Package index • adm

All functions

adm_eval(): Calculate different model performance metrics

adm_extract(): Extract values from a spatial raster based on x and y coordinates

adm_predict(): Spatial predictions from individual and ensemble models

adm_summarize(): Merge model performance tables

adm_transform(): Performs data transformation on a variable based on the specified method.

balance_dataset(): Balance database at a given absence-presence ratio

cnn_make_samples(): Creates sample data for Convolutional Neural Network

cretusa_data: A data set containing abundance of Cynophalla retusa.

cretusa_predictors(): Raster with Principal Component

croppin_hood(): Crop rasters around a point (Convolutional Neural Networks)

data_abund_bpdp(): Calculate data to construct bivariate partial dependence plots

data_abund_pdp(): Calculate data to construct partial dependence plots

envar(): Raster with environmental data

family_selector(): Select probability distributions for GAM and GLM

fit_abund_cnn(): Fit and validate Convolutional Neural Network Model

fit_abund_dnn(): Fit and validate Deep Neural Network model

fit_abund_gam(): Fit and validate Generalized Additive Models

fit_abund_gbm(): Fit and validate Generalized Boosted Regression models

fit_abund_glm(): Fit and validate Generalized Linear Models

fit_abund_net(): Fit and validate Artificial Neural Network models

fit_abund_raf(): Fit and validate Random Forests models

fit_abund_svm(): Fit and validate Support Vector Machine models

fit_abund_xgb(): Fit and validate Extreme Gradient Boosting models

generate_arch_list(): Generate architecture list for Deep Neural Network and Convolutional Neural Network

generate_cnn_architecture(): Generate architectures for Convolutional Neural Network

generate_dnn_architecture(): Generate architectures for Deep Neural Network

model_selection(): Best hyperparameter selection

p_abund_bpdp(): Bivariate partial dependence plots for abundance-based distribution models

p_abund_pdp(): Partial dependent plots for abundance-based distribution models

res_calculate(): Calculate the output resolution of a layer

select_arch_list(): Select architectures for Convolutional Neural Network or Deep Neural Network

sppabund: A data set containing species abundance of three species, partition folds, and environmental variables.

tune_abund_cnn(): Fit and validate Convolutional Neural Network with exploration of hyper-parameters that optimize performance

tune_abund_dnn(): Fit and validate Deep Neural Network model with exploration of hyper-parameters that optimize performance

tune_abund_gam(): Fit and validate Generalized Additive Models with exploration of hyper-parameters that optimize performance

tune_abund_gbm(): Fit and validate Generalized Boosted Regression models with exploration of hyper-parameters that optimize performance

tune_abund_glm(): Fit and validate Generalized Linear Models with exploration of hyper-parameters that optimize performance

tune_abund_net(): Fit and validate Shallow Neural Networks models with exploration of hyper-parameters that optimize performance

tune_abund_raf(): Fit and validate Random Forest models with exploration of hyper-parameters that optimize performance

tune_abund_svm(): Fit and validate Support Vector Machine models with exploration of hyper-parameters that optimize performance

tune_abund_xgb(): Fit and validate Extreme Gradient Boosting models with exploration of hyper-parameters that optimize performance