assemble_stacking_inputs: Assemble a data frame of inputs to stacking

In reichlab/2017-2018-cdc-flu-contest: code for cdc flu contest 2017-2018

Description

Assemble a data frame of inputs to stacking

Usage

assemble_stacking_inputs(regions, seasons = paste0(2010:2016, "-", 2011:2017),
  prediction_target, component_model_names, explanatory_variables,
  include_model_performance = FALSE, preds_path)

Arguments

regions	string with region: either "National" or in the format "Regionk" for k in 1, ..., 10
seasons	character vector specifying seasons for which to get predictions, "2011/2012" or "2011-2012" or "*" for all seasons
prediction_target	string with either "onset", "peak_week", "peak_inc", "ph1_inc", ..., "ph4_inc"
component_model_names	character vector with names of component models
explanatory_variables	character vector with names of explanatory variables to include for weights; a non-empty subset of "analysis_time_season_week", "kcde_model_confidence", "sarima_model_confidence", "weighted_ili"
include_model_performance	boolean; should measures of model performance be included in the return result? Generally, should be TRUE if we're getting inputs for model training and FALSE if we're just getting covariates to calculate model weights.
preds_path	path to directory with leave-one-season-out or test phase predictions from each component model. Predictions should be saved in files named like "kde-National-loso-predictions.rds"

Value

a data frame with covariates that model weights depend on (as specified by explanatory_variables) and possibly log scores from each component model

reichlab/2017-2018-cdc-flu-contest documentation built on May 24, 2019, 6:17 a.m.