新来的，请让我知道如果您需要更多信息。
我的目标：我正在使用Rehfeldt气候数据和eBird存在/不存在数据，使用Random Forest模型生成生态位模型。
我的问题：我想要预测整个北美洲的生态位模型。 Rehfeldt气候光栅具有整个大陆上每个单元格的数据值，但是这些被“海洋单元格”中的NAs所包围。请参见此处的图，其中我已将NAs涂成深绿色。如果独立数据集包含NAs，则randomForest :: predict（）无法运行。因此，我希望裁剪我的气候光栅（或设置工作范围？），使predict（）函数仅在包含数据的单元格上运行。
故障排除：
我已经使用不包括光栅的“NA oceans”的较小范围运行了Random Forest模型，并且该模型运行得非常好。因此，我知道NAs是问题。但是，我不想仅为北美洲的一个矩形块预测我的生态位模型。
我使用flowla的方法（此处）裁剪和遮罩了用于北美洲的多边形形状文件的光栅。我希望这将删除NAs，但它并没有。是否有类似的方法可以删除NAs？
我阅读了一些文章，但无法找到一种调整Random Forest代码本身的方法，以使predict（）忽略NAs。这篇文章看起来很相关，但我不确定它是否有助于我的情况。
数据
我的光栅，输入存在/不存在的文本文件以及其他函数的代码在此处。与下面的主要代码一起使用以获得可重复的示例。
代码
require(sp)
require(rgdal)
require(raster)
library(maptools)
library(mapproj)
library(dismo)
library(maps)
library(proj4)
data(stateMapEnv)
# This source code has all of the functions necessary for running the Random Forest models, as well as the code for the function detecting multi-collinearity
source("Functions.R")
# Read in Rehfeldt climate rasters
# these rasters were converted to .img and given WGS 84 projection in ArcGIS
d100 <- raster("d100.img")
dd0 <- raster("dd0.img")
dd5 <- raster("dd5.img")
fday <- raster("fday.img")
ffp <- raster("ffp.img")
gsdd5 <- raster("gsdd5.img")
gsp <- raster("gsp.img")
map <- raster("map.img")
mat <- raster("mat_tenths.img")
mmax <- raster("mmax_tenths.img")
mmin <- raster("mmin_tenths.img")
mmindd0 <- raster("mmindd0.img")
mtcm <- raster("mtcm_tenths.img")
mtwm <- raster("mtwm_tenths.img")
sday <- raster("sday.img")
smrpb <- raster("smrpb.img")
# add separate raster files into one big raster, with each file being a different layer.
rehfeldt <- addLayer(d100, dd0, dd5, fday, ffp, gsdd5, gsp, map, mat, mmax, mmin, mmindd0, mtcm, mtwm, sday, smrpb)
# plot some rasters to make sure everything worked
plot(d100)
plot(rehfeldt)
# read in presence/absence data
LAZB.INBUtemp <- read.table("LAZB.INBU.txt", header=T, sep = "\t")
colnames(LAZB.INBUtemp) <- c("Lat", "Long", "LAZB", "INBU")
LAZB.INBUtemp <- LAZB.INBUtemp[c(2,1,3,4)]
LAZB.INBU <- LAZB.INBUtemp
latpr <- (LAZB.INBU$Lat)
lonpr <- (LAZB.INBU$Long)
sites <- SpatialPoints(cbind(lonpr, latpr))
LAZB.INBU.spatial <- SpatialPointsDataFrame(sites, LAZB.INBU, match.ID=TRUE)
# The below function extracts raster values for each of the different layers for each of the eBird locations
pred <- raster::extract(rehfeldt, LAZB.INBU.spatial)
LAZB.INBU.spatial@data = data.frame(LAZB.INBU.spatial@data, pred)
LAZB.INBU.spatial@data <- na.omit(LAZB.INBU.spatial@data)
# ITERATIVE TEST FOR MULTI-COLINEARITY
# Determines which variables show multicolinearity
cl <- MultiColinear(LAZB.INBU.spatial@data[,7:ncol(LAZB.INBU.spatial@data)], p=0.05)
xdata <- LAZB.INBU.spatial@data[,7:ncol(LAZB.INBU.spatial@data)]
for(l in cl) {
cl.test <- xdata[,-which(names(xdata)==l)]
print(paste("REMOVE VARIABLE", l, sep=": "))
MultiColinear(cl.test, p=0.05)
}
# REMOVE MULTI-COLINEAR VARIABLES
for(l in cl) { LAZB.INBU.spatial@data <- LAZB.INBU.spatial@data[,-which(names(LAZB.INBU.spatial@data)==l)] }
################################################################################################
# FOR LAZB
# RANDOM FOREST MODEL AND RASTER PREDICTION
require(randomForest)
# NUMBER OF BOOTSTRAP REPLICATES
b=1001
# CREATE X,Y DATA
# use column 3 for LAZB and 4 for INBU
ydata <- as.factor(LAZB.INBU.spatial@data[,3])
xdata <- LAZB.INBU.spatial@data[,7:ncol(LAZB.INBU.spatial@data)]
# PERCENT OF PRESENCE OBSERVATIONS
( dim(LAZB.INBU.spatial[LAZB.INBU.spatial$LAZB == 1, ])[1] / dim(LAZB.INBU.spatial)[1] ) * 100
