Stack Overflow
Stack Overflow

Questions tagged [fable-r]

R package for tidy time series forecasting (fable: Forecasting Models for Tidy Time Series)

fable: Forecasting Models for Tidy Time Series

Provides a collection of commonly used univariate and multivariate time series forecasting models including automatically selected exponential smoothing (ETS) and autoregressive integrated moving average (ARIMA) models.

These models work within the 'fable' framework provided by the 'fabletools' package, which provides the tools to evaluate, visualise, and combine models in a workflow consistent with the tidyverse.

136 questions
1
vote
1 answer

How to extract simulation data from Fable package forecast?

In running the R code posted at the bottom, I derive a forecast for the next 10 periods at the 80% and 95% confidence levels, using forecast() function from the fable package and running 1000 simulation sample paths, as illustrated here: The…
Village.Idyot
  • 1,359
  • 2
  • 8
1
vote
1 answer

Forecasting with ARIMA and dummy variables

I am attempting to include a dummy regressor that notes the beginning of the pandemic and runs a regression with ARIMA errors. My dataset revolves around breaking & entering's happening in Toronto from 2014 to 2021. The issue is that the trend takes…
AtFirstYouTry
  • 59
  • 4
1
vote
1 answer

Future dataset is incomplete when using Fable Prophet

I'm trying to view the out of sample performance scores after running fable prophet. Please note, the forecast is grouped based on type and the forecast is looking 5 observations ahead. Here is the…
QMan5
  • 713
  • 1
  • 4
  • 20
1
vote
1 answer

Unnest column from `fabletools::forecast()` output

I am asking this question again because those answers don't work for my environment (see "Session Info" below), and thus I assume, don't work for the current versions of the relevant packages. Question How can I take the elements of a column…
josephD
  • 142
  • 7
1
vote
1 answer

How do I fit a forecast into a line graph?

I am at the very end of the forecasting model (Sydney House Prices(only interested in columns: Date and sellPrice)), but I get the error message below; **Code:** Data_fit %>% forecast(h=5) %>% filter(.model=='search') %>% …
Ezgi
  • 13
  • 3
1
vote
0 answers

Why does the constant coefficient change when using fable::refit(reestimate=FALSE)?

I try to refit an existing fable model to new data to get estimates for unseen data. I am wondering why the constant coefficient changes when I use fable::refit(m, reestimate=F) thats unintuitive to me. The coefficient also changes when I refit the…
Andreas Jendrzey
  • 11
  • 1
1
vote
1 answer

How to Log transformation Fable VAR model

I would like to take advantage of Fable's ability to back transform results for a regression. Unfortunately, I have been unable to do so using a VAR model in Fable. I have tried several options such as: fit <- model_data_ts %>% model( aicc…
Michael
  • 11
  • 2
1
vote
2 answers

Error when passing new_data back to transformation in ARIMA model to generate forecast

This is a follow up to the question posed here: new_transformation not working with multiple inputs from tsibble object inside ARIMA When passing back a CPI forecast as new_data to undo the CPI transformation, I receive an error. Any thoughts? Here…
Matt R
  • 25
  • 5
1
vote
1 answer

How to forecast with lagged external regressors using fable::VAR

I'd like to use lagged external regressors in my VAR forecast. Using the VAR() function from the fable package, I am able to fit a model, but I can't use it to forecast, as I return NAs for the dependent variables. My reprex follows examples from…
CaseyR
  • 55
  • 6
1
vote
0 answers

How to aggregate a categorical variable with 20 levels in hierarchical/ grouped forecasting and use it at external regressor

Fellow contributors, I have been working with a hierarchical time series, concerning a set of identical products in a number of stores. For this purpose when we aggregate the data set based on 2 attributes like "store" and "product_type" in my case,…
Anoushiravan R
  • 21,622
  • 3
  • 18
  • 41
1
vote
1 answer

Date format error while forecasting using tsibble objects

I have converted a normal DF into a tsibble object and used that for my time-series forecasting. While fitting the model I experience the date format error- "Error in decimal_date.default(x) : date(s) not in POSIXt or Date format". As you could see…
Arvind Menon
  • 35
  • 5
1
vote
1 answer

In fable's ARIMA function, is it possible to capture the output from trace = TRUE?

In fable's ARIMA function, we have the option to see all models that are evaluated with the trace = TRUE option. (Example below.) This output just prints to the console. Is there any place that this model evaluation history is getting saved or is…
bbgatch
  • 61
  • 5
1
vote
0 answers

map over mable of models and apply gg_tsresiduals() to each

I have a mable containing several models: pacman::p_load(tidyverse, fable, fpp3, feasts) retail_data |> autoplot() + facet_wrap(vars(State)) retail_train <- retail_data |> filter(year(Month) <= max(year(Month)) - 4) ft.mod <- retail_train |> model( …
Doug Fir
  • 19,971
  • 47
  • 169
  • 299
1
vote
1 answer

problem using a dynamic trend or seasonal parameter with ETS with fable and purrr

I have a tsibble as shown below. test.data <- structure(list(RSLITM = c("004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004", "004",…
LauraDR
  • 86
  • 9
1
vote
1 answer

Adjust date on x-axis for fpp3 autoplot()

A quick reprex from the book's website: melsyd_economy <- ansett %>% filter(Airports == "MEL-SYD", Class == "Economy") %>% mutate(Passengers = Passengers/1000) autoplot(melsyd_economy, Passengers) + labs(title = "Ansett airlines economy…
Blake Shurtz
  • 321
  • 3
  • 13
1 2
3
…
9 10