Apply Data 2 Horror Movies
Thomas Hall
2025-02-25
Goal: Build a regression model to predict the average movie rating (vote_average). Use the horror_movies dataset. Click here for the data
Import Data
horror_movies <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2022/2022-11-01/horror_movies.csv')
skimr::skim(horror_movies)| Name | horror_movies |
| Number of rows | 32540 |
| Number of columns | 20 |
| _______________________ | |
| Column type frequency: | |
| character | 10 |
| Date | 1 |
| logical | 1 |
| numeric | 8 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| original_title | 0 | 1.00 | 1 | 191 | 0 | 30296 | 0 |
| title | 0 | 1.00 | 1 | 191 | 0 | 29563 | 0 |
| original_language | 0 | 1.00 | 2 | 2 | 0 | 97 | 0 |
| overview | 1286 | 0.96 | 1 | 1000 | 0 | 31020 | 0 |
| tagline | 19835 | 0.39 | 1 | 237 | 0 | 12513 | 0 |
| poster_path | 4474 | 0.86 | 30 | 32 | 0 | 28048 | 0 |
| status | 0 | 1.00 | 7 | 15 | 0 | 4 | 0 |
| backdrop_path | 18995 | 0.42 | 29 | 32 | 0 | 13536 | 0 |
| genre_names | 0 | 1.00 | 6 | 144 | 0 | 772 | 0 |
| collection_name | 30234 | 0.07 | 4 | 56 | 0 | 815 | 0 |
Variable type: Date
| skim_variable | n_missing | complete_rate | min | max | median | n_unique |
|---|---|---|---|---|---|---|
| release_date | 0 | 1 | 1950-01-01 | 2022-12-31 | 2012-12-09 | 10999 |
Variable type: logical
| skim_variable | n_missing | complete_rate | mean | count |
|---|---|---|---|---|
| adult | 0 | 1 | 0 | FAL: 32540 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| id | 0 | 1.00 | 445910.83 | 305744.67 | 17 | 146494.8 | 426521.00 | 707534.00 | 1033095.00 | ▇▆▆▅▅ |
| popularity | 0 | 1.00 | 4.01 | 37.51 | 0 | 0.6 | 0.84 | 2.24 | 5088.58 | ▇▁▁▁▁ |
| vote_count | 0 | 1.00 | 62.69 | 420.89 | 0 | 0.0 | 2.00 | 11.00 | 16900.00 | ▇▁▁▁▁ |
| vote_average | 0 | 1.00 | 3.34 | 2.88 | 0 | 0.0 | 4.00 | 5.70 | 10.00 | ▇▂▆▃▁ |
| budget | 0 | 1.00 | 543126.59 | 4542667.81 | 0 | 0.0 | 0.00 | 0.00 | 200000000.00 | ▇▁▁▁▁ |
| revenue | 0 | 1.00 | 1349746.73 | 14430479.15 | 0 | 0.0 | 0.00 | 0.00 | 701842551.00 | ▇▁▁▁▁ |
| runtime | 0 | 1.00 | 62.14 | 41.00 | 0 | 14.0 | 80.00 | 91.00 | 683.00 | ▇▁▁▁▁ |
| collection | 30234 | 0.07 | 481534.88 | 324498.16 | 656 | 155421.0 | 471259.00 | 759067.25 | 1033032.00 | ▇▅▅▅▅ |
data <- horror_movies %>%
# Filter out Non Released Movies
filter(status == "Released") %>%
# Treat missing values
select(-overview,-tagline,-poster_path,-backdrop_path,-collection_name, -status, -original_title, -adult) %>%
na.omit() %>%
# Seperating Row Names
separate_rows(genre_names, sep = ", ") %>%
#log transform variables for voting average
mutate(vote_average = log(vote_average + 1)) %>%
mutate(across(where(is.character),as.factor)) %>%
mutate(title = as.character(title)) %>%
mutate(across(where(is.logical),as.factor))Explore Data
Identify good predictors.
