Lrnr_rugarch: Univariate GARCH Models
In jeremyrcoyle/sl3: Pipelines for Machine Learning and Super Learning

Description Format Value Parameters See Also Examples

This learner supports autoregressive fractionally integrated moving average and various flavors of generalized autoregressive conditional heteroskedasticity models for univariate time-series. All the models are fit using ugarchfit.

An R6Class object inheriting from Lrnr_base.

A learner object inheriting from Lrnr_base with methods for training and prediction. For a full list of learner functionality, see the complete documentation of Lrnr_base.

variance.model: List containing variance model specification. This includes model, GARCH order, submodel, external regressors and variance tageting. Refer to ugarchspec for more information.
mean.model: List containing the mean model specification. This includes ARMA model, whether the mean should be included, and external regressors among others.
distribution.model: Conditional density to be used for the innovations.
start.pars:List of staring parameters for the optimization routine.
fixed.pars:List of parameters which are to be kept fixed during the optimization routine.
...: Other parameters passed to ugarchfit.

Other Learners: Custom_chain, Lrnr_HarmonicReg, Lrnr_arima, Lrnr_bartMachine, Lrnr_base, Lrnr_bayesglm, Lrnr_bilstm, Lrnr_caret, Lrnr_cv_selector, Lrnr_cv, Lrnr_dbarts, Lrnr_define_interactions, Lrnr_density_discretize, Lrnr_density_hse, Lrnr_density_semiparametric, Lrnr_earth, Lrnr_expSmooth, Lrnr_gam, Lrnr_ga, Lrnr_gbm, Lrnr_glm_fast, Lrnr_glmnet, Lrnr_glm, Lrnr_grf, Lrnr_gru_keras, Lrnr_gts, Lrnr_h2o_grid, Lrnr_hal9001, Lrnr_haldensify, Lrnr_hts, Lrnr_independent_binomial, Lrnr_lightgbm, Lrnr_lstm_keras, Lrnr_mean, Lrnr_multiple_ts, Lrnr_multivariate, Lrnr_nnet, Lrnr_nnls, Lrnr_optim, Lrnr_pca, Lrnr_pkg_SuperLearner, Lrnr_polspline, Lrnr_pooled_hazards, Lrnr_randomForest, Lrnr_ranger, Lrnr_revere_task, Lrnr_rpart, Lrnr_screener_augment, Lrnr_screener_coefs, Lrnr_screener_correlation, Lrnr_screener_importance, Lrnr_sl, Lrnr_solnp_density, Lrnr_solnp, Lrnr_stratified, Lrnr_subset_covariates, Lrnr_svm, Lrnr_tsDyn, Lrnr_ts_weights, Lrnr_xgboost, Pipeline, Stack, define_h2o_X(), undocumented_learner

library(origami)
library(data.table)
data(bsds)

# make folds appropriate for time-series cross-validation
folds <- make_folds(bsds,
  fold_fun = folds_rolling_window, window_size = 500,
  validation_size = 100, gap = 0, batch = 50
)

# build task by passing in external folds structure
task <- sl3_Task$new(
  data = bsds,
  folds = folds,
  covariates = c(
    "weekday", "temp"
  ),
  outcome = "cnt"
)

# create tasks for taining and validation
train_task <- training(task, fold = task$folds[[1]])
valid_task <- validation(task, fold = task$folds[[1]])

# instantiate learner, then fit and predict
HarReg_learner <- Lrnr_HarmonicReg$new(K = 7, freq = 105)
HarReg_fit <- HarReg_learner$train(train_task)
HarReg_preds <- HarReg_fit$predict(valid_task)