goal: to predict how long a book will last on the NY Times Bestsellers list

Click here for the data

Import data

nyt_titles <- readr::read_tsv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-05-10/nyt_titles.tsv')
## Rows: 7431 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr  (2): title, author
## dbl  (5): id, year, total_weeks, debut_rank, best_rank
## date (1): first_week
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
skimr::skim(nyt_titles)
Data summary
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 ▇▅▃▃▂ 
my_data <- nyt_titles %>%
    select(-debut_rank, -first_week) %>%
    na.omit() %>%
    mutate(total_weeks = log(total_weeks))

skimr::skim(my_data)
Data summary
Name my_data
Number of rows 7427
Number of columns 6
_______________________
Column type frequency:
character 2
numeric 4
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
title 0 1 1 55 0 7168 0
author 0 1 4 73 0 2205 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
id 0 1 3716.06 2145.23 0 1858.50 3717.00 5573.5 7430.00 ▇▇▇▇▇
year 0 1 1989.63 26.21 1931 1968.00 2000.00 2011.0 2020.00 ▂▂▂▃▇
total_weeks 0 1 1.48 1.11 0 0.69 1.39 2.3 5.18 ▇▇▆▂▁
best_rank 0 1 6.92 4.57 1 3.00 6.00 10.5 17.00 ▇▅▃▃▂

Explore data

my_data_binarized <- my_data %>%
    select(-title, -id) %>%
               binarize()

my_data_binarized %>% glimpse
## Rows: 7,427
## Columns: 14
## $ author__Danielle_Steel                          <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `author__-OTHER`                                <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ `year__-Inf_1968`                               <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ year__1968_2000                                 <dbl> 1, 1, 1, 0, 0, 0, 1, 1…
## $ year__2000_2011                                 <dbl> 0, 0, 0, 0, 1, 0, 0, 0…
## $ year__2011_Inf                                  <dbl> 0, 0, 0, 1, 0, 1, 0, 0…
## $ `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…
## $ `best_rank__-Inf_3`                             <dbl> 1, 1, 0, 0, 0, 0, 1, 0…
## $ best_rank__3_6                                  <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ best_rank__6_10.5                               <dbl> 0, 0, 1, 0, 0, 1, 0, 1…
## $ best_rank__10.5_Inf                             <dbl> 0, 0, 0, 1, 1, 0, 0, 0…
mydata_correlate <- my_data_binarized %>%
    correlate(total_weeks__2.30258509299405_Inf)
mydata_correlate %>%
    plot_correlation_funnel()

Build Data

# my_data <- sample_n(my_data, 100)

# split data into training and testing

set.seed(1122)
my_data_split <- rsample::initial_split(my_data)
my_data_train <- training(my_data_split)
my_data_test <- testing(my_data_split)

# Further split training data
set.seed(2211)
my_data_cv <- rsample::vfold_cv(my_data_train)
my_data_cv
## #  10-fold cross-validation 
## # A tibble: 10 × 2
##    splits             id    
##    <list>             <chr> 
##  1 <split [5013/557]> Fold01
##  2 <split [5013/557]> Fold02
##  3 <split [5013/557]> Fold03
##  4 <split [5013/557]> Fold04
##  5 <split [5013/557]> Fold05
##  6 <split [5013/557]> Fold06
##  7 <split [5013/557]> Fold07
##  8 <split [5013/557]> Fold08
##  9 <split [5013/557]> Fold09
## 10 <split [5013/557]> Fold10
library(usemodels)
usemodels::use_xgboost(total_weeks ~ ., data = my_data_train)
## xgboost_recipe <- 
##   recipe(formula = total_weeks ~ ., data = my_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(94187)
## xgboost_tune <-
##   tune_grid(xgboost_workflow, resamples = stop("add your rsample object"), grid = stop("add number of candidate points"))
# Specify recipe
my_xgboost_recipe <- 
  recipe(formula = total_weeks ~ ., data = my_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(all_nominal_predictors(), one_hot = TRUE) %>%
    step_log(year, best_rank)
    
