isotree_po: Build Isolation forest species distribution model and explain...
In itsdm: Isolation Forest-Based Presence-Only Species Distribution Modeling

isotree_po

R Documentation

Build Isolation forest species distribution model and explain the the model and outputs.

Description

Call Isolation forest and its variations to do species distribution modeling and optionally call a collection of other functions to do model explanation.

Usage

isotree_po(
  obs_mode = "imperfect_presence",
  obs,
  obs_ind_eval = NULL,
  variables,
  categ_vars = NULL,
  contamination = 0.1,
  ntrees = 100L,
  sample_size = 1,
  ndim = 1L,
  seed = 10L,
  ...,
  offset = 0,
  response = TRUE,
  spatial_response = TRUE,
  check_variable = TRUE,
  visualize = FALSE
)

Arguments

`obs_mode`	(`string`) The mode of observations for training. It should be one of `c("perfect_presence", "imperfect_presence", "presence_absence")`. "perfect_presence" means presence-only occurrences without errors/uncertainties/bias, which should be rare in reality. "Imperfect_presence" means presence-only occurrences with errors/uncertainties/bias, which should be a most common case. "presence_absence" means presence-absence observations regardless quality. See details to learn how to set it. The default is "imperfect_presence".
`obs`	(`sf`) The `sf` of observation for training. It is recommended to call function `format_observation` to format the occurrence (`obs`) before passing it here. Otherwise, make sure there is a column named "observation" for observation.
`obs_ind_eval`	(`sf` or `NULL`) Optional `sf` of observations for independent test. It is recommended to call function `format_observation` to format the occurrence (`obs`) before passing it here. Otherwise, make sure there is a column named "observation" for observation. If `NULL`, no independent test set will be used. The default is `NULL`.
`variables`	(`RasterStack` or `stars`) The stack of environmental variables.
`categ_vars`	(`vector` of `character` or `NULL`) The names of categorical variables. Must be the same as the names in `variables`.
`contamination`	(`numeric`) The percentage of abnormal cases within a dataset. Because `iForest` is an outlier detection algorithm. It picks up abnormal cases (much fewer) from normal cases. This argument is used to set how many abnormal cases should be there if the users have the power to control. See details for how to set it. The value should be less than 0.5. Here we constrain it in (0, 0.3]. The default value is 0.1.
`ntrees`	(`integer`) The number of trees for the isolation forest. It must be integer, which you could use function `as.integer` to convert to. The default is `100L`.
`sample_size`	(`numeric`) It should be a rate for sampling size in `⁠[0, 1]⁠`. The default is `1.0`.
`ndim`	(`integer`) ExtensionLevel for isolation forest. It must be integer, which you could use function `as.integer` to convert to. Also, it must be no smaller than the dimension of environmental variables. When it is 1, the model is a traditional isolation forest, otherwise the model is an extended isolation forest. The default is 1.
`seed`	(`integer`) The random seed used in the modeling. It should be an integer. The default is `10L`.
`...`	Other arguments that `isolation.forest` needs.
`offset`	(`numeric`) The offset to adjust fitted suitability. The default is zero. Highly recommend to leave it as default.
`response`	(`logical`) If `TRUE`, generate response curves. The default is `TRUE`.
`spatial_response`	(`logical`) If `TRUE`, generate spatial response maps. The default is `TRUE` because it might be slow. NOTE that here SHAP-based map is not generated because it is slow. If you want it be mapped, you could call function `spatial_response` to make it.
`check_variable`	(`logical`) If `TRUE`, check the variable importance. The default is `TRUE`.
`visualize`	(`logical`) If `TRUE`, generate the essential figures related to the model. The default is `FALSE`.

Details

For "perfect_presence", a user-defined number (contamination) of samples will be taken from background to let iForest function normally.

If "imperfect_presence", no further actions is required.

If the obs_mode is "presence_absence", a contamination percent of absences will be randomly selected and work together with all presences to train the model.

NOTE: obs_mode and mode only works for obs. obs_ind_eval will follow its own structure.

Please read details of algorithm isolation.forest on https://github.com/david-cortes/isotree, and the R documentation of function isolation.forest.

