Apply 3
Tyler Roden
2026-02-24
Import Data
nyt_titles <- readr::read_tsv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2022/2022-05-10/nyt_titles.tsv')
skimr::skim(nyt_titles)| Name | nyt_titles |
| Number of rows | 7431 |
| Number of columns | 8 |
| _______________________ | |
| Column type frequency: | |
| character | 2 |
| Date | 1 |
| numeric | 5 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| title | 0 | 1 | 1 | 74 | 0 | 7172 | 0 |
| author | 4 | 1 | 4 | 73 | 0 | 2205 | 0 |
Variable type: Date
| skim_variable | n_missing | complete_rate | min | max | median | n_unique |
|---|---|---|---|---|---|---|
| first_week | 0 | 1 | 1931-10-12 | 2020-12-06 | 2000-06-25 | 3348 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| id | 0 | 1 | 3715.00 | 2145.29 | 0 | 1857.5 | 3715 | 5572.5 | 7430 | ▇▇▇▇▇ |
| year | 0 | 1 | 1989.61 | 26.23 | 1931 | 1968.0 | 2000 | 2011.0 | 2020 | ▂▂▂▃▇ |
| total_weeks | 0 | 1 | 8.13 | 11.21 | 1 | 2.0 | 4 | 10.0 | 178 | ▇▁▁▁▁ |
| debut_rank | 0 | 1 | 7.90 | 4.57 | 1 | 4.0 | 8 | 12.0 | 17 | ▇▆▅▅▅ |
| best_rank | 0 | 1 | 6.91 | 4.57 | 1 | 3.0 | 6 | 10.0 | 17 | ▇▅▃▃▂ |
data <- nyt_titles %>%
# Treat missing values
select(-debut_rank, -best_rank, -first_week) %>%
na.omit() %>%
filter(total_weeks <= 100) %>%
# log transform variables with pos-skewed distribution
mutate(total_weeks = log(total_weeks))
data## # A tibble: 7,416 × 5
## id title author year total_weeks
## <dbl> <chr> <chr> <dbl> <dbl>
## 1 0 "\"H\" IS FOR HOMICIDE" Sue Grafton 1991 2.71
## 2 1 "\"I\" IS FOR INNOCENT" Sue Grafton 1992 2.40
## 3 10 "''G'' IS FOR GUMSHOE" Sue Grafton 1990 1.79
## 4 100 "A DOG'S JOURNEY" W. Bruce Cameron 2012 0
## 5 1000 "CHANGING FACES" Kimberla Lawson Roby 2006 0
## 6 1001 "CHAOS" Patricia Cornwell 2016 1.10
## 7 1002 "CHAPTERHOUSE: DUNE" Frank Herbert 1985 2.77
## 8 1003 "CHARADE" Sandra Brown 1994 1.61
## 9 1004 "CHARLESTON" John Jakes 2002 1.39
## 10 1005 "CHARLOTTE GRAY" Sebastian Faulks 1999 0
## # ℹ 7,406 more rowsExplore Data
data %>%
ggplot(aes(total_weeks,author)) +
geom_point()
data %>%
ggplot(aes(total_weeks,year)) +
geom_point()
data_binarized_tbl <- data %>%
select(-year) %>%
binarize()
data_binarized_tbl %>% glimpse()## Rows: 7,416
## Columns: 12
## $ `id__-Inf_1858.75` <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ id__1858.75_3715.5 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ id__3715.5_5574.25 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ id__5574.25_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ title__GONE <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `title__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ author__Danielle_Steel <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `author__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ `total_weeks__-Inf_0.693147180559945` <dbl> 0, 0, 0, 1, 1, 0, 0, 0…
## $ total_weeks__0.693147180559945_1.38629436111989 <dbl> 0, 0, 0, 0, 0, 1, 0, 0…
## $ total_weeks__1.38629436111989_2.30258509299405 <dbl> 0, 0, 1, 0, 0, 0, 0, 1…
## $ total_weeks__2.30258509299405_Inf <dbl> 1, 1, 0, 0, 0, 0, 1, 0…data_corr_tbl <- data_binarized_tbl %>%
correlate(total_weeks__2.30258509299405_Inf)
data_corr_tbl## # A tibble: 12 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 total_weeks 2.30258509299405_Inf 1
## 2 total_weeks -Inf_0.693147180559945 -0.396
## 3 total_weeks 1.38629436111989_2.30258509299405 -0.322
## 4 total_weeks 0.693147180559945_1.38629436111989 -0.256
## 5 id -Inf_1858.75 -0.0279
## 6 id 3715.5_5574.25 0.0235
## 7 title -OTHER 0.0129
## 8 title GONE -0.0129
## 9 id 5574.25_Inf 0.00880
## 10 id 1858.75_3715.5 -0.00440
## 11 author Danielle_Steel 0.00425
## 12 author -OTHER -0.00425data_corr_tbl %>%
plot_correlation_funnel()## Warning: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## ℹ The deprecated feature was likely used in the correlationfunnel package.
