Skip to contents

Prepare and plot response curve data for Hmsc models

Source: R/mod_resp_curv_prepare_data.R, R/mod_resp_curv_plot_species.R, R/mod_resp_curv_plot_species_all.R, and 1 more
Response_curves.Rd

The RespCurv_*() functions process and visualise response curves for Hmsc models. They support parallel computation and optionally return processed data. There are four functions in this group:

  • resp_curv_prepare_data(): Prepares response curve data for analysis

  • resp_curv_plot_species(): Generates response curve plots for individual species

  • resp_curv_plot_species_all(): Generates response curves for all species together in a single plot

  • resp_curv_plot_SR(): Plots response curves for species richness.

Usage

resp_curv_prepare_data(
  path_model = NULL,
  n_grid = 50L,
  n_cores = 8L,
  strategy = "multisession",
  return_data = FALSE,
  probabilities = c(0.025, 0.5, 0.975),
  use_TF = TRUE,
  TF_environ = NULL,
  TF_use_single = FALSE,
  LF_n_cores = n_cores,
  LF_check = FALSE,
  LF_temp_cleanup = TRUE,
  LF_commands_only = FALSE,
  temp_dir = "TEMP_Pred",
  temp_cleanup = TRUE,
  verbose = TRUE
)

resp_curv_plot_species(
  model_dir = NULL,
  n_cores = 20,
  env_file = ".env",
  return_data = FALSE
)

resp_curv_plot_species_all(
  model_dir = NULL,
  n_cores = 8L,
  strategy = "multisession",
  return_data = FALSE,
  plotting_alpha = 0.3
)

resp_curv_plot_SR(
  model_dir,
  verbose = TRUE,
  n_cores = 8L,
  strategy = "multisession"
)

Arguments

path_model

Character. Path to the file containing the fitted Hmsc model.

n_grid

Integer. Number of points along the gradient for continuous focal variables. Higher values result in smoother curves. Default: 50. See Hmsc::constructGradient for details.

n_cores

Integer. Number of CPU cores to use for parallel processing. Defaults to 8L for all functions, except for resp_curv_plot_species, in which it defaults to 20L.

strategy

Character. The parallel processing strategy to use. Valid options are "sequential", "multisession" (default), "multicore", and "cluster". See future::plan() and ecokit::set_parallel() for details.

return_data

Logical. If TRUE, the function returns processed data as an R object. Default: FALSE.

probabilities

Numeric vector. Quantiles to calculate in response curve predictions. Default: c(0.025, 0.5, 0.975). See stats::quantile for details.

use_TF

Logical. Whether to use TensorFlow for calculations. Defaults to TRUE.

TF_environ

Character. Path to the Python environment. This argument is required if use_TF is TRUE under Windows. Defaults to NULL.

TF_use_single

Logical. Whether to use single precision for the TensorFlow calculations. Defaults to FALSE.

LF_n_cores

Integer. Number of cores to use for parallel processing of latent factor prediction. Defaults to 8L.

LF_check

Logical. If TRUE, the function checks if the output files are already created and valid. If FALSE, the function will only check if the files exist without checking their integrity. Default is FALSE.

LF_temp_cleanup

Logical. Whether to delete temporary files in the temp_dir directory after finishing the LF predictions.

LF_commands_only

Logical. If TRUE, returns the command to run the Python script. Default is FALSE.

temp_dir

Character. Path for temporary storage of intermediate files.

temp_cleanup

Logical. Whether to clean up temporary files. Defaults to TRUE.

verbose

Logical. Whether to print a message upon successful saving of files. Defaults to FALSE.

model_dir

Character. Path to the root directory containing fitted models. The function reads data from the RespCurv_DT subdirectory, which is created by resp_curv_prepare_data.

env_file

Character. Path to the environment file containing paths to data sources. Defaults to .env.

plotting_alpha

Numeric. Opacity level for response curve lines (0 = fully transparent, 1 = fully opaque). Default: 0.3.

Author

Ahmed El-Gabbas