Apply 2
Johnny McKinnon
2024-09-19
Goal: Predict the average movie rating
Import data
horror_movies <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-11-01/horror_movies.csv')## Rows: 32540 Columns: 20
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (10): original_title, title, original_language, overview, tagline, post...
## dbl (8): id, popularity, vote_count, vote_average, budget, revenue, runtim...
## lgl (1): adult
## date (1): release_date
##
## 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(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 %>%
# Treat missing values
select(-tagline, -backdrop_path, -collection_name, -collection, -release_date) %>%
na.omit() %>%
# Log transform variables with pos-skewed distribution
mutate(popularity = log(popularity))Explore data
Identify good predictors
Popularity
data %>%
ggplot(aes(vote_average, popularity)) +
scale_x_log10() +
geom_point()## Warning in scale_x_log10(): log-10 transformation introduced infinite values.
Revenue
data %>%
ggplot(aes(vote_average, revenue)) +
geom_point()
Runtime
data %>%
ggplot(aes(vote_average, runtime)) +
geom_point()
Title
data %>%
# Tokenize title
unnest_tokens(output = word, input = title) %>%
# Calculate avg rating per word
group_by(word) %>%
summarise(vote_average = mean(vote_average),
n = n()) %>%
ungroup() %>%
filter(n > 5, !str_detect(word, "\\d")) %>%
slice_max(order_by = vote_average, n = 25) %>%
# Plot
ggplot(aes(vote_average, fct_reorder(word, vote_average))) +
geom_point() +
labs(y = "Words in Title")
Build models
Split Data
data <- sample_n(data, 100)
# Split into train and test data-set
set.seed(1234)
data_split <- rsample::initial_split(data)
data_train <- training(data_split)
data_test <- testing(data_split)
# Further split training data-set for cross-validation
set.seed(4321)
data_cv <- rsample::vfold_cv(data_train)
data_cv## # 10-fold cross-validation
## # A tibble: 10 × 2
## splits id
## <list> <chr>
## 1 <split [67/8]> Fold01
## 2 <split [67/8]> Fold02
## 3 <split [67/8]> Fold03
## 4 <split [67/8]> Fold04
## 5 <split [67/8]> Fold05
## 6 <split [68/7]> Fold06
## 7 <split [68/7]> Fold07
## 8 <split [68/7]> Fold08
## 9 <split [68/7]> Fold09
## 10 <split [68/7]> 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(4796)
## xgboost_tune <-
## tune_grid(xgboost_workflow, resamples = stop("add your rsample object"), grid = stop("add number of candidate points"))xgboost_recipe <-
recipe(formula = vote_average ~ ., data = data_train) %>%
step_zv(all_predictors()) %>%
update_role(id, new_role = "id variable") %>%
step_tokenize(overview) %>%
step_tokenfilter(overview, max_tokens = 100) %>%
step_tfidf(overview) %>%
step_other(original_title, title, poster_path, original_language, genre_names) %>%
step_dummy(original_title, title, poster_path, original_language, genre_names, one_hot = TRUE) %>%
step_YeoJohnson(popularity, vote_count, budget, revenue, runtime)
xgboost_recipe %>% prep() %>% juice() %>% glimpse()## Rows: 75
## Columns: 120
## $ id <dbl> 256781, 580627, 388705, …
## $ popularity <dbl> -0.51076049, -0.67663608…
## $ vote_count <dbl> 0.9210510, 0.0000000, 0.…
## $ budget <dbl> 0.000000, 0.000000, 0.00…
## $ revenue <dbl> 0.000000, 0.000000, 0.00…
## $ runtime <dbl> 96.528151, 90.432636, 12…
## $ vote_average <dbl> 3.5, 0.0, 5.5, 0.0, 2.8,…
## $ tfidf_overview_a <dbl> 0.07732266, 0.09389180, …
## $ tfidf_overview_about <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_accident <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_after <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_all <dbl> 0.03440293, 0.00000000, …
## $ tfidf_overview_an <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_and <dbl> 0.05461537, 0.00000000, …
## $ tfidf_overview_are <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_as <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_at <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_be <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_been <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_being <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_boy <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_but <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_by <dbl> 0.04582778, 0.00000000, …
## $ tfidf_overview_college <dbl> 0.04791318, 0.00000000, …
## $ tfidf_overview_crew <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_dark <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_day <dbl> 0.09582637, 0.00000000, …
## $ tfidf_overview_death <dbl> 0.0438699, 0.0000000, 0.…
## $ tfidf_overview_during <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_each <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_evil <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_family <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_film <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_finds <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_for <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_forced <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_found <dbl> 0.04077336, 0.00000000, …
## $ tfidf_overview_four <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_friends <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_from <dbl> 0.00000000, 0.13375414, …
## $ tfidf_overview_get <dbl> 0.0438699, 0.0000000, 0.