I am forecasting different type of models(ARIMA, ETS and Neural networks) on a tsibble based time series data set dat() with the structure Date & Data. The recently released feast/fable packages provide the forecast data that I want to plot. Usually, with ggplot2 i just use the autoplot() function. As i want to convert the obtained plot to a nicer one with plotly, I have added in the last row ggplotly(). The code works totally fine until the penultimate line.
I get the following message in my console:
Warning in geom2trace.default(dots[[1L]][[2L]], dots[[2L]][[1L]], dots[[3L]][[1L]]) :
geom_GeomForecast() has yet to be implemented in plotly.
If you'd like to see this geom implemented,
Please open an issue with your example code at
https://github.com/ropensci/plotly/issues
plot <- dat() %>%
model(ARIMA(Data),
ETS(Data),
NNETAR(Data)) %>%
forecast(h = 10) %>%
autoplot(dat()) %>%
ggplotly()
I am forecasting different type of models(ARIMA, ETS and Neural networks) on a tsibble based time series data set dat() with the structure Date & Data. The recently released feast/fable packages provide the forecast data that I want to plot. Usually, with ggplot2 i just use the autoplot() function. As i want to convert the obtained plot to a nicer one with plotly, I have added in the last row ggplotly(). The code works totally fine until the penultimate line.
I get the following message in my console: