How can I have my forecast in ggplot ?

[Vic]

Hi ! I would like to have this forecast graph in ggplot2 to make it interractive with plotly but when I try ggplot(forecast1) I get this error message : Error: data must be a data frame, or other object coercible by fortify(), not an S3 object with class forecast

Can anyone explain me how I can do to fix it ?

My code below

library(ggplot2)
library(readxl)
library(forecast)

DensityPerYear <- read_xlsx("DensityPerYear.xlsx")

tsDensityPerYear <- ts(DensityPerYear$Density, frequency = 1, start = c(1970))

autoarima1 <- auto.arima(tsDensityPerYear)

forecast1 <- forecast(autoarima1, h=12)

plot(forecast1)

[FJCC]

Here is a very rough beginning to reproducing in ggplot what is returned by plot(forecast1).

library(forecast)
library(ggplot2)

DensityPerYear <- data.frame(Year = 1970:2019, Density = sin((1:50)*pi/4))
tsDensityPerYear <- ts(DensityPerYear$Density, frequency = 1, start = c(1970))

autoarima1 <- auto.arima(tsDensityPerYear)

forecast1 <- forecast(autoarima1, h=12)
plot(forecast1)

NewDF <- data.frame(Year = 2020:2031, 
                    Mean =forecast1$mean, 
                    Lower = forecast1$lower, #forecast1$lower is a data frame with 2 col
                    Upper = forecast1$upper)
ggplot(data = NewDF) + geom_line(mapping = aes(Year, Mean)) +
  geom_line(mapping = aes(Year, Lower.80.)) +
  geom_line(mapping = aes(Year, Lower.95.)) +
  geom_line(mapping = aes(Year, Upper.80.)) +
  geom_line(mapping = aes(Year, Upper.95.)) +
  geom_line(mapping = aes(Year, Density), data = DensityPerYear)
#> Don't know how to automatically pick scale for object of type ts. Defaulting to continuous.

^{Created on 2020-03-22 by the reprex package (v0.3.0)}

[robjhyndman]

The forecast package contains the autoplot() function which produces ggplot output rather than base plot output. So replace your plot() command with autoplot() and it should do what you want.