control outcome transformations

[topepo]

The extract_* functions do different things when there is an outcome transformation in a formula:

library(tidymodels)
library(important)

tidymodels_prefer()
theme_set(theme_bw())
options(pillar.advice = FALSE, pillar.min_title_chars = Inf)

# In-line function in preprocessor formula

ames <- ames %>% select(Sale_Price, Lot_Area, Neighborhood)

lm_wflow <- workflow(log(Sale_Price) ~ . , linear_reg())
lm_fit <- fit(lm_wflow, ames)

# Different variable names and units
important:::extract_data_original(lm_fit, head(ames)) %>% 
    select(contains("Sale"))
#> # A tibble: 6 × 1
#>   Sale_Price
#>        <int>
#> 1     215000
#> 2     105000
#> 3     172000
#> 4     244000
#> 5     189900
#> 6     195500
important:::extract_data_derived(lm_fit, head(ames)) %>% 
    select(contains("Sale"))
#> # A tibble: 6 × 1
#>   `log(Sale_Price)`
#>               <dbl>
#> 1              12.3
#> 2              11.6
#> 3              12.1
#> 4              12.4
#> 5              12.2
#> 6              12.2

# In-line function in extra formula from add_model()

lm_form_wflow <- 
    workflow() %>% 
    add_formula(Sale_Price~ . ) %>% 
    add_model(linear_reg(), formula = log(Sale_Price) ~ .)

lm_form_fit <- fit(lm_form_wflow, ames)

# Same variable names and units
important:::extract_data_original(lm_form_fit, head(ames)) %>% 
    select(contains("Sale"))
#> # A tibble: 6 × 1
#>   Sale_Price
#>        <int>
#> 1     215000
#> 2     105000
#> 3     172000
#> 4     244000
#> 5     189900
#> 6     195500
important:::extract_data_derived(lm_form_fit, head(ames)) %>% 
    select(contains("Sale"))
#> # A tibble: 6 × 1
#>   Sale_Price
#>        <int>
#> 1     215000
#> 2     105000
#> 3     172000
#> 4     244000
#> 5     189900
#> 6     195500

This may be intended/helpful in some cases but definitely not in others. We should perhaps make an option for this.

[topepo]

library(tidymodels)
library(important)

tidymodels_prefer()
theme_set(theme_bw())
options(pillar.advice = FALSE, pillar.min_title_chars = Inf)

# In-line function in preprocessor formula

ames <- ames %>% select(Sale_Price, Lot_Area, Neighborhood)

lm_wflow <- workflow(log(Sale_Price) ~ . , linear_reg())
lm_fit <- fit(lm_wflow, ames)

# Maybe detect when a formula preprocessor is used, look for transformations, 
# then return just the column name when this happens. 

lm_fit |> 
    hardhat::extract_mold() |> 
    purrr::pluck("blueprint") %>% 
    pluck("formula") %>% 
    rlang::f_lhs() %>% 
    all.vars()
#> [1] "Sale_Price"

^{Created on 2024-12-18 with reprex v2.1.0}