Value

(POIsotree) A list of

model (isolation.forest) The threshold set in function inputs
variables (stars) The formatted image stack of environmental variables
observation (sf) A sf of training occurrence dataset
background_samples (sf) A sf of background points for training dataset evaluation or SHAP dependence plot
independent_test (sf or NULL) A sf of test occurrence dataset
background_samples_test (sf or NULL) A sf of background points for test dataset evaluation or SHAP dependence plot
vars_train (data.frame) A data.frame with values of each environmental variables for training occurrence
pred_train (data.frame) A data.frame with values of prediction for training occurrence
eval_train (POEvaluation) A list of presence-only evaluation metrics based on training dataset. See details of POEvaluation in evaluate_po
var_test (data.frame or NULL) A data.frame with values of each environmental variables for test occurrence
pred_test (data.frame or NULL) A data.frame with values of prediction for test occurrence
eval_test (POEvaluation or NULL) A list of presence-only evaluation metrics based on test dataset. See details of POEvaluation in evaluate_po
prediction (stars) The predicted environmental suitability
marginal_responses (MarginalResponse or NULL) A list of marginal response values of each environmental variables. See details in marginal_response
offset (numeric) The offset value set as inputs.
independent_responses (IndependentResponse or NULL) A list of independent response values of each environmental variables. See details in independent_response
shap_dependences (ShapDependence or NULL) A list of variable dependence values of each environmental variables. See details in shap_dependence
spatial_responses (SpatialResponse or NULL) A list of spatial variable dependence values of each environmental variables. See details in shap_dependence
variable_analysis (VariableAnalysis or NULL) A list of variable importance analysis based on multiple metrics. See details in variable_analysis

References

Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou. "Isolation forest." 2008 eighth ieee international conference on data mining.IEEE, 2008. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1109/ICDM.2008.17")}
Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou. "Isolation-based anomaly detection." ACM Transactions on Knowledge Discovery from Data (TKDD) 6.1 (2012): 1-39. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1145/2133360.2133363")}
Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou. "On detecting clustered anomalies using SCiForest." Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Berlin, Heidelberg, 2010. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1007/978-3-642-15883-4_18")}
Ha riri, Sahand, Matias Carrasco Kind, and Robert J. Brunner. "Extended isolation forest." IEEE Transactions on Knowledge and Data Engineering (2019). \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1109/TKDE.2019.2947676")}
https://github.com/david-cortes/isotree
References of related feature such as response curves and variable importance will be listed under their own functions

Examples


########### Presence-absence mode #################
library(dplyr)
library(sf)
library(stars)
library(itsdm)

# Load example dataset
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"
obs_type <- "presence_absence"

# 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 = obs_type)

# Load variables
env_vars <- system.file(
  'extdata/bioclim_tanzania_10min.tif',
  package = 'itsdm') %>% read_stars() %>%
  slice('band', c(1, 5, 12))

# Modeling
mod_virtual_species <- isotree_po(
  obs_mode = "presence_absence",
  obs = obs_train_eval$obs,
  obs_ind_eval = obs_train_eval$eval,
  variables = env_vars, ntrees = 10,
  sample_size = 0.6, ndim = 1L,
  seed = 123L, nthreads = 1)

# Check results
## Evaluation based on training dataset
print(mod_virtual_species$eval_train)
plot(mod_virtual_species$eval_train)

## Response curves
plot(mod_virtual_species$marginal_responses)
plot(mod_virtual_species$independent_responses,
     target_var = c('bio1', 'bio5'))
plot(mod_virtual_species$shap_dependence)

## Relationships between target var and related var
plot(mod_virtual_species$shap_dependence,
     target_var = c('bio1', 'bio5'),
     related_var = 'bio12', smooth_span = 0)

# Variable importance
mod_virtual_species$variable_analysis
plot(mod_virtual_species$variable_analysis)

########### Presence-absence mode ##################
# Load example dataset
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")

# Modeling with perfect_presence mode
mod_perfect_pres <- isotree_po(
  obs_mode = "perfect_presence",
  obs = obs_train_eval$obs,
  obs_ind_eval = obs_train_eval$eval,
  variables = env_vars, ntrees = 10,
  sample_size = 0.6, ndim = 1L,
  seed = 123L, nthreads = 1)

# Modeling with imperfect_presence mode
mod_imperfect_pres <- 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 = 0.6, ndim = 1L,
  seed = 123L, nthreads = 1)

itsdm documentation built on July 9, 2023, 6:45 p.m.