predict_split: predict_split

In maxikellerbauer/stAirPol: Spatio-temporal Modelling of Air Pollution Data

Description

Perform all predictions on subsample datasets to avoid a shortage of RAM.

Usage

predict_split(model, new_data, sample_count = 100,
  mc.cores = parallel::detectCores() - 1, ...)

Arguments

model	a spatio-temporal model as returned by fit_sp_model
sample_count	how much subsamples?, default is 100
mc.cores	how much cores should be used for parallelization, default is one core less your maximum number of detected cores.
...	additional parameters which are passed to predict.stAirPol.model
newdata	a dataset with informations of the covariable

Value

the newdata with added columns of the prediction calculations

See Also

fit_subintervalls, predict.stAirPol.model, predict_split fit_model

Examples

data("mini_dataset")
mini_dataset <- clean_model_data(mini_dataset)
formula = value ~ humi + temp + rainhist + windhist +
  trafficvol + log(sensor_age)
training_set <- get_test_and_training_set(mini_dataset, sampel_size = 0.75,
                                          random.seed = 220292)
model.gp <- fit_sp_model(data = mini_dataset, formula = formula,
                         model = 'GP', training_set = training_set)
pred.gp <- predict_split(model.gp, mini_dataset, training_set)

maxikellerbauer/stAirPol documentation built on May 3, 2019, 3:16 p.m.