…
## $ tfidf_overview_ghost <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_go <dbl> 0.04386990, 0.00000000, …
## $ tfidf_overview_goes <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_government <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_grandfather <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_group <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_has <dbl> 0.02913237, 0.12381259, …
## $ tfidf_overview_he <dbl> 0.00000000, 0.10864192, …
## $ tfidf_overview_her <dbl> 0.12232009, 0.00000000, …
## $ tfidf_overview_him <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_himself <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_his <dbl> 0.00000000, 0.09498911, …
## $ tfidf_overview_home <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_horror <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_house <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_however <dbl> 0.0000000, 0.1864471, 0.…
## $ tfidf_overview_in <dbl> 0.04389414, 0.00000000, …
## $ tfidf_overview_into <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_is <dbl> 0.03368036, 0.00000000, …
## $ tfidf_overview_island <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_it <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_john <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_known <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_life <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_looking <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_lost <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_love <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_making <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_man <dbl> 0.0000000, 0.1626681, 0.…
## $ tfidf_overview_may <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_mother <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_new <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_night <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_not <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_now <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_overview_of <dbl> 0.02767598, 0.00000000, …
## $ tfidf_overview_off <dbl> 0.04077336, 0.00000000, …
## $ tfidf_overview_old <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_on <dbl> 0.02719969, 0.00000000, …
## $ tfidf_overview_one <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_out <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_over <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_own <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_school <dbl> 0.09582637, 0.00000000, …
## $ tfidf_overview_she <dbl> 0.05624669, 0.11952422, …
## $ tfidf_overview_story <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_strange <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_that <dbl> 0.04363731, 0.18545857, …
## $ tfidf_overview_the <dbl> 0.09124598, 0.04847443, …
## $ tfidf_overview_their <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_them <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_they <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_this <dbl> 0.03440293, 0.00000000, …
## $ tfidf_overview_those <dbl> 0.04077336, 0.00000000, …
## $ tfidf_overview_to <dbl> 0.06650414, 0.05652852, …
## $ tfidf_overview_two <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_was <dbl> 0.03827485, 0.00000000, …
## $ tfidf_overview_when <dbl> 0.03284694, 0.00000000, …
## $ tfidf_overview_which <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_while <dbl> 0.00000000, 0.00000000, …
## $ tfidf_overview_who <dbl> 0.02415041, 0.00000000, …
## $ tfidf_overview_will <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_with <dbl> 0.04702517, 0.00000000, …
## $ tfidf_overview_woman <dbl> 0.16423472, 0.27919903, …
## $ tfidf_overview_years <dbl> 0.0000000, 0.0000000, 0.…
## $ tfidf_overview_young <dbl> 0.0000000, 0.1538006, 0.…
## $ original_title_Alien.Space.Avenger <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_title_other <dbl> 1, 1, 1, 1, 1, 1, 1, 1, …
## $ title_Alien.Space.Avenger <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ title_other <dbl> 1, 1, 1, 1, 1, 1, 1, 1, …
## $ poster_path_X.1chy8R4wkggtW6NTMDY3lu7aibf.jpg <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ poster_path_other <dbl> 1, 1, 1, 1, 1, 1, 1, 1, …
## $ original_language_en <dbl> 0, 0, 1, 1, 1, 1, 0, 1, …
## $ original_language_es <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ original_language_other <dbl> 1, 1, 0, 0, 0, 0, 1, 0, …
## $ genre_names_Comedy..Horror <dbl> 0, 0, 0, 0, 0, 0, 0, 0, …
## $ genre_names_Horror <dbl> 1, 1, 0, 0, 0, 0, 1, 1, …
## $ genre_names_Horror..Thriller <dbl> 0, 0, 1, 0, 0, 0, 0, 0, …
## $ genre_names_other <dbl> 0, 0, 0, 1, 1, 1, 0, 0, …xgboost_spec <-
boost_tree(trees = tune(), min_n = tune(), mtry = tune(), learn_rate = tune()) %>%
set_mode("regression") %>%
set_engine("xgboost")
xgboost_workflow <-
workflow() %>%
add_recipe(xgboost_recipe) %>%
add_model(xgboost_spec)
set.seed(4796)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5)## i Creating pre-processing data to finalize unknown parameter: mtry## Warning: package 'xgboost' was built under R version 4.3.3## → A | warning: A correlation computation is required, but `estimate` is constant and has 0
## standard deviation, resulting in a divide by 0 error. `NA` will be returned.##
There were issues with some computations A: x1
There were issues with some computations A: x2
There were issues with some computations A: x3
There were issues with some computations A: x4
There were issues with some computations A: x5
There were issues with some computations A: x6
There were issues with some computations A: x7
There were issues with some computations A: x8
There were issues with some computations A: x9
There were issues with some computations A: x10
There were issues with some computations A: x10