Estimate suitability on stars
object using trained isolation.forest
model.
Source: R/probability.R
probability.Rd
Apply an isolation.forest
model on a stars object to calculate
environmental suitability and do quantile stretch to [0, 1]
.
Arguments
- x
(
isolation_forest
). It could be the itemmodel
ofPOIsotree
made by functionisotree_po
.- vars
(
stars
) The stack of environmental variables. More specifically, make sure it has x and y dimensions only, and distribute variables to attributes of thisstars
. Otherwise, the function would stop.- offset
(
numeric
) The offset to adjust fitted suitability. The default is zero. Highly recommend to leave it as default.
Examples
if (FALSE) { # \dontrun{
# Using a pseudo presence-only occurrence dataset of
# virtual species provided in this package
library(dplyr)
library(sf)
library(stars)
library(itsdm)
# Prepare data
data("occ_virtual_species")
obs_df <- occ_virtual_species %>% filter(usage == "train")
eval_df <- occ_virtual_species %>% filter(usage == "eval")
x_col <- "x"
y_col <- "y"
obs_col <- "observation"
# Format the observations
obs_train_eval <- format_observation(
obs_df = obs_df, eval_df = eval_df,
x_col = x_col, y_col = y_col, obs_col = obs_col,
obs_type = "presence_only")
env_vars <- system.file(
'extdata/bioclim_tanzania_10min.tif',
package = 'itsdm') %>% read_stars() %>%
slice('band', c(1, 5, 16))
# With imperfect_presence mode,
mod <- isotree_po(
obs_mode = "imperfect_presence",
obs = obs_train_eval$obs,
obs_ind_eval = obs_train_eval$eval,
variables = env_vars, ntrees = 10,
sample_size = 0.8, ndim = 2L,
seed = 123L, nthreads = 1,
response = FALSE,
spatial_response = FALSE,
check_variable = FALSE)
suit <- probability(mod$model, mod$variables)
} # }