使用模型拟合另一组的寓言预测结果

Question

I am trying to use a fable model fit on one group's time series to predict onto another group's time series:

library(dplyr)
library(fable)
library(feasts)
library(tsibble)
library(fabletools)

df <- data.frame(
    id = rep(c('A', 'B'), each = 5),
    date = seq(as.Date('2020-01-01'), by = "month", length.out = 10),
    y = rnorm(10)
)

train_tsbl <- as_tsibble(filter(df, id == 'A'), key = id, index = date)
test_tsbl <- as_tsibble(filter(df, id == 'B'), key = id, index = date)

model <- train_tsbl %>%
    model(lm = TSLM(y ~ trend()))

However, when forecasting onto the "test" set – records corresponding to ID 'B', the forecast call returns an empty result for 'B' – the test set.

> forecast(model, test_tsbl)
# A fable: 0 x 4 [?]
# Key:     id, .model [0]
# … with 4 variables: id <fct>, .model <chr>, date <date>, y <dist>

But for train_tsbl , the following:

> forecast(model, train_tsbl)
# A fable: 5 x 5 [1D]
# Key:     id, .model [1]
  id    .model date                   y  .mean
  <fct> <chr>  <date>            <dist>  <dbl>
1 A     lm     2020-01-01  N(0.19, 1.8)  0.191
2 A     lm     2020-02-01 N(-0.12, 1.5) -0.122
3 A     lm     2020-03-01 N(-0.42, 1.3) -0.416
4 A     lm     2020-04-01 N(-0.73, 1.5) -0.730
5 A     lm     2020-05-01    N(-1, 1.8) -1.03 

I can't seem to find any option specifying to predict onto new IDs. What is going on here?

Answer 1

You're using id as a key, which means you fit a separate model for each key. Yet your training data does not contain id==B , so there is no B model.

It is hard to know what you expect here. What model do you want to use for the B rows?

If you want to use the A model, then set up the test set with B replaced by A :

> forecast(model, test_tsbl %>% mutate(id = 'A'))
# A fable: 5 x 5 [1D]
# Key:     id, .model [1]
  id    .model date            y .distribution 
  <chr> <chr>  <date>      <dbl> <dist>        
1 A     lm     2020-06-01 -0.100 N(-0.10, 0.32)
2 A     lm     2020-07-01 -0.217 N(-0.22, 0.42)
3 A     lm     2020-08-01 -0.338 N(-0.34, 0.56)
4 A     lm     2020-09-01 -0.459 N(-0.46, 0.73)
5 A     lm     2020-10-01 -0.575 N(-0.58, 0.93)