occupancy_bootstrap_gof: Goodness of fit metrics for bootstrapped occupancy objects

In hypervolume: High Dimensional Geometry, Set Operations, Projection, and Inference Using Kernel Density Estimation, Support Vector Machines, and Convex Hulls

Goodness of fit metrics for bootstrapped occupancy objects

Description

The occupancy_bootstrap_gof() function calculates goodness of fit metrics for objects generated with hypervolume_n_occupancy_bootstrap().

Usage

occupancy_bootstrap_gof(path, FUN)

Arguments

path	A path to a directory of bootstrapped hypervolumes generated with hypervolume_n_occupancy_bootstrap().
FUN	Function to calculate the goodness of fit. It can be mae for the mean absolute error, rmse for the root mean square error or a function provided by the user.

Details

Goodness of fit metrics are calculated on the difference between input and recomputed volumes for each bootstrapped element (set with n in hypervolume_n_resample()). See hypervolume_n_occupancy() for details on the meaning of input and recomputed hypervolumes.

Value

A one row data.frame reporting mean, standard deviation, minimum, maximum, median, 2.5%, 25%, 75% ans 97.5% quantiles.

Examples

## Not run: 
data(penguins,package='palmerpenguins')
penguins_no_na = as.data.frame(na.omit(penguins))

# split the dataset on species and sex
penguins_no_na_split = split(penguins_no_na, 
paste(penguins_no_na$species, penguins_no_na$sex, sep = "_"))

# calculate the hypervolume for each element of the splitted dataset
hv_list = mapply(function(x, y) 
  hypervolume_gaussian(x[, c("bill_length_mm","bill_depth_mm","flipper_length_mm")],
                       samples.per.point=100, name = y), 
                       x = penguins_no_na_split, 
                       y = names(penguins_no_na_split))


# transform the list into an HypervolumeList
hv_list = hypervolume_join(hv_list)

# bootstrap hypervolumes based on sex
hv_resample = hypervolume_n_resample(hv_list, name = "boot_example")

# calculate occupancy for each bootstrap
hv_occupancy_bootstrap = hypervolume_n_occupancy_bootstrap(hv_resample, 
                                    name = "occupancy_example", 
                                    classification = rep(c("female", "male"), 3))
                
                
occupancy_bootstrap_gof(hv_occupancy_bootstrap, FUN = "rmse")


## End(Not run)

hypervolume documentation built on May 29, 2024, 8:19 a.m.