In ahaeusser/echos: Echo State Networks for Time Series Modeling and Forecasting

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.height = 5,
  fig.width = 7
)

Introduction

This vignette gives you a quick tour of the time series datasets embedded in echos:

m4_data: Six monthly time series drawn from the well‑known M4 Forecasting Competition.
synthetic_data: Ten synthetic time series, useful for teaching, prototyping and testing.

Load packages

library(echos)
library(tidyverse)
library(tsibble)

M4 data

The dataset m4_data is a tsibble with six monthly time series from the M4 Forecasting Competition. The datasets contains the following time series:

M21655 (Demographic), 1995 Jan - 2015 Mar
M21683 (Demographic), 2000 Jan - 2023 Apr
M2717 (Macro), 1996 Jan - 2016 Nov
M28597 (Industry), 1996 Jan - 2016 Dec
M42529 (Finance), 2001 Jan - 2009 Apr
M4813 (Macro), 1994 Apr - 2006 May

m4_data

p <- ggplot()

p <- p + geom_line(
  data = m4_data,
  aes(
    x = index,
    y = value
  )
)

p <- p + facet_wrap(
  ~series,
  ncol = 2,
  scales = "free")

p <- p + labs(x = "Time")
p <- p + labs(y = "Value")
p

Synthetic data

The dataset synthetic_data is a tibble with ten synthetic time series. The dataset contains the following time series:

Square Wave
Sawtooth Wave
Harmonic Wave
Harmonic Wave w/ Trend
Amplitude Modulated Wave
Frequency Modulated Wave
AR(1) Process
MA(2) Process
White Noise Process
Random Walk Process

synthetic_data

p <- ggplot()

p <- p + geom_line(
  data = synthetic_data,
  aes(
    x = index,
    y = value
  )
)

p <- p + facet_wrap(
  ~factor(
    variable, 
    levels = c(
      "Square Wave",
      "Sawtooth Wave",
      "Harmonic Wave",
      "Harmonic Wave w/ Trend",
      "Amplitude Modulated Wave",
      "Frequency Modulated Wave",
      "AR(1) Process",
      "MA(2) Process",
      "White Noise Process",
      "Random Walk Process"
    )),
  ncol = 2,
  scales = "free")

p <- p + labs(x = "Time")
p <- p + labs(y = "Value")
p