My goal is to show multiple plots of residual vs. fitted values for a dataframe of 13 stations each having a separate lm() model. Working from an example in Chapter 25 (Many Models) in the R for Data Science (1st ed) textbook.

When running this line of R code (from Section 25.2.2 in the textbook)

by_stn <- by_stn %>% mutate(model = map(data, allstn_models))

…I receive the following error:

`Error in `mutate()`:
ℹ In argument: `model = map(data, allstn_models)`.
ℹ In group 1: `station = s04029000`.
Caused by error in `map()`:
ℹ In index: 1.
Caused by error in `pluck_raw()`:
! Index 1 must have length 1, not 13.
Run `rlang::last_trace()` to see where the error occurred.`

I have searched for greater understanding without success.

The structure of by_stn is:

# A tibble: 13 × 2
# Groups:   station [13]
   station   data              
   <fct>     <list>            
 1 s04029000 <tibble [110 × 2]>
 2 s04029990 <tibble [110 × 2]>
 3 s04030000 <tibble [110 × 2]>
 4 s04062011 <tibble [110 × 2]>
 5 s04063000 <tibble [110 × 2]>
 6 s04063700 <tibble [110 × 2]>
 7 s04064000 <tibble [110 × 2]>
 8 s04064500 <tibble [110 × 2]>
 9 s04065106 <tibble [110 × 2]>
10 s04066000 <tibble [110 × 2]>
11 s04066003 <tibble [110 × 2]>
12 s04066500 <tibble [110 × 2]>
13 s04067500 <tibble [110 × 2]>

The object allstn_models, a list of 13, is a set of lm() models for 13 different stations.

I went back to the example in the textbook and used the gapminder dataset and followed through with the example code. It worked without issue.

So I then thought to convert my original dataframe to a tibble. But that did not solve the problem.

Any suggestions to correct my error are appreciated.