Click here for the data

Import Data

nyt_titles <- 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 ▇▅▃▃▂ 
data <- nyt_titles

Explore Data

Identify Good Predictors

first week

data %>%
    ggplot(aes(first_week, best_rank)) +
    geom_point()

author

data %>%
    ggplot(aes(author, debut_rank)) +
    geom_boxplot()

year

data %>%
    ggplot(aes(year, debut_rank)) +
    geom_line()

data %>%
    
    # tokenize title
    unnest_tokens(output = word, input = title) %>%
    
    # calculate avg rent per word
    group_by(word) %>%
    summarise(debut_rank = mean(debut_rank),
              n     = n()) %>%
    ungroup() %>%
    
    filter(n > 10, !str_detect(word, "\\d")) %>%
    slice_max(order_by = debut_rank, n = 30)
## # A tibble: 31 × 3
##    word    debut_rank     n
##    <chr>        <dbl> <int>
##  1 fatal        11.7     11
##  2 room         11.1     15
##  3 gate         11       13
##  4 ice          10.9     11
##  5 beyond       10.5     12
##  6 never        10.4     12
##  7 water        10.1     17
##  8 tell         10       11
##  9 devil's       9.93    14
## 10 silver        9.92    13
## # ℹ 21 more rows

Build Models

data <- sample_n(data, 100)

# Split into training and test dataset
set.seed(1234)
data_split <- rsample::initial_split(data)
data_train <- training(data_split)
data_test <- testing(data_split)

# further split 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]> Fold10
library(usemodels)
usemodels::use_xgboost(debut_rank ~ ., data = data_train)
## xgboost_recipe <- 
##   recipe(formula = debut_rank ~ ., 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
xgboost_recipe <- 
    recipe(formula = debut_rank ~ ., data = data_train) %>% 
  recipes::update_role(title, new_role = "id variable") %>%
    step_tokenize(title) %>%
    step_tokenfilter(max_tokens = 100) %>%
    step_tfidf(title) %>%
    step_other(author) %>%
    step_log(total_weeks, debut_rank, best_rank)
    


