recipes 1.1.0 will work work sf objects

[EmilHvitfeldt]

In the upcoming recipes release you will be able to pass in a sf object without error.
Release tracked with tidymodels/recipes#1342.

I just wanted to let you know since I know that {tidysdm} works on such problems.

library(spatialsample)
library(recipes)

boston_canopy
#> Simple feature collection with 682 features and 18 fields
#> Geometry type: MULTIPOLYGON
#> Dimension:     XY
#> Bounding box:  xmin: 739826.9 ymin: 2908294 xmax: 812069.7 ymax: 2970073
#> Projected CRS: NAD83 / Massachusetts Mainland (ftUS)
#> # A tibble: 682 × 19
#>    grid_id land_area canopy_gain canopy_loss canopy_no_change canopy_area_2014
#>    <chr>       <dbl>       <dbl>       <dbl>            <dbl>            <dbl>
#>  1 AB-4      795045.      15323.       3126.           53676.           56802.
#>  2 I-33      265813.       8849.      11795.           78677.           90472.
#>  3 AO-9      270153        6187.       1184.           26930.           28114.
#>  4 H-10     2691490.      73098.      80362.          345823.          426185.
#>  5 V-7       107890.        219.       3612.             240.            3852.
#>  6 Q-22     2648089.     122211.     154236.         1026632.         1180868.
#>  7 X-4       848558.       8275.       1760.            6872.            8632.
#>  8 P-18     2690726.     110928.     113146.          915137.         1028283.
#>  9 J-29     2574479.      38069.      15530.         2388638.         2404168.
#> 10 G-28     2641525.      87024.      39246.         1202528.         1241774.
#> # ℹ 672 more rows
#> # ℹ 13 more variables: canopy_area_2019 <dbl>, change_canopy_area <dbl>,
#> #   change_canopy_percentage <dbl>, canopy_percentage_2014 <dbl>,
#> #   canopy_percentage_2019 <dbl>, change_canopy_absolute <dbl>,
#> #   mean_temp_morning <dbl>, mean_temp_evening <dbl>, mean_temp <dbl>,
#> #   mean_heat_index_morning <dbl>, mean_heat_index_evening <dbl>,
#> #   mean_heat_index <dbl>, geometry <MULTIPOLYGON [US_survey_foot]>

recipe(land_area ~ ., data = boston_canopy)
#> 
#> ── Recipe ──────────────────────────────────────────────────────────────────────
#> 
#> ── Inputs
#> Number of variables by role
#> outcome:    1
#> predictor: 18

[dramanica]

Thanks @EmilHvitfeldt, I'll have a thorough test with the RC for {recipes}, and then submit an updated version to CRAN early next week.

[dramanica]

@EmilHvitfeldt this is fixed in the new version now on CRAN