# RUN RANDOM FORESTS MODEL SELECTION FUNCTION
# This model is using the model improvement ratio to select a final model.
pdf(file = "LAZB Random Forest Model Rehfeldt.pdf")
( rf.model <- rf.modelSel(x=xdata, y=ydata, imp.scale="mir", ntree=b) )
dev.off()
# RUN RANDOM FORESTS CLASS BALANCE BASED ON SELECTED VARIABLES
# This code would help in the case of imbalanced sample
mdata <- data.frame(y=ydata, xdata[,rf.model$SELVARS])
rf.BalModel <- rfClassBalance(mdata[,1], mdata[,2:ncol(mdata)], "y", ntree=b)
# CREATE NEW XDATA BASED ON SELECTED MODEL AND RUN FINAL RF MODEL
sel.vars <- rf.model$PARAMETERS[[3]]
rf.data <- data.frame(y=ydata, xdata[,sel.vars])
write.table(rf.data, "rf.data.txt", sep = ",", row.names = F)
# This the code given to me; takes forever to run for my dataset (I haven't tried to let it finish)
# ( rf.final <- randomForest(y ~ ., data=rf.data, ntree=b, importance=TRUE, norm.votes=TRUE, proximity=TRUE) )
# I use this form because it's a lot faster
( rf.final <- randomForest(x = rf.data[2:6], y = rf.data$y, ntree=1000, importance=TRUE, norm.votes=TRUE, proximity=F) )
################################################################################################
# MODEL VALIDATION
# PREDICT TO VALIDATION DATA
# Determines the percent correctly classified
rf.pred <- predict(rf.final, rf.data[,2:ncol(rf.data)], type="response")
rf.prob <- as.data.frame(predict(rf.final, rf.data[,2:ncol(rf.data)], type="prob"))
ObsPred <- data.frame(cbind(Observed=as.numeric(as.character(ydata)),
PRED=as.numeric(as.character(rf.pred)), Prob1=rf.prob[,2],
Prob0=rf.prob[,1]) )
op <- (ObsPred$Observed == ObsPred$PRED)
( pcc <- (length(op[op == "TRUE"]) / length(op))*100 )
# PREDICT MODEL PROBABILITIES RASTER
# The first line of code says what directory I'm working, and then what folder in that directory has the raster files that I'm using to predict the range
# The second line defines the x variable, wich is my final Random Forest model
rpath=paste('~/YOURPATH', "example", sep="/")
xvars <- stack(paste(rpath, paste(rownames(rf.final$importance), "img", sep="."), sep="/"))
tr <- blockSize(xvars)
s <- writeStart(xvars[[1]], filename=paste('~/YOURPATH', "prob_LAZB_Rehfeldt.img", sep="/"), overwrite=TRUE)
for (i in 1:tr$n) {
v <- getValuesBlock(xvars, row=tr$row[i], nrows=tr$nrows[i])
v <- as.data.frame(v)
rf.pred <- predict(rf.final, v, type="prob")[,2]
writeValues(s, rf.pred, tr$row[i])
}
s <- writeStop(s)
prob_LAZB <- raster("prob_LAZB_Rehfeldt.img")
# Write range prediction raster to .pdf
pdf(file="LAZB_range_pred.pdf")
plot(prob_LAZB)
map("state", add = TRUE)
dev.off()
Thanks!!