In forvis/forvision: Tools for forecast visualisation and evaluation

knitr::opts_chunk$set(echo = TRUE)

1. Load наборы данных с rolling-origin

library(tidyverse)
bitcoin_ts <- read_csv("D:/01_Projects/bitcoin/bitcoin_ts.csv")
bitcoin_fc <- read_csv("D:/01_Projects/bitcoin/bitcoin_fc.csv")

knitr::kable(head(bitcoin_ts))
knitr::kable(head(bitcoin_fc))

2. Построить coverage diagram

2.1 для auto.arima

library(forvision)
bitcoin_af <- createAFTS(bitcoin_ts, bitcoin_fc)
plotCoverage(bitcoin_af, pi = 70, methods = "auto.arima", horizons = 1:9)

plotCoverage(bitcoin_af, pi = 90, methods = "auto.arima", horizons = 10:19)

2.2 для auto.ets

plotCoverage(bitcoin_af, pi = 70, methods = "auto.ets", horizons = 1:9)

plotCoverage(bitcoin_af, pi = 90, methods = "auto.ets", horizons = 10:19)

2.3 для naive

plotCoverage(bitcoin_af, pi = 70, methods = "naive", horizons = 1:9)

plotCoverage(bitcoin_af, pi = 90, methods = "naive", horizons = 10:19)

forvis/forvision documentation built on April 30, 2020, 3:28 a.m.