PrintMap: Output module: PrintMap

In zoonproject/modules: Species Distribution Modelling Code Modules for the ZOON Package

Description

Plot a map of predicted surface.

Usage

PrintMap(.model, .ras, plot = TRUE, points = FALSE, dir = NULL,
  filename = NULL, size = c(480, 480), res = 72, threshold = NULL,
  thresholdmethod = c("probability", "quantile", "falsepositive",
  "falsenegative"), ...)

Arguments

.model	Internal parameter, do not use in the workflow function. .model is list of a data frame (data) and a model object (model). .model is passed automatically in workflow, combining data from the model module(s) and process module(s), to the output module(s) and should not be passed by the user.
.ras	Internal parameter, do not use in the workflow function. .ras is a raster layer, brick or stack object. .ras is passed automatically in workflow from the covariate module(s) to the output module(s) and should not be passed by the user.
plot	If TRUE the plot will be displayed in the device
points	If TRUE the training points will be plotted over the prediction surface
dir	Directory where plots are saved. If both dir and filename are NULL (default) then plots are not saved.
filename	The name to be given to the output as a character, don't include a file extension. If both dir and filename are NULL (default) then plots are not saved.
size	A vector containing the width and height of the output figure when writing to a png file. Example: c(800,600).
res	The output resolution in ppi when writing to a png file.
threshold	The threshold value to use to convert probabilities to binary 1's and 0's. Default is NULL ie not used.
thresholdmethod	The method used to calculate probability threshold. One of 'probability', 'quantile', 'falsepositive', 'falsenegative'. See Details for specifics.
...	Parameters passed to sp::spplot, useful for setting title and axis labels e.g. xlab = 'Axis Label', main = 'My Plot Title'

Details

For creating maps with only presence absence values, there are a number of options for setting a threshold. The threshold argument sets the value for the threshold while thresholdmethod selects the methods used to set the threshold.

1. ‘probability’ (default) Any pixels with predicted probability (or relative probability, depending on the model) greater than the threshold are set to presence

2. ‘quantile’ threshold gives the proportion of pixels that should be absense. The threshold value is selected so that this is true.

3. ‘falsepositive’ threshold sets the proportion of absense data points (not pixels) that should be misclassified as presence.

4. ‘falsenegative’ threshold sets the proportion of presence data points (not pixels) that should be misclassified as absense

Value

A Raster object giving the probabilistic model predictions for each cell of covariate raster layer

Version

1.2

Date submitted

2016-04-02

Author(s)

ZOON Developers, James Campbell, David Wilkinson [e-mail]

See Also

Other output: AIC, AUC, Appify, CoefficientPlot, CovHistograms, DataSummary, Deviance, GenerateCovariateReport, InteractiveCovariateMap, InteractiveMap, InteractiveOccurrenceMap, NoOutput, PairPlot, PerformanceMeasures, PredictNewRasterMap, PrintOccurrenceMap, ROCcurve, ReliabilityPlot, ResponseCurveViz, ResponseCurve, ResponsePlot, SameTimePlaceMap, SeparatePA, SurfaceMap, VariableImportance

zoonproject/modules documentation built on May 4, 2019, 11:25 p.m.