library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(tidytext)
library(correlationfunnel)
## ══ correlationfunnel Tip #1 ════════════════════════════════════════════════════
## Make sure your data is not overly imbalanced prior to using `correlate()`.
## If less than 5% imbalance, consider sampling. :)
library(tidymodels) # for model building
## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom        1.0.5     ✔ rsample      1.2.1
## ✔ dials        1.2.1     ✔ tune         1.2.1
## ✔ infer        1.0.7     ✔ workflows    1.1.4
## ✔ modeldata    1.4.0     ✔ workflowsets 1.1.0
## ✔ parsnip      1.2.1     ✔ yardstick    1.3.1
## ✔ recipes      1.1.0
## Warning: package 'modeldata' was built under R version 4.3.3
## Warning: package 'recipes' was built under R version 4.3.3
## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter()   masks stats::filter()
## ✖ recipes::fixed()  masks stringr::fixed()
## ✖ dplyr::lag()      masks stats::lag()
## ✖ yardstick::spec() masks readr::spec()
## ✖ recipes::step()   masks stats::step()
## • Learn how to get started at https://www.tidymodels.org/start/
library(textrecipes) # for preprocessing string variables
library(xgboost)
## Warning: package 'xgboost' was built under R version 4.3.3
## 
## Attaching package: 'xgboost'
## 
## The following object is masked from 'package:dplyr':
## 
##     slice
library(lubridate)

nyt_titles <- readr::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 %>%
    mutate(total_weeks = log(total_weeks))

skimr::skim(data)
Data summary
Name data
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 1857.50 3715.00 5572.5 7430.00 ▇▇▇▇▇
year 0 1 1989.61 26.23 1931 1968.00 2000.00 2011.0 2020.00 ▂▂▂▃▇
total_weeks 0 1 1.48 1.11 0 0.69 1.39 2.3 5.18 ▇▇▆▂▁
debut_rank 0 1 7.90 4.57 1 4.00 8.00 12.0 17.00 ▇▆▅▅▅
best_rank 0 1 6.91 4.57 1 3.00 6.00 10.0 17.00 ▇▅▃▃▂ 
data_binarized <- data %>%
    select(-title, -id, -author) %>%
    mutate(year = year(first_week), 
           month = month(first_week, label = TRUE),
           weekday = wday(first_week, label = TRUE)) %>%
               select(-first_week) %>% 
               binarize()

data_binarized %>% glimpse()
## Rows: 7,431
## Columns: 30
## $ `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_10                                 <dbl> 0, 0, 1, 0, 0, 1, 0, 1…
## $ best_rank__10_Inf                               <dbl> 0, 0, 0, 1, 1, 0, 0, 0…
## $ month__01                                       <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ month__02                                       <dbl> 0, 0, 0, 0, 1, 0, 0, 0…
## $ month__03                                       <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ month__04                                       <dbl> 0, 1, 0, 0, 0, 0, 1, 0…
## $ month__05                                       <dbl> 1, 0, 1, 1, 0, 0, 0, 1…
## $ month__06                                       <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ month__07                                       <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ month__08                                       <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ month__09                                       <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ month__10                                       <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ month__11                                       <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ month__12                                       <dbl> 0, 0, 0, 0, 0, 1, 0, 0…
## $ weekday__Sun                                    <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ weekday__Mon                                    <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
data_correlate <- data_binarized %>%
    correlate(total_weeks__2.30258509299405_Inf)
data_correlate %>%
    plot_correlation_funnel()
## Warning: ggrepel: 12 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

# data <- sample_n(data, 100)

set.seed(223)
data_split <- rsample::initial_split(data)
data_train <- training(data_split)
data_test <- testing(data_split)

set.seed(332)
data_cv <- rsample::vfold_cv(data_train)
data_cv
## #  10-fold cross-validation 
## # A tibble: 10 × 2
##    splits             id    
##    <list>             <chr> 
##  1 <split [5015/558]> Fold01
##  2 <split [5015/558]> Fold02
##  3 <split [5015/558]> Fold03
##  4 <split [5016/557]> Fold04
##  5 <split [5016/557]> Fold05
##  6 <split [5016/557]> Fold06
##  7 <split [5016/557]> Fold07
##  8 <split [5016/557]> Fold08
##  9 <split [5016/557]> Fold09
## 10 <split [5016/557]> Fold10
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(69523)
## xgboost_tune <-
##   tune_grid(xgboost_workflow, resamples = stop("add your rsample object"), grid = stop("add number of candidate points"))
# Preprocessing
recipe <- 
  recipe(formula = total_weeks ~ ., data = data_train) %>% 
  recipes::update_role(id, new_role = "id variable") %>%
    step_tokenize(title) %>%
    step_tokenfilter(title, max_tokens = 125) %>%
    step_tfidf(title) %>%
    step_date(first_week, keep_original_cols = FALSE) %>%
    step_other(author) %>%
    step_unknown(author) %>%
    step_dummy(all_nominal_predictors(), one_hot = TRUE) %>%
    step_log(year, best_rank, debut_rank) 

