train_selection_ensemble: Train a method-selecting ensemble that minimizes forecasting...

In pmontman/fforma: Feature-based Forecast Method Averaging

Description

Train a method-selecting ensemble that minimizes forecasting error

Usage

train_selection_ensemble(data, errors, params, nrounds)

predict_selection_ensemble(model, newdata)

summary_performance(predictions, dataset, print.summary = TRUE)

Arguments

data	A matrix with the input features data (extracted from the series). One observation (the features from the original series) per row.
errors	A matrix with the errors produced by each of the forecasting methods. Each row is a vector with the errors of the forecasting methods.
params	A list containing thr speficic parameters to be passed to the xgboost::xgb.train function
nrounds	nrounds param in xgb.train
model	The xgboost model
newdata	The feature matrix, one row per series
predictions	A NXM matrix with N the number of observations(time series) and M the number of methods. Each row contains the weights assigned to the methods for the series
dataset	The list with the meta information, forecasts of each method...MUST contain the precalculated errors with process_errors()!
print.summary	Boolean indicating wheter to print the information

Functions

• predict_selection_ensemble: Produces predictions probabilities for the selection ensemble.

• summary_performance: Analysis of the predictions, the weighted error and the selection error, along with extra information

pmontman/fforma documentation built on March 16, 2020, 12:23 a.m.