Apply it to your data3
Jackson Chicklis
2026-02-20
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 | ▇▅▃▃▂ |
data1 <- nyt_titles %>%
#treat missing values
select(-id, -year, -first_week) %>%
na.omit() %>%
#log transform variables with pos-skewed distribution
mutate(total_weeks = log(total_weeks))data_binarized_tbl1 <- data1 %>%
select(-author) %>%
binarize()
#step 2 correlate
data_corr_tbl1 <- data_binarized_tbl1 %>%
correlate(total_weeks__0.693147180559945_1.38629436111989)
data_corr_tbl1 %>%
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.
Split data
#data <- sample_n(data, 100)
#split into train and test dataset
set.seed(1234)
data_split <- rsample::initial_split(data1)
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 [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]> Fold10library(usemodels)
usemodels::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"))xgboost_recipe <-
recipe(formula = total_weeks ~ ., data = data_train) %>%
step_tokenize(title) %>%
step_tokenfilter(title, max_tokens = 100) %>%
step_tfidf(title) %>%
step_other(author, threshold = 0.003) %>%
step_dummy(author) %>%
step_zv(all_predictors())
xgboost_recipe %>% prep() %>% juice() %>% glimpse## Rows: 5,570
## Columns: 144
## $ debut_rank <dbl> 8, 4, 14, 4, 12, 12, 10, 6, 7…
## $ best_rank <dbl> 10, 6, 13, 1, 6, 4, 7, 5, 8, …
## $ total_weeks <dbl> 2.1972246, 0.6931472, 0.00000…
## $ tfidf_title_a <dbl> 1.033044, 0.000000, 0.000000,…
## $ tfidf_title_after <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_all <dbl> 0.000000, 0.000000, 0.000000,…
## $ tfidf_title_an <dbl> 0.000000, 0.000000, 0.000000,…
## $ tfidf_title_and <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_are <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_as <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_at <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_big <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_black <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_blood <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_blue <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_bones <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_book <dbl> 0.000000, 0.000000, 0.000000,…
## $ tfidf_title_cat <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_christmas <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_cold <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_dark <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_day <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_days <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_dead <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_death <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_die <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_down <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_edge <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_fall <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_fire <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_first <dbl> 0.000000, 0.000000, 0.000000,…
## $ tfidf_title_for <dbl> 1.415046, 0.000000, 0.000000,…
## $ tfidf_title_from <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_game <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_girl <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_girls <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_god <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_golden <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_gone <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_good <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_heart <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_heaven <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_high <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_home <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_honor <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_house <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_i <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_in <dbl> 0.000000, 0.000000, 0.000000,…
## $ tfidf_title_is <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_island <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_lady <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_last <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_life <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_light <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_little <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_long <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_lost <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_love <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_man <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_me <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_men <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_midnight <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_moon <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_mr <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_murder <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_my <dbl> 0.000000, 0.000000, 0.000000,…
## $ tfidf_title_new <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_night <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_no <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_not <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_of <dbl> 0.0000000, 0.0000000, 0.00000…
## $ tfidf_title_on <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_one <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_prey <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_red <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_river <dbl> 0.000000, 0.000000, 0.000000,…
## $ tfidf_title_road <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_sea <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_second <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_secret <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_shadow <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_son <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_star <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_storm <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_street <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_summer <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_the <dbl> 0.4312176, 0.0000000, 0.00000…
## $ tfidf_title_this <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_three <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_time <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_to <dbl> 0.000000, 0.000000, 0.000000,…
## $ tfidf_title_tree <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_two <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_we <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_white <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_who <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_wife <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_wind <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_with <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_woman <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_world <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_you <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Anne.Rice <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Barbara.Taylor.Bradford <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Catherine.Coulter <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Danielle.Steel <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_David.Baldacci <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Dean.Koontz <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Debbie.Macomber <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Dick.Francis <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Douglas.Preston.and.Lincoln.Child <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Harlan.Coben <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Iris.Johansen <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_J..A..Jance <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_J..D..Robb <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Jack.Higgins <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_James.Lee.Burke <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_James.Patterson <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_James.Patterson.and.Maxine.Paetro <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Janet.Evanovich <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Jeffrey.Archer <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_John.Grisham <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_John.le.Carré <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_John.Sandford <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Jonathan.Kellerman <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Ken.Follett <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Lisa.Scottoline <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Mary.Higgins.Clark <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Michael.Connelly <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Nora.Roberts <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Patricia.Cornwell <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Richard.Paul.Evans <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Robert.B..Parker <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Robert.Ludlum <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Robin.Cook <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Sandra.Brown <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Stephen.King <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Stuart.Woods <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Sue.Grafton <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Taylor.Caldwell <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_Terry.Brooks <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,…
## $ author_W..E..B..Griffin <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ author_other <dbl> 1, 1, 1, 1, 1, 1, 1, 0, 1, 1,…xgboost_spec <-
boost_tree(trees = tune(), min_n = tune(), tree_depth = tune(), learn_rate = tune())%>%
set_mode("regression") %>%
set_engine("xgboost")
xgboost_workflow <-
workflow() %>%
add_recipe(xgboost_recipe) %>%
add_model(xgboost_spec)
set.seed(12193)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5)#evaluate models
tune::show_best(xgboost_tune, metric = "rmse")## # A tibble: 5 × 10
## trees min_n tree_depth learn_rate .metric .estimator mean n std_err
## <int> <int> <int> <dbl> <chr> <chr> <dbl> <int> <dbl>
## 1 1000 2 1 0.0750 rmse standard 0.830 10 0.00613
## 2 2000 40 8 0.0178 rmse standard 0.833 10 0.00711
## 3 1500 11 11 0.001 rmse standard 0.842 10 0.00511
## 4 500 21 15 0.316 rmse standard 0.905 10 0.00839
## 5 1 30 4 0.00422 rmse standard 1.11 10 0.00741
## # ℹ 1 more variable: .config <chr>#update the model by selecting 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.
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 0.817 pre0_mod0_post0
## 2 rsq standard 0.451 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()