predict_glmnet_raster: predict cv.glmnet model to ratser

In rvalavi/myspatial: A collection of functions for spatial data analysis and modelling

Description

This function is to predict the glmnet model object on raster data. It accepts the quadratic transformation if it was provided in the original model fit.

Usage

predict_glmnet_raster(
  r,
  model,
  slambda = "lambda.1se",
  type = "response",
  quadraticObj = NULL,
  factors = NULL,
  filename = NULL,
  verbose = TRUE
)

Arguments

r	a raster file
model	cv.glmnet model object
slambda	the values of the penalty lambda in cv.glmnet model. The default if "lambda.1se", alternatively "lambda.min" can be used. See predict.cv.glment help file in the glmnet pakage.
type	the prediction type. Could be "link" or "response". The default is "response".
quadraticObj	a make_quadratic object. If the model is fitted with the quadratic terms created by make_quadratic function, provide the make_quadratic object here.
factors	factor variables in the model
filename	output file directory for the predicted map. If provided, the map will be save on the disk.
verbose	logical. Control amount of printing...

Author(s)

Roozbeh Valavi

rvalavi/myspatial documentation built on May 15, 2021, 12:14 a.m.