## Please report the issue at
## <https://github.com/business-science/correlationfunnel/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: The `size` argument of `element_rect()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## ℹ The deprecated feature was likely used in the correlationfunnel package.
## Please report the issue at
## <https://github.com/business-science/correlationfunnel/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
Build Models
data <- sample_n(data, 100)
# Split into train and test dataset
set.seed(1234)
data_split <- rsample::initial_split(data)
data_train <- training(data_split)
data_test <- testing(data_split)
# Further spit training dataset for cross-validation
set.seed(2345)
data_cv <- rsample::vfold_cv(data_train)
data_cv## # 10-fold cross-validation
## # A tibble: 10 × 2
## splits id
## <list> <chr>
## 1 <split [67/8]> Fold01
## 2 <split [67/8]> Fold02
## 3 <split [67/8]> Fold03
## 4 <split [67/8]> Fold04
## 5 <split [67/8]> Fold05
## 6 <split [68/7]> Fold06
## 7 <split [68/7]> Fold07
## 8 <split [68/7]> Fold08
## 9 <split [68/7]> Fold09
## 10 <split [68/7]> Fold10usemodels::use_xgboost(total_weeks ~ ., data = data_train)## xgboost_recipe <-
## recipe(formula = total_weeks ~ ., data = data_train) %>%
## step_zv(all_predictors())
##
## xgboost_spec <-
## boost_tree(trees = tune(), min_n = tune(), tree_depth = tune(), learn_rate = tune(),
## loss_reduction = tune(), sample_size = tune()) %>%
## set_mode("classification") %>%
## set_engine("xgboost")
##
## xgboost_workflow <-
## workflow() %>%
## add_recipe(xgboost_recipe) %>%
## add_model(xgboost_spec)
##
## set.seed(6804)
## xgboost_tune <-
## tune_grid(xgboost_workflow, resamples = stop("add your rsample object"), grid = stop("add number of candidate points"))# Specify recipe
# Specify recipe
xgboost_recipe <-
recipe(formula = total_weeks ~ ., data = data_train) %>%
recipes::update_role(id, new_role = "id variable") %>%
step_tokenize(title) %>%
step_tokenfilter(title, max_tokens = 100) %>%
step_tfidf(title) %>%
step_other(author) %>%
step_dummy(author, all_nominal_predictors(), one_hot = TRUE) %>%
step_zv(all_predictors())
xgboost_recipe %>% prep() %>% juice() %>% glimpse()## Rows: 75
## Columns: 105
## $ id <dbl> 4830, 3939, 1937, 5744, 2112, 3738, 3495, 458…
## $ year <dbl> 1995, 1954, 2008, 1985, 1990, 2002, 2007, 198…
## $ total_weeks <dbl> 3.367296, 3.044522, 1.791759, 3.850148, 2.079…
## $ tfidf_title_206 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_a <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_against <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_aimless <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_all <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_america <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_among <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_an <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_and <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_as <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_assassin <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_at <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_attorney <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_bachman <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_beloved <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_birds <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_blood <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_blue <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_bones <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_books <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_bother <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_box <dbl> 1.443578, 0.000000, 0.000000, 0.000000, 0.000…
## $ `tfidf_title_brother's` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_came <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_can <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_captain <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_cat <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_catch <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_centennial <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_chef <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_christmas <dbl> 1.443578, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_circus <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_cold <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_cross <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_currents <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_daniel <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_daughters <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `tfidf_title_day's` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_dead <dbl> 0.000000, 0.000000, 2.165367, 0.000000, 0.000…
## $ tfidf_title_dearly <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_devil <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_dinner <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_directive <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_disclosure <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_document <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_dream <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_dying <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_equals <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_false <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_firestarter <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_first <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_five <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_for <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_fortune <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_from <dbl> 0.000000, 0.000000, 1.629048, 0.000000, 0.000…
## $ tfidf_title_future <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_game <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_glass <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_gold <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_goodbar <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_grant <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_hampshire <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_harmful <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 2.165…
## $ tfidf_title_hattie <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_haunted <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_have <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_heist <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_hill <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_holdout <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_home <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_hotel <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_houseful <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_hunters <dbl> 0.000000, 0.000000, 0.000000, 1.443578, 0.000…
## $ tfidf_title_i <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_impression <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_in <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_inconvenient <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_intent <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 2.165…
## $ tfidf_title_iron <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_janson <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_jingle <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_kings <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_kiss <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_known <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_knows <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_last <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_liar <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_light <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_lion <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_long <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_looking <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_love <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_lying <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_mammoth <dbl> 0.000000, 0.000000, 0.000000, 1.443578, 0.000…
## $ tfidf_title_man <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_martin <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_mr <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_of <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_the <dbl> 0.4175877, 0.0000000, 0.0000000, 0.4175877, 0…
## $ tfidf_title_woman <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ author_David.Baldacci <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ author_other <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …# Specify model
xgboost_spec <-
boost_tree(trees = tune(), min_n = tune(), mtry = tune(), learn_rate = tune()) %>%
set_mode("regression") %>%
set_engine("xgboost")
# Combine recipe and models using workflow
xgboost_workflow <-
workflow() %>%
add_recipe(xgboost_recipe) %>%
add_model(xgboost_spec)
# Tune hyperparameters
set.seed(6804)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5)Evaluate Models
tune::show_best(xgboost_tune, metric = "rmse")## # A tibble: 5 × 10
## mtry trees min_n learn_rate .metric .estimator mean n std_err .config
## <int> <int> <int> <dbl> <chr> <chr> <dbl> <int> <dbl> <chr>
## 1 103 2000 21 0.0178 rmse standard 1.06 10 0.117 pre0_mod5…
## 2 77 500 30 0.001 rmse standard 1.13 10 0.0923 pre0_mod4…
## 3 52 1 2 0.0750 rmse standard 1.18 10 0.0926 pre0_mod3…
## 4 1 1500 11 0.00422 rmse standard 1.19 10 0.0908 pre0_mod1…
## 5 26 1000 40 0.316 rmse standard 1.21 10 0.0904 pre0_mod2…# Upadate the model by selecting the best hyperparameters
xgboost_fw <- tune::finalize_workflow(xgboost_workflow,
tune::select_best(xgboost_tune, metric = "rmse"))
# Fit the model on the entire training data and test it on the test data site
data_fit <- tune::last_fit(xgboost_fw, data_split)
tune::collect_metrics(data_fit)## # A tibble: 2 × 4
## .metric .estimator .estimate .config
## <chr> <chr> <dbl> <chr>
## 1 rmse standard 0.838 pre0_mod0_post0
## 2 rsq standard 0.275 pre0_mod0_post0