Apply to your data 3
Liam Smith
2026-02-20
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 [5005/557]> Fold01
## 2 <split [5005/557]> Fold02
## 3 <split [5006/556]> Fold03
## 4 <split [5006/556]> Fold04
## 5 <split [5006/556]> Fold05
## 6 <split [5006/556]> Fold06
## 7 <split [5006/556]> Fold07
## 8 <split [5006/556]> Fold08
## 9 <split [5006/556]> Fold09
## 10 <split [5006/556]> 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(41811)
## 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_other(author) %>%
step_dummy(author, all_nominal_predictors(), one_hot = TRUE) %>%
step_zv(all_predictors())
xgboost_recipe %>% prep() %>% juice() %>% glimpse()## Rows: 5,562
## Columns: 105
## $ id <dbl> 77, 866, 1901, 1558, 7355, 3425, 1839, 5052, 365…
## $ year <dbl> 1996, 2000, 1951, 1936, 1948, 1996, 2009, 2010, …
## $ total_weeks <dbl> 2.0794415, 0.0000000, 0.0000000, 3.8286414, 2.30…
## $ tfidf_title_a <dbl> 1.545264, 0.000000, 0.000000, 0.000000, 1.030176…
## $ tfidf_title_after <dbl> 0, 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, 0, …
## $ tfidf_title_an <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_and <dbl> 0.00000, 0.00000, 0.00000, 0.00000, 0.00000, 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> 0.000, 0.000, 0.000, 0.000, 0.000, 0.000, 0.000,…
## $ 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_by <dbl> 0, 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, 0.000000…
## $ 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_dark <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_daughter <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_day <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ 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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_die <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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_for <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_from <dbl> 0, 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, 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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ 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_gone <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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_high <dbl> 0, 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, 0, …
## $ 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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_i <dbl> 0, 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, 0.000000…
## $ tfidf_title_is <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_island <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ 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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_man <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ 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_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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ 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_not <dbl> 0.00000, 5.63157, 0.00000, 0.00000, 0.00000, 0.0…
## $ tfidf_title_of <dbl> 1.0874237, 0.0000000, 0.0000000, 0.0000000, 0.00…
## $ tfidf_title_on <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ 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_river <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_sea <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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ 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_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, 0.0000000, 1.2998935, 0.00…
## $ tfidf_title_this <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_three <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_two <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_we <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 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_with <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 1.673142…
## $ tfidf_title_woman <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 1.721238…
## $ 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 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)## i Creating pre-processing data to finalize 1 unknown parameter: "mtry"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 0.982 10 0.00728 pre0_mod5…
## 2 26 1000 40 0.316 rmse standard 0.997 10 0.00980 pre0_mod2…
## 3 77 500 30 0.001 rmse standard 1.02 10 0.00811 pre0_mod4…
## 4 1 1500 11 0.00422 rmse standard 1.05 10 0.00772 pre0_mod1…
## 5 52 1 2 0.0750 rmse standard 1.08 10 0.00879 pre0_mod3…# 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 0.970 pre0_mod0_post0
## 2 rsq standard 0.231 pre0_mod0_post0tune::collect_predictions(data_fit) %>%
ggplot(aes(total_weeks, .pred)) +
geom_point(alpha = 0.3, fill = "midnightblue") +
geom_abline(lty = 2, color = "gray50") +
coord_fixed()