prepare_explainable_data: Explain SDM models

In boyanangelov/sdmexplain: Provides tools to make Species Distribution Models easier to explain

Description

Prepare data for plotting interactive explainable SDM.

Usage

prepare_explainable_data(test_dataset, mlr_model, coordinates_df,
  selected_feature = "none", randomize = FALSE,
  randomize_proportion = 0.1)

Arguments

test_dataset	A DataFrame containing the test data.
mlr_model	A trained MLR model
coordinates_df	A Dataframe containing the coordinates.
selected_feature	A character indicating if a feature should be extracted for plotting.
randomize	Boolean deciding if a sample of the dataset should be taken
randomize_proportion	Float deciding what proportion of the data should be sampled

Value

A list containing data necessary for the interactive map

Examples

## Not run: 
# build and train a machine learning model
task <- makeClassifTask(id = "model", data = data.train, target = "label")
lrn <- makeLearner("classif.lda", predict.type = "prob")
mod <- train(lrn, task)

# prepare explainable data
explainable_data <- prepare_explainable_data(data.test, mod, coordinates.df)

## End(Not run)

boyanangelov/sdmexplain documentation built on Nov. 26, 2019, 2:56 a.m.