xgboost_recipe %>% prep() %>% juice() %>% glimpse()
## Rows: 75
## Columns: 166
## $ id                       <dbl> 6362, 1789, 135, 7388, 4260, 7125, 2170, 4247…
## $ author                   <fct> other, other, other, other, other, other, oth…
## $ year                     <dbl> 1937, 2010, 2015, 1974, 1946, 1958, 2016, 197…
## $ total_weeks              <dbl> 0.0000000, 1.0986123, 2.3025851, 1.9459101, 2…
## $ first_week               <date> 1937-02-08, 2010-05-30, 2015-10-25, 1974-05-…
## $ best_rank                <dbl> 1.9459101, 1.0986123, 0.6931472, 1.9459101, 1…
## $ debut_rank               <dbl> 1.945910, 1.386294, 2.639057, 2.079442, 1.945…
## $ tfidf_title_a            <dbl> 0.0000000, 0.0000000, 0.5430161, 0.0000000, 0…
## $ tfidf_title_alive        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_all          <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_am           <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_and          <dbl> 0.0000000, 0.0000000, 0.0000000, 0.8145241, 0…
## $ tfidf_title_babe         <dbl> 0.000000, 0.000000, 0.000000, 1.082683, 0.000…
## $ tfidf_title_babylon      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_be           <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_belgarath    <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_belongs      <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_bleu         <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_bones        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_box          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_bright       <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_burgoyne     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_camillo      <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_catcher      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_chance       <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_christmas    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_clown        <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_code         <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_contenders   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_d.c          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_da           <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_danger       <dbl> 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, …
## $ tfidf_title_deceiver     <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_demon        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_destiny      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_dirty        <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_don          <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_doomsday     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_dragons      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_dream        <dbl> 0.000000, 2.165367, 0.000000, 0.000000, 0.000…
## $ tfidf_title_dress        <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_eagle        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_earth        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_edge         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_empire       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_esquire      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_europe       <dbl> 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, …
## $ tfidf_title_fancy        <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_feet         <dbl> 0.8661467, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_fever        <dbl> 0.000000, 2.165367, 0.000000, 0.000000, 0.000…
## $ tfidf_title_fire         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_flames       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_flight       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_flock        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_flown        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_for          <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_gemini       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_gold         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_gondolin     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_goodbye      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_greengage    <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_guns         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_h            <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_halo         <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_has          <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_heart        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_here         <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_his          <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_hornet       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_house        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_i            <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ `tfidf_title_i'll`       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_ice          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_in           <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_inherent     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_job          <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_karanda      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_key          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_kin          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_kingdoms     <dbl> 0.0000000, 0.0000000, 0.7217889, 0.0000000, 0…
## $ tfidf_title_kiss         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_kissing      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_knight       <dbl> 0.0000000, 0.0000000, 0.7217889, 0.0000000, 0…
## $ tfidf_title_knives       <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_labyrinth    <dbl> 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, …
## $ tfidf_title_lies         <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_life         <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_lightship    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_like         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_lord         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_m            <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_me           <dbl> 0.0000000, 0.0000000, 0.0000000, 0.9126646, 0…
## $ tfidf_title_midnight     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_month        <dbl> 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, 0.000…
## $ tfidf_title_mystery      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_nature       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_nine         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_not          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_obsession    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_of           <dbl> 0.3962003, 0.0000000, 0.3301669, 0.0000000, 0…
## $ tfidf_title_old          <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_or           <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_our          <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_party        <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_phasma       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_pillars      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_pink         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_pot          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_pretty       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_pulham       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_rising       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_running      <dbl> 0.8661467, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_rye          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_sacré        <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_second       <dbl> 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, …
## $ tfidf_title_seeing       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_services     <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_seven        <dbl> 0.0000000, 0.0000000, 0.7217889, 0.0000000, 0…
## $ tfidf_title_shalimar     <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_silentium    <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_skin         <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_soldier      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_someone      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_song         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_sorcerer     <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_sound        <dbl> 0.8661467, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_special      <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_sphinx       <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_spider       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_spirits      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_spoonhandle  <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 4.330…
## $ tfidf_title_star         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_summer       <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_sundays      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_superstition <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_suspect      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_suspicion    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_temptation   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_tenderloin   <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_terrorist    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_the          <dbl> 0.2967337, 0.0000000, 0.2472781, 0.0000000, 0…
## $ tfidf_title_this         <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_to           <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_title_tomorrow     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_toys         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_twenty       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_vice         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_victorine    <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_vinci        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_wars         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_washington   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_white        <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_wishes       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_with         <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_title_woman        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_wrecker      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_years        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_you          <dbl> 0.0000000, 0.0000000, 0.0000000, 0.8145241, 0…
## $ tfidf_title_your         <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
# 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
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 = 10)
## i Creating pre-processing data to finalize unknown parameter: mtry
## → A | error:   Some columns are non-numeric. The data cannot be converted to numeric matrix: 'author', 'first_week'.
## 
There were issues with some computations   A: x1

There were issues with some computations   A: x2

There were issues with some computations   A: x7

There were issues with some computations   A: x11

There were issues with some computations   A: x16

There were issues with some computations   A: x21

There were issues with some computations   A: x26

There were issues with some computations   A: x31

There were issues with some computations   A: x34

There were issues with some computations   A: x40

There were issues with some computations   A: x43

There were issues with some computations   A: x49

There were issues with some computations   A: x53

There were issues with some computations   A: x58

There were issues with some computations   A: x62

There were issues with some computations   A: x68

There were issues with some computations   A: x72

There were issues with some computations   A: x77

There were issues with some computations   A: x81

There were issues with some computations   A: x86

There were issues with some computations   A: x91

There were issues with some computations   A: x96

There were issues with some computations   A: x100
## Warning: All models failed. Run `show_notes(.Last.tune.result)` for more
## information.