What is the reason for the error reported for the ETS and ARIMA accuracy checks?

Question

The code is as follows.

library(fable)
library(tsibble)
library(dplyr)

tourism_melb <- tourism %>%
  filter(Region == "Melbourne")
tourism_melb %>%
  group_by(Purpose) %>%
  slice(1)

tourism_melb %>%
  autoplot(Trips)

fit <- tourism_melb %>%
  model(
    ets = ETS(Trips ~ trend("A")),
    arima = ARIMA(Trips)
  )

fit %>%
  accuracy() %>%
  arrange(MASE)

Error in accuracy.default(.) : No accuracy method found for an object of class mdl_dfNo accuracy method found for an object of class tbl_dfNo accuracy method found for an object of class tblNo accuracy method found for an object of class data.frame

What is the reason for the error in the last step?

Answer 1

This might be some configuration issue at your computer. I get some output instead of errors when I run your code.I am pasting the output from my console below, when I run your code.

> library(fable)
Loading required package: fabletools
> library(tsibble)

Attaching package: ‘tsibble’

The following objects are masked from ‘package:base’:

    intersect, setdiff, union

> library(dplyr)

Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

> 
> tourism_melb <- tourism %>%
+   filter(Region == "Melbourne")
> tourism_melb %>%
+   group_by(Purpose) %>%
+   slice(1)
# A tsibble: 4 x 5 [1Q]
# Key:       Region, State, Purpose [4]
# Groups:    Purpose [4]
  Quarter Region    State    Purpose  Trips
    <qtr> <chr>     <chr>    <chr>    <dbl>
1 1998 Q1 Melbourne Victoria Business 405. 
2 1998 Q1 Melbourne Victoria Holiday  428. 
3 1998 Q1 Melbourne Victoria Other     79.9
4 1998 Q1 Melbourne Victoria Visiting 666. 
> 
> tourism_melb %>%
+   autoplot(Trips)
> 
> fit <- tourism_melb %>%
+   model(
+     ets = ETS(Trips ~ trend("A")),
+     arima = ARIMA(Trips)
+   )
> 
> fit %>%
+   accuracy() %>%
+   arrange(MASE)
# A tibble: 8 × 13
  Region    State  Purpose .model .type     ME  RMSE   MAE
  <chr>     <chr>  <chr>   <chr>  <chr>  <dbl> <dbl> <dbl>
1 Melbourne Victo… Holiday ets    Trai…  4.67   50.5  37.2
2 Melbourne Victo… Busine… ets    Trai…  3.31   56.4  42.9
3 Melbourne Victo… Busine… arima  Trai…  2.54   58.2  46.0
4 Melbourne Victo… Holiday arima  Trai… -4.64   54.3  41.4
5 Melbourne Victo… Other   arima  Trai… -0.344  21.7  17.0
6 Melbourne Victo… Other   ets    Trai… -0.142  21.7  17.0
7 Melbourne Victo… Visiti… ets    Trai…  8.17   60.9  51.4
8 Melbourne Victo… Visiti… arima  Trai…  6.89   63.1  51.7
# … with 5 more variables: MPE <dbl>, MAPE <dbl>,
#   MASE <dbl>, RMSSE <dbl>, ACF1 <dbl>
# ℹ Use `colnames()` to see all variable names