recipe %>% prep() %>% juice() %>% glimpse()
## Rows: 5,573
## Columns: 153
## $ id                    <dbl> 5383, 5505, 254, 1190, 6042, 2043, 2263, 3334, 4…
## $ year                  <dbl> 7.597898, 7.602401, 7.578657, 7.608374, 7.599902…
## $ debut_rank            <dbl> 1.7917595, 1.3862944, 2.1972246, 1.6094379, 0.69…
## $ best_rank             <dbl> 2.0794415, 2.5649494, 0.6931472, 1.7917595, 2.56…
## $ total_weeks           <dbl> 1.3862944, 0.0000000, 3.0445224, 0.6931472, 1.09…
## $ tfidf_title_a         <dbl> 0.000000, 0.000000, 1.537289, 0.000000, 0.000000…
## $ 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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_angel     <dbl> 0, 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, 0, …
## $ tfidf_title_at        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_back      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_before    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_big       <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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ 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, 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> 2.792464, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_cold      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_country   <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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_dead      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_death     <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_down      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_dream     <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_eye       <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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ 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_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_great     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_green     <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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_her       <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_his       <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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_island    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_king      <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_kiss      <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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ 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_more      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_mountain  <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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_new       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ 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> 0.0000000, 0.0000000, 1.0870579, 0.0000000, 0.00…
## $ tfidf_title_old       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_on        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_one       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_paradise  <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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ tfidf_title_shadow    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_shadows   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_silent    <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_song      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_spy       <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_story     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_stranger  <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> 0.6496197, 1.2992395, 0.0000000, 0.0000000, 1.29…
## $ 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_through   <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> 0.000000, 0.000000, 0.000000, 0.000000, 0.000000…
## $ 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_wind      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_winter    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_title_with      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ 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> 1994, 2003, 1956, 2015, 1998, 1935, 2002, 2018, …
## $ author_Danielle.Steel <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, …
## $ author_other          <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, …
## $ author_unknown        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_dow_Sun    <dbl> 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ first_week_dow_Mon    <dbl> 0, 0, 0, 0, 0, 1, 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, 1, 0, 0, …
## $ first_week_month_Feb  <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 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, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, …
## $ first_week_month_May  <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, …
## $ first_week_month_Jun  <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ first_week_month_Jul  <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ first_week_month_Aug  <dbl> 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Sep  <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, …
## $ first_week_month_Oct  <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Nov  <dbl> 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ first_week_month_Dec  <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, …
# Specifying model with xgboost
xgboost_spec <- 
  boost_tree(trees = tune(), mtry = tune(), learn_rate = tune(), stop_iter = tune()) %>% 
  set_mode("regression") %>% 
  set_engine("xgboost") 

xgboost_workflow <- 
  workflow() %>% 
  add_recipe(recipe) %>% 
  add_model(xgboost_spec) 

set.seed(70139)
xgboost_tune <-
  tune_grid(xgboost_workflow,
            resamples = data_cv, 
            grid = 5)
## i Creating pre-processing data to finalize unknown parameter: mtry
tune::show_best(xgboost_tune, metric = "rmse")
## # A tibble: 5 × 10
##    mtry trees learn_rate stop_iter .metric .estimator  mean     n std_err
##   <int> <int>      <dbl>     <int> <chr>   <chr>      <dbl> <int>   <dbl>
## 1   100   436    0.0350         15 rmse    standard   0.533    10 0.00734
## 2   136  1425    0.0118          8 rmse    standard   0.533    10 0.00726
## 3    50  1866    0.178          18 rmse    standard   0.589    10 0.00895
## 4    11  1022    0.00183         5 rmse    standard   0.814    10 0.00614
## 5    85    87    0.00325        11 rmse    standard   1.18     10 0.00973
## # ℹ 1 more variable: .config <chr>
xgboost_fw <- tune::finalize_workflow(xgboost_workflow,
                                      tune::select_best(xgboost_tune, metric = "rmse"))
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       0.562 Preprocessor1_Model1
## 2 rsq     standard       0.740 Preprocessor1_Model1
tune::collect_predictions(data_fit) %>%
    ggplot(aes(total_weeks, .pred)) +
    geom_point(alpha = 0.3, fill = "midnightblue") +
    geom_abline(lty = 2, color = "gray50") +
    coord_fixed()

# specify model with svm

svm_spec <- 
    svm_linear() %>%
    set_mode("regression")

svm_spec
## Linear Support Vector Machine Model Specification (regression)
## 
## Computational engine: LiblineaR
svm_wf <- workflow(recipe, svm_spec)

contrl_preds <- control_resamples(save_pred = TRUE)

svm_rs <- fit_resamples(
    svm_wf,
    resamples = data_cv,
    control = contrl_preds)
## Warning: package 'LiblineaR' was built under R version 4.3.3
tune::collect_metrics(svm_rs)
## # A tibble: 2 × 6
##   .metric .estimator  mean     n std_err .config             
##   <chr>   <chr>      <dbl> <int>   <dbl> <chr>               
## 1 rmse    standard   1.11     10 0.00565 Preprocessor1_Model1
## 2 rsq     standard   0.103    10 0.00838 Preprocessor1_Model1
bind_rows(collect_predictions(svm_rs)) %>%
    mutate(mod = "SVM") %>%
    ggplot(aes(total_weeks, .pred)) +
    geom_point(alpha = 0.3, fill = "midnightblue") +
    geom_abline(lty = 2, color = "gray50")

final_fitted <- last_fit(svm_wf, data_split)
tune::collect_metrics(final_fitted)
## # A tibble: 2 × 4
##   .metric .estimator .estimate .config             
##   <chr>   <chr>          <dbl> <chr>               
## 1 rmse    standard      1.11   Preprocessor1_Model1
## 2 rsq     standard      0.0779 Preprocessor1_Model1