Skip to contents

Direct autoregressive classifier with covariates

Source: R/arx_classifier.R
arx_classifier.Rd

This is an autoregressive classification model for epiprocess::epi_df data. It does "direct" forecasting, meaning that it estimates a class at a particular target horizon.

Usage

arx_classifier(
  epi_data,
  outcome,
  predictors,
  trainer = logistic_reg(),
  args_list = arx_class_args_list()
)

Arguments

epi_data

An epi_df object

outcome

A character (scalar) specifying the outcome (in the epi_df). Note that as with arx_forecaster(), this is expected to be real-valued. Conversion of this data to unordered classes is handled internally based on the breaks argument to arx_class_args_list(). If discrete classes are already in the epi_df, it is recommended to code up a classifier from scratch using epi_recipe().

predictors

A character vector giving column(s) of predictor variables. This defaults to the outcome. However, if manually specified, only those variables specifically mentioned will be used. (The outcome will not be added.) By default, equals the outcome. If manually specified, does not add the outcome variable, so make sure to specify it.

trainer

A {parsnip} model describing the type of estimation. For now, we enforce mode = "classification". Typical values are parsnip::logistic_reg() or parsnip::multinom_reg(). More complicated trainers like parsnip::naive_Bayes() or parsnip::rand_forest() can also be used.

args_list

A list of customization arguments to determine the type of forecasting model. See arx_class_args_list().

Value

A list with (1) predictions an epi_df of predicted classes and (2) epi_workflow, a list that encapsulates the entire estimation workflow

See also

arx_class_epi_workflow(), arx_class_args_list()

Examples

library(dplyr)
jhu <- covid_case_death_rates %>%
  filter(time_value >= as.Date("2021-11-01"))

out <- arx_classifier(jhu, "death_rate", c("case_rate", "death_rate"))

out <- arx_classifier(
  jhu,
  "death_rate",
  c("case_rate", "death_rate"),
  trainer = parsnip::multinom_reg(),
  args_list = arx_class_args_list(
    breaks = c(-.05, .1), ahead = 14,
    horizon = 14, method = "linear_reg"
  )
)