R terra -01
Naimul Islam
2024-09-20
call the terra package
library("terra")## terra 1.7.78raster with 100 cells
r <- rast(ncol=10, nrow=10)
ncell(r)## [1] 100hasValues(r)## [1] FALSE# use the 'values' function, e.g.,
values(r) <- 1:ncell(r)
# or
set.seed(0)
values(r) <- runif(ncell(r))
hasValues(r)## [1] TRUEsources(r)## [1] ""values(r)[1:10]## [1] 0.8966972 0.2655087 0.3721239 0.5728534 0.9082078 0.2016819 0.8983897
## [8] 0.9446753 0.6607978 0.6291140## [1] 0.8966972 0.2655087 0.3721239 0.5728534 0.9082078 0.2016819 0.8983897
## [8] 0.9446753 0.6607978 0.6291140
plot(r, main='Raster with 100 cells')
raster map from file
filename <- system.file("ex/meuse.tif", package="terra")
filename## [1] "C:/Users/154455/AppData/Local/R/win-library/4.4/terra/ex/meuse.tif"r <- rast(filename)
sources(r)## [1] "C:/Users/154455/AppData/Local/R/win-library/4.4/terra/ex/meuse.tif"hasValues(r)## [1] TRUEplot(r, main='SpatRaster from file')
r logo
logo <- rast(system.file("ex/logo.tif", package="terra"))
plot(logo)
data points
p <- matrix(c(48, 48, 48, 53, 50, 46, 54, 70, 84, 85, 74, 84, 95, 85,
66, 42, 26, 4, 19, 17, 7, 14, 26, 29, 39, 45, 51, 56, 46, 38, 31,
22, 34, 60, 70, 73, 63, 46, 43, 28), ncol=2)
a <- matrix(c(22, 33, 64, 85, 92, 94, 59, 27, 30, 64, 60, 33, 31, 9,
99, 67, 15, 5, 4, 30, 8, 37, 42, 27, 19, 69, 60, 73, 3, 5, 21,
37, 52, 70, 74, 9, 13, 4, 17, 47), ncol=2)
xy <- rbind(cbind(1, p), cbind(0, a))
xy## [,1] [,2] [,3]
## [1,] 1 48 7
## [2,] 1 48 14
## [3,] 1 48 26
## [4,] 1 53 29
## [5,] 1 50 39
## [6,] 1 46 45
## [7,] 1 54 51
## [8,] 1 70 56
## [9,] 1 84 46
## [10,] 1 85 38
## [11,] 1 74 31
## [12,] 1 84 22
## [13,] 1 95 34
## [14,] 1 85 60
## [15,] 1 66 70
## [16,] 1 42 73
## [17,] 1 26 63
## [18,] 1 4 46
## [19,] 1 19 43
## [20,] 1 17 28
## [21,] 0 22 8
## [22,] 0 33 37
## [23,] 0 64 42
## [24,] 0 85 27
## [25,] 0 92 19
## [26,] 0 94 69
## [27,] 0 59 60
## [28,] 0 27 73
## [29,] 0 30 3
## [30,] 0 64 5
## [31,] 0 60 21
## [32,] 0 33 37
## [33,] 0 31 52
## [34,] 0 9 70
## [35,] 0 99 74
## [36,] 0 67 9
## [37,] 0 15 13
## [38,] 0 5 4
## [39,] 0 4 17
## [40,] 0 30 47# extract predictor values for points
e <- extract(logo, xy[,2:3])
e## red green blue
## 1 194 205 237
## 2 147 161 208
## 3 142 156 203
## 4 221 228 254
## 5 162 173 229
## 6 115 129 174
## 7 195 202 230
## 8 179 187 233
## 9 110 116 152
## 10 34 40 66
## 11 240 248 255
## 12 162 167 171
## 13 189 191 180
## 14 102 99 90
## 15 187 184 177
## 16 196 196 184
## 17 171 171 163
## 18 187 189 176
## 19 13 12 10
## 20 181 181 173
## 21 255 255 255
## 22 255 255 255
## 23 246 249 242
## 24 246 249 242
## 25 253 255 254
## 26 255 255 255
## 27 254 255 250
## 28 247 249 238
## 29 255 255 255
## 30 255 255 253
## 31 245 247 244
## 32 255 255 255
## 33 255 255 255
## 34 253 253 253
## 35 255 255 255
## 36 254 255 255
## 37 255 255 255
## 38 255 255 255
## 39 255 255 255
## 40 255 255 255# combine with response
v <- data.frame(cbind(pa=xy[,1], e))
v## pa red green blue
## 1 1 194 205 237
## 2 1 147 161 208
## 3 1 142 156 203
## 4 1 221 228 254
## 5 1 162 173 229
## 6 1 115 129 174
## 7 1 195 202 230
## 8 1 179 187 233
## 9 1 110 116 152
## 10 1 34 40 66
## 11 1 240 248 255
## 12 1 162 167 171
## 13 1 189 191 180
## 14 1 102 99 90
## 15 1 187 184 177
## 16 1 196 196 184
## 17 1 171 171 163
## 18 1 187 189 176
## 19 1 13 12 10
## 20 1 181 181 173
## 21 0 255 255 255
## 22 0 255 255 255
## 23 0 246 249 242
## 24 0 246 249 242
## 25 0 253 255 254
## 26 0 255 255 255
## 27 0 254 255 250
## 28 0 247 249 238
## 29 0 255 255 255
## 30 0 255 255 253
## 31 0 245 247 244
## 32 0 255 255 255
## 33 0 255 255 255
## 34 0 253 253 253
## 35 0 255 255 255
## 36 0 254 255 255
## 37 0 255 255 255
## 38 0 255 255 255
## 39 0 255 255 255
## 40 0 255 255 255GLM
#build a model, here with glm
model <- glm(formula=pa~., data=v)
#predict to a raster
r1 <- predict(logo, model)
plot(r1)
points(p, bg='blue', pch=21)
points(a, bg='red', pch=21)
pca
sr <- values(spatSample(logo, 100, as.raster=TRUE))
pca <- prcomp(sr)
x <- predict(logo, pca)
plot(x)
Reference - https://rspatial.org/pkg/9-predict.html