    
my_xgboost_recipe %>% prep() %>% juice() %>% glimpse()
## Rows: 5,570
## Columns: 106
## $ id                    <dbl> 556, 182, 387, 2072, 6718, 6674, 6901, 3890, 341…
## $ year                  <dbl> 7.580700, 7.601402, 7.608374, 7.606885, 7.609862…
## $ best_rank             <dbl> 2.5649494, 0.0000000, 2.6390573, 0.6931472, 1.94…
## $ total_weeks           <dbl> 1.6094379, 3.0910425, 0.0000000, 1.7917595, 1.38…
## $ tfidf_title_a         <dbl> 0.000000, 1.531764, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_all       <dbl> 0.000000, 0.000000, 1.190632, 0.000000, 0.000000…
## $ tfidf_title_an        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_and       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_angel     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_are       <dbl> 0, 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, 0, …
## $ tfidf_title_before    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_black     <dbl> 0, 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, 0, …
## $ tfidf_title_blue      <dbl> 0, 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, 0, …
## $ tfidf_title_book      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_cat       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_christmas <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_city      <dbl> 0, 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, 0, …
## $ tfidf_title_cross     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_dark      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_day       <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_days      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_dead      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_death     <dbl> 0.00000, 0.00000, 0.00000, 0.00000, 0.00000, 0.0…
## $ tfidf_title_devil     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_down      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_end       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_fall      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_family    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_fire      <dbl> 0, 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, 0, …
## $ tfidf_title_for       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_from      <dbl> 2.447496, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_game      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_girl      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_girls     <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_god       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_golden    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_good      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_heart     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_heaven    <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_her       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_home      <dbl> 2.705376, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_honor     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_house     <dbl> 0.00000, 2.35122, 0.00000, 0.00000, 0.00000, 0.0…
## $ tfidf_title_i         <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_in        <dbl> 0.0000000, 0.0000000, 0.8393239, 0.0000000, 0.00…
## $ tfidf_title_is        <dbl> 0.00000, 0.00000, 0.00000, 0.00000, 0.00000, 0.0…
## $ tfidf_title_island    <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_king      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_lady      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_last      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_life      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_light     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_little    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_long      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_lost      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_love      <dbl> 0.00000, 0.00000, 0.00000, 0.00000, 0.00000, 0.0…
## $ tfidf_title_man       <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_me        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_men       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_midnight  <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_moon      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_more      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_mr        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_mrs       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_murder    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_my        <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_new       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_night     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_no        <dbl> 0, 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, 0.00…
## $ tfidf_title_old       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_on        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_one       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_prey      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_red       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_road      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_second    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_secret    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_shadow    <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_son       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_star      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_storm     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_street    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_summer    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_the       <dbl> 0.0000000, 0.0000000, 0.6468264, 0.0000000, 1.29…
## $ tfidf_title_this      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_time      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_to        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_tree      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_two       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_we        <dbl> 0.00000, 0.00000, 0.00000, 0.00000, 0.00000, 0.0…
## $ tfidf_title_white     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_who       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_wife      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_winter    <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_with      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_woman     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_world     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_you       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ author_Danielle.Steel <dbl> 0, 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, 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 model using workflow
my_xgboost_workflow <- 
  workflow() %>% 
  add_recipe(my_xgboost_recipe) %>% 
  add_model(xgboost_spec) 

# tune hyperparameters
set.seed(34266)
my_xgboost_tune <-
  tune_grid(my_xgboost_workflow, 
            resamples = my_data_cv, 
            grid = 5)
## i Creating pre-processing data to finalize unknown parameter: mtry

Evaluate Model

tune::show_best(my_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    77  1213    38    0.00456 rmse    standard   0.545    10 0.00684 Preproces…
## 2    49  1106    29    0.114   rmse    standard   0.554    10 0.00682 Preproces…
## 3   103  1602     9    0.0647  rmse    standard   0.565    10 0.00747 Preproces…
## 4    13   142    11    0.0172  rmse    standard   0.753    10 0.00811 Preproces…
## 5    32   718    23    0.00142 rmse    standard   0.849    10 0.00902 Preproces…
my_xgboost_fw <- tune::finalize_workflow(my_xgboost_workflow,
                                         tune::select_best(my_xgboost_tune, metric = "rmse"))

my_data_fit <- tune::last_fit(my_xgboost_fw, my_data_split)
tune::collect_metrics(my_data_fit)
## # A tibble: 2 × 4
##   .metric .estimator .estimate .config             
##   <chr>   <chr>          <dbl> <chr>               
## 1 rmse    standard       0.538 Preprocessor1_Model1
## 2 rsq     standard       0.768 Preprocessor1_Model1
tune::collect_predictions(my_data_fit) %>%
    ggplot(aes(total_weeks, .pred)) +
    geom_point(alpha = 0.3, fill = "midnightblue") + 
    geom_abline(lty = 2, color = "gray50") + 
    coord_fixed()