Apply 2: nyt_titles
Reed Wilson
2024-02-07
Goal: To predict total weeks on best sellers list
Click[here for the data] (‘https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-05-10/nyt_titles.tsv’)
nyt_titles <- readr::read_tsv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-05-10/nyt_titles.tsv')
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(-id) %>%
filter(!is.na(author)) %>%
filter(total_weeks < 100) %>%
mutate(total_weeks = log(total_weeks)) %>%
mutate(decade = year %/% 10 * 10)#Explore Data
Identify Good Predictors
best_rank
data%>%
ggplot(aes(total_weeks, best_rank)) +
scale_y_log10() +
geom_point()
debut_rank
data%>%
ggplot(aes(total_weeks, as.factor(debut_rank))) +
geom_boxplot()
author
data %>%
group_by(author) %>%
summarise(total_weeks_avg = mean(total_weeks)) %>% ungroup() %>%
slice_max(order_by = total_weeks_avg, n = 20) %>%
ggplot(aes(total_weeks_avg, fct_reorder(author, total_weeks_avg))) +
geom_col() +
labs(title = "Best Author by Total Weeks", y = NULL)
Title
data %>%
#tokenize title
unnest_tokens(output = word, input = title) %>%
#calculate avg rent per word
group_by(word) %>%
summarise(total_weeks = mean(total_weeks),
n = n()) %>%
ungroup() %>%
filter(n > 10, !str_detect(word, "\\a")) %>%
slice_max(order_by = total_weeks, n = 20) %>%
#plot
ggplot(aes(total_weeks, fct_reorder(word, total_weeks))) +
geom_point() +
labs(y = "Words in Title")
EDA shortcut
# step 1 - prepare data
data_binarized_tbl <- data %>%
select(-author, -title, -first_week) %>%
binarize()
data_binarized_tbl %>% glimpse()## Rows: 7,415
## Columns: 24
## $ `id__-Inf_1858.5` <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ id__1858.5_3715 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ id__3715_5574.5 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ id__5574.5_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `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…
## $ `debut_rank__-Inf_4` <dbl> 1, 0, 1, 1, 0, 1, 0, 0…
## $ debut_rank__4_8 <dbl> 0, 0, 0, 0, 0, 0, 0, 1…
## $ debut_rank__8_12 <dbl> 0, 0, 0, 0, 1, 0, 1, 0…
## $ debut_rank__12_Inf <dbl> 0, 1, 0, 0, 0, 0, 0, 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_11 <dbl> 0, 0, 1, 0, 0, 1, 0, 1…
## $ best_rank__11_Inf <dbl> 0, 0, 0, 1, 1, 0, 0, 0…
## $ `decade__-Inf_1960` <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ decade__1960_2000 <dbl> 1, 1, 1, 0, 1, 0, 1, 1…
## $ decade__2000_2010 <dbl> 0, 0, 0, 1, 0, 1, 0, 0…
## $ decade__2010_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0…# step 2: Correlate
data_corr_tbl <- data_binarized_tbl %>%
correlate(total_weeks__2.30258509299405_Inf)
data_corr_tbl## # A tibble: 24 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 total_weeks 2.30258509299405_Inf 1
## 2 total_weeks -Inf_0.693147180559945 -0.396
## 3 best_rank -Inf_3 0.341
## 4 total_weeks 1.38629436111989_2.30258509299405 -0.322
## 5 best_rank 11_Inf -0.283
## 6 decade 2000_2010 -0.261
## 7 total_weeks 0.693147180559945_1.38629436111989 -0.256
## 8 year 1968_2000 0.243
## 9 year 2011_Inf -0.235
## 10 year 2000_2011 -0.231
## # ℹ 14 more rows# Step 3: Plot
data_corr_tbl %>%
plot_correlation_funnel()
Build Models
Split Data
#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 Split training dataset for cross-varification
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 [5004/557]> Fold01
## 2 <split [5005/556]> Fold02
## 3 <split [5005/556]> Fold03
## 4 <split [5005/556]> Fold04
## 5 <split [5005/556]> Fold05
## 6 <split [5005/556]> Fold06
## 7 <split [5005/556]> Fold07
## 8 <split [5005/556]> Fold08
## 9 <split [5005/556]> Fold09
## 10 <split [5005/556]> 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) %>%
step_date(first_week, keep_original_cols = FALSE) %>%
step_dummy(all_nominal_predictors(), one_hot = TRUE) %>%
step_YeoJohnson(year)
xgboost_recipe %>% prep() %>% juice() %>% glimpse() ## Rows: 5,561
## Columns: 128
## $ id <dbl> 770, 867, 1901, 1558, 7356, 3425, 1839, 5052, 36…
## $ year <dbl> 1999, 2007, 1951, 1936, 1958, 1996, 2009, 2010, …
## $ debut_rank <dbl> 1, 8, 14, 4, 10, 11, 10, 3, 7, 1, 16, 8, 14, 16,…
## $ best_rank <dbl> 11, 14, 13, 1, 4, 10, 7, 8, 3, 8, 15, 6, 4, 10, …
## $ decade <dbl> 1990, 2000, 1950, 1930, 1950, 1990, 2000, 2010, …
## $ total_weeks <dbl> 1.7917595, 0.0000000, 0.0000000, 3.8286414, 2.83…
## $ tfidf_title_a <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_after <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_all <dbl> 0.000000, 0.000000, 0.000000, 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> 0.000000, 0.000000, 0.000000, 0.000000, 3.529332…
## $ tfidf_title_are <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_as <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_at <dbl> 1.647274, 0.000000, 0.000000, 0.000000, 0.000000…
## $ 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> 1.87713, 0.00000, 0.00000, 0.00000, 0.00000, 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, 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_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_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_good <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_heart <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ 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_hour <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_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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_of <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ 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_place <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_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> 0.4345384, 0.0000000, 0.0000000, 1.3036151, 0.00…
## $ 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, 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, 0.000000…
## $ 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, …
## $ first_week_year <int> 1999, 2007, 1951, 1936, 1958, 1996, 2009, 2010, …
## $ 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, …
## $ first_week_dow_Sun <dbl> 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ first_week_dow_Mon <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_dow_Tue <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_dow_Wed <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_dow_Thu <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_dow_Fri <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_dow_Sat <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Jan <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Feb <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ first_week_month_Mar <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Apr <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ first_week_month_May <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, …
## $ first_week_month_Jun <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, …
## $ first_week_month_Jul <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Aug <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Sep <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Oct <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Nov <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Dec <dbl> 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, …#Specify Model
xgboost_spec <-
boost_tree(trees = 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(344)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5)