genre_names
data %>%
ggplot(aes(vote_average, genre_names)) +
geom_boxplot()
popularity
data %>%
ggplot(aes(vote_average, popularity)) +
geom_point()
EDA shortcut
# Step 1: Prepare data
data_binarized_tbl <- data %>%
select(-id, -release_date) %>%
binarize()
data_binarized_tbl %>% glimpse()## Rows: 4,949
## Columns: 47
## $ `title__Scooby-Doo!_Frankencreepy` <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `title__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ original_language__cn <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ original_language__de <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ original_language__en <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ original_language__es <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ original_language__id <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ original_language__ja <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ original_language__th <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `original_language__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `popularity__-Inf_1.55` <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ popularity__1.55_4.882 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ popularity__4.882_13.017 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ popularity__13.017_Inf <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ `vote_count__-Inf_5` <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ vote_count__5_36 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ vote_count__36_205 <dbl> 0, 0, 1, 1, 1, 0, 0, 0…
## $ vote_count__205_Inf <dbl> 1, 1, 0, 0, 0, 1, 1, 1…
## $ `vote_average__-Inf_1.66770682055808` <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ vote_average__1.66770682055808_1.85629799036563 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ vote_average__1.85629799036563_1.97408102602201 <dbl> 0, 0, 1, 1, 1, 0, 0, 0…
## $ vote_average__1.97408102602201_Inf <dbl> 1, 1, 0, 0, 0, 1, 1, 1…
## $ `budget__-Inf_7e+05` <dbl> 1, 1, 0, 0, 0, 0, 0, 0…
## $ `budget__7e+05_Inf` <dbl> 0, 0, 1, 1, 1, 1, 1, 1…
## $ revenue__0 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `revenue__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1…
## $ `runtime__-Inf_81` <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ runtime__81_90 <dbl> 0, 0, 1, 1, 1, 0, 0, 0…
## $ runtime__90_99 <dbl> 1, 1, 0, 0, 0, 0, 0, 0…
## $ runtime__99_Inf <dbl> 0, 0, 0, 0, 0, 1, 1, 1…
## $ genre_names__Action <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ genre_names__Adventure <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ genre_names__Animation <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ genre_names__Comedy <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ genre_names__Crime <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ genre_names__Drama <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ genre_names__Fantasy <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ genre_names__Horror <dbl> 1, 0, 1, 0, 0, 1, 0, 0…
## $ genre_names__Mystery <dbl> 0, 0, 0, 1, 0, 0, 1, 0…
## $ genre_names__Science_Fiction <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ genre_names__Thriller <dbl> 0, 1, 0, 0, 1, 0, 0, 1…
## $ genre_names__TV_Movie <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `genre_names__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ `collection__-Inf_133352` <dbl> 0, 0, 1, 1, 1, 0, 0, 0…
## $ collection__133352_459212 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ collection__459212_744915 <dbl> 0, 0, 0, 0, 0, 0, 0, 0…
## $ collection__744915_Inf <dbl> 1, 1, 0, 0, 0, 1, 1, 1…# Step 2: Correlate
data_corr_tbl <- data_binarized_tbl %>%
correlate(vote_average__1.97408102602201_Inf)
data_corr_tbl## # A tibble: 47 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 vote_average 1.97408102602201_Inf 1
## 2 vote_average 1.66770682055808_1.85629799036563 -0.335
## 3 vote_average -Inf_1.66770682055808 -0.330
## 4 vote_average 1.85629799036563_1.97408102602201 -0.324
## 5 popularity 13.017_Inf 0.243
## 6 revenue 0 -0.233
## 7 revenue -OTHER 0.233
## 8 vote_count 205_Inf 0.214
## 9 runtime 99_Inf 0.196
## 10 vote_count 5_36 -0.123
## # ℹ 37 more rows# Step 3: Plot
data_corr_tbl %>%
plot_correlation_funnel()## Warning: ggrepel: 18 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps
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-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 [3339/372]> Fold01
## 2 <split [3340/371]> Fold02
## 3 <split [3340/371]> Fold03
## 4 <split [3340/371]> Fold04
## 5 <split [3340/371]> Fold05
## 6 <split [3340/371]> Fold06
## 7 <split [3340/371]> Fold07
## 8 <split [3340/371]> Fold08
## 9 <split [3340/371]> Fold09
## 10 <split [3340/371]> Fold10library(usemodels)
usemodels::use_xgboost(vote_average ~ ., data = data_train)## xgboost_recipe <-
## recipe(formula = vote_average ~ ., 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(10213)
## 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 = vote_average ~ ., data = data_train) %>%
recipes::update_role(id, new_role ="id variable") %>%
step_tokenize(title) %>%
step_tokenfilter(title, max_tokens = 100) %>%
step_tf(title) %>%
step_date(release_date, keep_original_cols = FALSE) %>%
step_dummy(all_nominal_predictors())
xgboost_recipe %>% prep() %>% juice() %>% glimpse()## Rows: 3,711
## Columns: 170
## $ id <dbl> 29426, 520901, 68557, 246403, 147619, 6492…
## $ popularity <dbl> 17.627, 28.724, 4.015, 19.296, 0.600, 3.19…
## $ vote_count <dbl> 376, 325, 17, 1078, 2, 21, 130, 20, 26, 12…
## $ budget <dbl> 4.0e+06, 0.0e+00, 0.0e+00, 3.0e+06, 0.0e+0…
## $ revenue <dbl> 0, 0, 0, 1882074, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ runtime <dbl> 90, 97, 106, 102, 97, 72, 88, 78, 87, 86, …
## $ collection <dbl> 944437, 634390, 856206, 553902, 690968, 74…
## $ vote_average <dbl> 1.774952, 1.774952, 2.014903, 1.871802, 1.…
## $ tf_title_1 <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_2 <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_3 <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ tf_title_4 <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_5 <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_6 <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_a <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_alien <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_all <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_and <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_angel <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_atta <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_attack <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_beast <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_bizarre <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_black <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_blood <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_bong <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_boys <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_children <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_curse <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_dark <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_darkness <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_day <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_dead <int> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_death <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_demon <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_devil <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `tf_title_don't` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_doo <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_evil <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_fear <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_final <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ tf_title_from <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_gamera <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_ghost <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_girl <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_halloween <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_haunted <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_hell <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_high <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ tf_title_honto <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_horror <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_house <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_hunter <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `tf_title_i'm` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_ii <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, …
## $ tf_title_iii <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_in <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_iv <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_kamen <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_killer <int> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ tf_title_lake <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_last <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_legend <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_lost <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_man <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_massacre <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_master <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_me <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_movie <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_my <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_new <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_ni <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_night <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_nightmare <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_no <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_noroi <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_of <int> 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ tf_title_on <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_paranormal <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_part <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_pop <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_psycho <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_rattle <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_resident <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_return <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_revenge <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_rider <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_roll <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_scared <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_scooby <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_shake <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_shark <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_special <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_spirit <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_story <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_tales <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_terror <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_the <int> 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, …
## $ tf_title_to <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_tokyo <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_tremors <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_troublesome <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_vampire <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_video <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_volume <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_vs <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_world <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tf_title_zombie <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_year <int> 2010, 2019, 2009, 2014, 1976, 1999, 2011, …
## $ original_language_da <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_de <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_el <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_en <dbl> 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, …
## $ original_language_es <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_fi <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_fr <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_hi <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_id <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_it <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_ja <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ original_language_ko <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_ml <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_ms <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_no <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_pl <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_pt <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_ru <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_si <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_ta <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_te <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_th <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_tl <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_tr <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_xx <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_zh <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Adventure <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Animation <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Comedy <dbl> 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Crime <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ genre_names_Documentary <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Drama <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Family <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Fantasy <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_History <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Horror <dbl> 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0, …
## $ genre_names_Music <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Mystery <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Romance <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Science.Fiction <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Thriller <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, …
## $ genre_names_TV.Movie <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_War <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Western <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_dow_Mon <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_dow_Tue <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ release_date_dow_Wed <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_dow_Thu <dbl> 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, …
## $ release_date_dow_Fri <dbl> 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ release_date_dow_Sat <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1, …
## $ release_date_month_Feb <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_month_Mar <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, …
## $ release_date_month_Apr <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_month_May <dbl> 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, …
## $ release_date_month_Jun <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_month_Jul <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_month_Aug <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_month_Sep <dbl> 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_month_Oct <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, …
## $ release_date_month_Nov <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ release_date_month_Dec <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, …# Specify model
xgboost_spec <-
boost_tree(trees = tune(), min_n = tune(), mtry = tune(), learn_rate = tune()) %>%
set_mode("regression") %>%
set_engine("xgboost")
# Combinte 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)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 42 1000 40 0.316 rmse standard 0.124 10 0.00561 Preproces…
## 2 168 2000 21 0.0178 rmse standard 0.135 10 0.00355 Preproces…
## 3 1 1500 11 0.00422 rmse standard 0.454 10 0.0106 Preproces…
## 4 126 500 30 0.001 rmse standard 0.811 10 0.00392 Preproces…
## 5 84 1 2 0.0750 rmse standard 1.22 10 0.00483 Preproces…# Update 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.
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 0.108 Preprocessor1_Model1
## 2 rsq standard 0.968 Preprocessor1_Model1tune::collect_predictions(data_fit) %>%
ggplot(aes(vote_average, .pred)) +
geom_point(alpha = 0.3, fill = "midnightblue") +
geom_abline(lty = 2, color = "gray50") +
coord_fixed()
Make Predictions
I adjusted the step_tf so that it would run a little smoother, but aside from that not many changes were made.