whitebox (version 2.1.0)

wbt_knn_classification: Knn classification

Description

Performs a supervised k-nearest neighbour classification using training site polygons/points and predictor rasters.

Usage

wbt_knn_classification(
  inputs,
  training,
  field,
  output,
  scaling = "Normalize",
  k = 5,
  clip = TRUE,
  test_proportion = 0.2,
  wd = NULL,
  verbose_mode = FALSE,
  compress_rasters = FALSE
)

Arguments

inputs

Names of the input predictor rasters.

training

Name of the input training site polygons/points shapefile.

field

Name of the attribute containing class name data.

output

Name of the output raster file.

scaling

Scaling method for predictors. Options include 'None', 'Normalize', and 'Standardize'.

k

k-parameter, which determines the number of nearest neighbours used.

clip

Perform training data clipping to remove outlier pixels?.

test_proportion

The proportion of the dataset to include in the test split; default is 0.2.

wd

Changes the working directory.

verbose_mode

Sets verbose mode. If verbose mode is False, tools will not print output messages.

compress_rasters

Sets the flag used by WhiteboxTools to determine whether to use compression for output rasters.

Value

Returns the tool text outputs.