimX,dimY,dimT), mv,prec="double")

nc <- create.ncdf( "writevals.nc", list(var1d,var2d,var3d))

Count是维度的索引，而不是轴位置值，因此我们将start更正为1，并使用第3维的计数（长度）（不是-1）。

put.var.ncdf(nc, var3d, dataset[[1]], start = c(1, 1, 1),  count = c(1, 1, length(dataset[[1]])))

close.ncdf(nc)

询问文件大小。

file.info("writevals.nc")$size/1e6
[1] 219.0866

Answer 2

这是mdsumner的答案的更新版本，该版本适用于R（ncdf4）的NetCDF4包。

# Open library
library(ncdf4)

# Get x and y vectors (dimensions)
Longvector = seq(-180, 180, length = 50)
Latvector = seq(-90, 90, length = 30)
# Define data
dataset = list(1:18250)

# Define the dimensions
dimX = ncdim_def("Long", "degrees", Longvector)
dimY = ncdim_def("Lat", "degrees", Latvector)
dimT = ncdim_def("Time", "days", 1:18250)

# Define missing value
mv = -9999

# Define the data
var1d = ncvar_def( "var1d", "units", dimX, mv, prec="double")
var2d = ncvar_def( "var2d", "units", list(dimX,dimY), mv, prec="double")
var3d = ncvar_def( "var3d", "units", list(dimX,dimY,dimT), mv, prec="double")

# Create the NetCDF file
# If you want a NetCDF4 file, explicitly add force_v4=T
nc = nc_create("writevals.nc", list(var1d, var2d, var3d))

# Write data to the NetCDF file
ncvar_put(nc, var3d, dataset[[1]], start=c(1, 1, 1),
    count=c(1, 1, length(dataset[[1]])))

# Close your new file to finish writing
nc_close(nc)

在R中创建多维NetCDF

2 个答案: