What am I doing wrong. tune_grid cubist failed - r

Question

Tried to follow the instructions to generate the engine, workflow, then the recipe.
The part which i can't seem to get right is to tune the cubist model. appreciate your guidance.
These untuned models work;
#untuned rf
rf_model <-
rand_forest(trees = 1000
# ,mtry = 30
# ,min_n = 3
) %>%
set_engine("ranger",
num.threads = parallel::detectCores(),
importance = "permutation") %>%
set_mode("regression")
rf_wflow <-
workflow() %>%
add_recipe(df_recipe) %>%
add_model(rf_model)
system.time(rf_fit <- rf_wflow %>% fit(data = train))
# build untuned cubist model
cubist_mod <-
cubist_rules(
committees = 100,
neighbors = 9
# max_rules = integer(1)
) %>%
set_engine("Cubist") %>%
set_mode("regression")
cubist_wflow <-
workflow() %>%
add_recipe(cube_recipe) %>%
add_model(cubist_mod)
system.time(final_cb_mod <- cubist_wflow %>% fit(data = train))
summary(final_cb_mod$fit)
And the tuned version of the rf works too
#tune ranger
tune_spec <- rand_forest(
mtry = tune(),
trees = 1000,
min_n = tune()) %>%
set_mode("regression") %>%
set_engine("ranger")
tune_wf <-
workflow() %>%
add_model(tune_spec) %>%
add_recipe(df_recipe)
set.seed(234)
trees_folds <- vfold_cv(train)
rf_grid <- grid_regular(
mtry(range = c(10, 30)),
min_n(range = c(2, 8)),
levels = 5
)
set.seed(345)
system.time(
tune_res <- tune_grid(
tune_wf,
resamples = trees_folds,
grid = rf_grid,
control =
control_grid(#save_pred = T,
pkgs = c('tm', 'stringr'))
)
)
But when i tried to tune cubist, it generated this error. My cubist tune code is as below
Warning message:
All models failed. See the `.notes` column.
> car_tune_res$.notes[1]
[[1]]
# A tibble: 1 x 1
.notes
<chr>
1 preprocessor 1/1: Error in `contrasts<-`(`*tmp*`, value = contr.funs[1 + isOF[nn]]): contrasts can be applied only to factors with 2 or more levels
the tuning of cubist
#tune cubist
cb_grid <- expand.grid(committees = c(1, 10, 50, 100), neighbors = c(1, 5, 7, 9))
set.seed(8226)
cubist_mod <-
cubist_rules(neighbors = tune(), committees = tune()) %>%
set_engine("Cubist") %>%
set_mode("regression")
tuned_cubist_wf <- workflow() %>%
add_model(cubist_mod) %>%
add_recipe(cube_recipe)
system.time(
car_tune_res <-
cubist_mod %>%
tune_grid(
price ~ .,
resamples = trees_folds,
grid = cb_grid,
control =
control_grid(#save_pred = T,
pkgs = c('tm', 'stringr'))
)
)
added the recipe for reference
int_var <- train %>% select(where(is.integer)) %>% colnames()
int_var <- c(int_var,'geo_dist')
# excl_var <- c('url')
add_words <-
str_extract(train$url,'(?<=-).*(?=-)') %>%
str_extract_all(.,'[[:alpha:]]+') %>%
unlist() %>%
unique() %>%
str_to_lower()
df_recipe <-
recipe(price ~ .,data = train) %>%
step_geodist(lat = lat, lon = long, log = FALSE,
ref_lat = 144.946457, ref_lon = -37.840935, # Melb CBD
is_lat_lon = FALSE) %>%
step_rm('suburb') %>%
step_rm('prop_type') %>%
step_rm('url') %>%
step_zv(all_predictors()) %>%
# step_rm('desc') %>%
step_mutate(desc_raw = desc) %>%
step_textfeature(desc_raw) %>%
step_rename_at(
starts_with("textfeature_"),
fn = ~ gsub("textfeature_desc_raw_", "", .)) %>%
step_mutate(desc = str_to_lower(desc)) %>%
step_mutate(desc = removeNumbers(desc)) %>%
step_mutate(desc = removePunctuation(desc)) %>%
step_tokenize(desc) %>% #engine = "spacyr"
step_stopwords(desc, stopword_source = 'snowball') %>%
step_stopwords(desc, custom_stopword_source = add_words) %>%
step_tokenfilter(desc, max_tokens = 1e3) %>% #, max_tokens = tune()
step_tfidf(desc) %>% #lda_models = lda_model
step_novel(all_nominal(), -all_outcomes()) %>%
step_YeoJohnson(all_of(!!int_var), -all_outcomes()) %>%
step_dummy(all_nominal(), -all_outcomes(), one_hot = TRUE) %>%
step_normalize(all_of(!!int_var))
#dimension reduction due to the sparse matrix
cube_recipe <-
df_recipe %>%
step_pca(matches("school|tfidf_desc"),threshold = .8) %>% #|lda_desc
step_rm(starts_with("school")) %>%
step_rm(starts_with("lda_desc"))