Apply to your data 2
Liam Smith
2026-02-13
Import Data
nyt_titles <- readr::read_tsv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/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)| 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()
# Prepare
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…# Correlate
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 GONE -0.0129
## 8 title -OTHER 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 -0.00425# Plot
data_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 every 8 hours.
## 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 every 8 hours.
## 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]> Fold10library(usemodels)## Warning: package 'usemodels' was built under R version 4.5.2usemodels::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
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_tokenize(author) %>%
step_tokenfilter(author, max_tokens = 100) %>%
step_tfidf(author) %>%
step_zv(all_predictors()) %>%
step_dummy(all_nominal_predictors(), one_hot = TRUE)
xgboost_recipe %>% prep() %>% juice() %>% glimpse()## Rows: 75
## Columns: 203
## $ id <dbl> 6499, 3669, 840, 234, 4209, 4702, 4054, 103…
## $ year <dbl> 1959, 2002, 2013, 2015, 1948, 1980, 2003, 1…
## $ total_weeks <dbl> 1.0986123, 1.7917595, 0.6931472, 2.5649494,…
## $ tfidf_title_47th <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_a <dbl> 0.0000000, 0.0000000, 0.0000000, 0.9943845,…
## $ tfidf_title_abiding <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_abode <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_about <dbl> 0.0000000, 0.0000000, 0.7217889, 0.0000000,…
## $ tfidf_title_abstinence <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_account <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_agent <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_american <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_and <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_title_any <dbl> 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…
## $ tfidf_title_bare <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_blue <dbl> 0.000000, 0.000000, 0.000000, 1.443578, 0.0…
## $ tfidf_title_blues <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_bourne <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_boy <dbl> 0.0000000, 0.0000000, 0.7217889, 0.0000000,…
## $ tfidf_title_bride <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_bridget <dbl> 0.0000000, 0.0000000, 0.7217889, 0.0000000,…
## $ tfidf_title_career <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_catch <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_chances <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_china <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_choice <dbl> 2.165367, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_coma <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_corner <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_title_countdown <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_court <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_courtship <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_creation <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_darkest <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_darkness <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_date <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_daughter <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_dead <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_title_death <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_demons <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_die <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_dog <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_dreams <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_dwell <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_evening <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_evil <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_eye <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_title_few <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_first <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_fisherman <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_for <dbl> 0.000000, 1.491577, 0.000000, 0.000000, 0.0…
## $ tfidf_title_four <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_from <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_title_frozen <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_fundamentalist <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_gathering <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_girl <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_glory <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_god <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_goddess <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_golden <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_goodbar <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_hard <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_heaven <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_his <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_title_homeland <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_hound <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_hours <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_identity <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_in <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_title_is <dbl> 0.000000, 1.825329, 0.000000, 0.000000, 0.0…
## $ tfidf_title_jones <dbl> 0.0000000, 0.0000000, 0.7217889, 0.0000000,…
## $ tfidf_title_king <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> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_title_lawyer <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_leaving <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_legacy <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_leia <dbl> 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…
## $ tfidf_title_line <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_looking <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_love <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_mad <dbl> 0.0000000, 0.0000000, 0.7217889, 0.0000000,…
## $ tfidf_title_man <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_matarese <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_me <dbl> 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…
## $ tfidf_title_mischief <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_moon <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 1.2…
## $ tfidf_title_more <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_mountains <dbl> 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…
## $ tfidf_title_naked <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_title_nature <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_title_new <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, 0.5972532,…
## $ tfidf_title_shadow <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_title_the <dbl> 0.6645680, 0.0000000, 0.2215227, 0.0000000,…
## $ tfidf_title_time <dbl> 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…
## $ tfidf_author_a <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_allison <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_amanda <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_and <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_author_andrews <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_ann <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_anne <dbl> 0.000000, 0.000000, 0.000000, 4.330733, 0.0…
## $ tfidf_author_aubrey <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_bach <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_berry <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_bradda <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_brandon <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_burcell <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_author_by <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_caldwell <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_carl <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_carré <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_child <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_christopher <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_cleeves <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_clive <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_author_cook <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_crombie <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_cussler <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_author_d <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_danielle <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_dave <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_dean <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_deborah <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_denis <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_dorst <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_doug <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_dustin <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_edward <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_elizabeth <dbl> 2.165367, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_erica <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_evanovich <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_field <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_fielding <dbl> 0.000000, 0.000000, 2.165367, 0.000000, 0.0…
## $ tfidf_author_fred <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_galbraith <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_gallico <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_garwood <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_george <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 1.4…
## $ tfidf_author_gipson <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_godden <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_goodkind <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_grafton <dbl> 0.000000, 1.825329, 0.000000, 0.000000, 0.0…
## $ tfidf_author_grisham <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_hamid <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_harold <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_harrison <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_harry <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_hayden <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_helen <dbl> 0.000000, 0.000000, 2.165367, 0.000000, 0.0…
## $ tfidf_author_heller <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_hiaasen <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_hitrec <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 1.4…
## $ tfidf_author_hunter <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_ian <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_author_illustrated <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_j <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_j.d <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_jacqueline <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_jakes <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_jan <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_jance <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_janet <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_janeway <dbl> 2.165367, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_jayne <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_jeff <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_jodi <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_john <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_johnson <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_jong <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_jordan <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_joseph <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 1.2…
## $ tfidf_author_judith <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_julie <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_karin <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_karon <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_kathy <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_kay <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_kaye <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_kim <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_kinsella <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_koontz <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_krentz <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_l <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_le <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_lee <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_ludlum <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_mary <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_morris <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_richard <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ tfidf_author_robb <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_author_robert <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_author_robin <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000,…
## $ tfidf_author_sue <dbl> 0.000000, 1.825329, 0.000000, 0.000000, 0.0…
## $ tfidf_author_west <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…# Specify model
xgboost_spec <-
boost_tree(trees = tune(), min_n = tune(), tree_depth = tune(), learn_rate = tune(),
loss_reduction = tune(), sample_size = 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)## → A | warning: A correlation computation is required, but `estimate` is constant and has 0
## standard deviation, resulting in a divide by 0 error. `NA` will be returned.## There were issues with some computations A: x3There were issues with some computations A: x6There were issues with some computations A: x9There were issues with some computations A: x12There were issues with some computations A: x15There were issues with some computations A: x18There were issues with some computations A: x21There were issues with some computations A: x24There were issues with some computations A: x27There were issues with some computations A: x30There were issues with some computations A: x30