Classify All Unclassified Cells

Classify all cells in classVector that have not yet been classified based on contiguity and continuity conditions.

classify.all(attTbl, ngbList, rNumb = FALSE, classVector)

Arguments

attTbl

data.frame, the attribute table returned by the function attTbl.

ngbList

list, the list of neighborhoods returned by the function ngbList.

rNumb

logic, the neighborhoods of the argument ngbList are identified by cell numbers (rNumb=FALSE) or by row numbers (rNumb=TRUE) (see ngbList). It is advised to use row numbers for large rasters.

classVector

numeric vector, defines the cells in the attribute table that have already been classified. See conditions for more information about class vectors.

Value

Update classVector with the new cells that were classified by the function. See conditions for more details about class vectors.

Details

The neighborhood of unclassified cells is considered. Among neighbors, the class with the highest number of members is assigned to the unclassified cell. If two or more classes have the same number of members, then one of these classes is assigned randomly to the unclassified cell. The function considers class continuity, thus, even cells that at first were not contiguous to any class will be classified if continuous with at least one cell having a class (see conditions).

See also

attTbl(), ngbList(), conditions()

Examples

# DUMMY DATA
############################################################################
# LOAD LIBRARIES
library(scapesClassification)
library(terra)

# LOAD THE DUMMY RASTER
r <- list.files(system.file("extdata", package = "scapesClassification"),
                pattern = "dummy_raster\\.tif", full.names = TRUE)
r <- terra::rast(r)

# COMPUTE THE ATTRIBUTE TABLE
at <- attTbl(r, "dummy_var")

# COMPUTE THE LIST OF NEIGBORHOODS
nbs <- ngbList(r)

################################################################################
# CLASSIFY.ALL
################################################################################
# compute example class vector
cv <- cond.4.all(attTbl = at, cond = "dummy_var <= 1", class = 1)
# update example calss vector
cv <- cond.4.all(attTbl = at, cond = "dummy_var <= 3", class = 2,
                 classVector = cv) # input previous class vector

# classify all unclassified cells
ca <- classify.all(attTbl = at, ngbList = nbs, rNumb = TRUE, classVector = cv)


# Convert class vectors into rasters
r_cv <- cv.2.rast(r, at$Cell, classVector = cv)
r_ca <- cv.2.rast(r, at$Cell,classVector = ca)
################################################################################
# PLOTS
################################################################################
oldpar <- par(mfrow = c(1,2))
m <- c(3, 1, 5, 1)

# 1)
plot(r_cv, type="classes", axes=FALSE, legend=FALSE, asp=NA, mar=m,
     colNA="#818792", col=c("#78b2c4", "#cfc1af"))
text(r)
mtext(side=3, line=2, adj=0, cex=1, font=2, "COND.4.ALL")
mtext(side=3, line=1, adj=0, cex=0.9, "Step1: 'dummy_var<=1', Class: 1")
mtext(side=3, line=0, adj=0, cex=0.9, "Step2: 'dummy_var<=3', Class: 2")
legend("bottomright", bg = "white", fill = c("#78b2c4", "#cfc1af", "#818792"),
       legend = c("Class 1", "Class 2", "Unclassified cells"))

# 2)
plot(r_ca, type="classes", axes=FALSE, legend=FALSE, asp=NA,  mar=m,
     colNA="#818792", col=c("#78b2c4", "#cfc1af"))
text(r)
mtext(side=3, line=2, adj=0, cex=1, font=2, "CLASSIFY.ALL")
mtext(side=3, line=1, adj=0, cex=0.9, "Classify all unclassified cells")
legend("bottomright", bg = "white", fill = c("#78b2c4", "#cfc1af", "#818792"),
       legend = c("Class 1", "Class 2"))

par(oldpar)