ensemble_average: Creates an Ensemble Model using Mean/Median Averaging

In modeltime.ensemble: Ensemble Algorithms for Time Series Forecasting with Modeltime

Creates an Ensemble Model using Mean/Median Averaging

Description

Creates an Ensemble Model using Mean/Median Averaging

Usage

ensemble_average(object, type = c("mean", "median"))

Arguments

object	A Modeltime Table
type	Specify the type of average ("mean" or "median")

Details

The input to an ensemble_average() model is always a Modeltime Table, which contains the models that you will ensemble.

Averaging Methods

The average method uses an un-weighted average using type of either:

• "mean": Performs averaging using mean(x, na.rm = TRUE) to aggregate each underlying models forecast at each timestamp

• "median": Performs averaging using stats::median(x, na.rm = TRUE) to aggregate each underlying models forecast at each timestamp

Value

A mdl_time_ensemble object.

Examples

library(tidymodels)
library(modeltime)
library(modeltime.ensemble)
library(tidyverse)
library(timetk)

# Make an ensemble from a Modeltime Table
ensemble_fit <- m750_models %>%
    ensemble_average(type = "mean")

ensemble_fit

# Forecast with the Ensemble
modeltime_table(
    ensemble_fit
) %>%
    modeltime_forecast(
        new_data    = testing(m750_splits),
        actual_data = m750
    ) %>%
    plot_modeltime_forecast(
        .interactive = FALSE,
        .conf_interval_show = FALSE
    )

modeltime.ensemble documentation built on April 18, 2023, 5:09 p.m.