Sample_points: Sample training data for image classification from multiple...

In MartinezLaura/CanHeMonR.MaxEnt: Application of MaxEnt for canopy health monitoring through airbone image analysis.

Description

For each class in .shp polygon file, Sample training data for image classification from multiple image tiles using their raster bricks as predictors.

Usage

Sample_points(r_train_dir, text_train_dir, tile = "ALL", text = "ALL",
  prob_tifs = FALSE, vuln_classes, training_pol_filename, field_name,
  ninputs_tile, data_outp_dir, abs_samp = 100, parallel = F, nWorkers = 4,
  data_outp_name, randompt = TRUE, EOS = FALSE)

Arguments

r_train_dir	A directory where .tifs for training can be found for multiple tiles
text_train_dir	A directory where .tifs of the textures associated with r_train_dir
tile	Character vector or CVS file. Names of tile(s) to run a cvs file. 'ALL' will run all tiles in r_train_dir. Default is 'ALL'
text	Character vector or CVS file. Names of text(s) to run in a cvs file. 'ALL' will run all tiles in text_train_dir. Default is 'ALL'
prob_tifs	Boolean (FALSE) if not wanted, Directory if wanted. tifs of each raster to run with 0 vaue for the areas that we don't want to sample and 1 fore the ones that we want to sample. Default FALSE
vuln_classes	A list of the classes you want to model The list can contain one or more vectors. Each vector represents a seperate vegetation class and response variable for the model and the vector elements are synonyms used to describe that class The fist place in each vector will be used in the output name used to store the calibrated model, so it should not contain spaces. The other places should appear as attributes in the field 'field_name' of Pols
training_pol_filename	Full path to the vector file (SpatialPointsDataFrame) of which one field contains the vuln.classes
field_name	Character. The field in AOI.filename that contains the vuln_classes
ninputs_tile	Integer. Number of inputs that we have fore each tile, including the tile, for exemple number of textures
data_outp_dir	The folder where you want to save the sampled data
abs_samp	Integer. How many 'absence' pixels should be randomly selected from eah tile to train the model. Default is 100.
parallel	Boolean. Should the code be run in parallel using the doParallel package? Default is FALSE
nWorkers	Integer. If running the ocde in parallel, how many workers should be used? Default is 4
data_outp_name	Character. Name of the data to output
randompt	Boolean. if True random points will be added in the tiles that doesn't have any visual point. Default TRUE
EOS	If EOS true the for loop will be avoided if False will work with a for loop. Default FALSE

Value

Saves a serialize object with the list with class-specific data frames of which the first column is the presence-absence response that can be used to train distribution model.

MartinezLaura/CanHeMonR.MaxEnt documentation built on May 17, 2019, 6:21 p.m.