.R

library(tidyverse)
library(tidymodels)

sf_trees <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-01-28/sf_trees.csv")

trees_df <- sf_trees %>%
    mutate(
        legal_status = case_when(
            legal_status == "DPW Maintained" ~ legal_status,
            TRUE ~ "Other"
        ),
        plot_size = parse_number(plot_size)
    ) %>%
    select(-address) %>%
    na.omit() %>%
    mutate_if(is.character, factor)

tree_rec <- recipe(legal_status ~ ., data = trees_train) %>%
    update_role(tree_id, new_role = "ID") %>%
    step_other(species, caretaker, threshold = 0.01) %>%
    step_other(site_info, threshold = 0.005) %>%
    step_dummy(all_nominal(), -all_outcomes()) %>%
    step_date(date, features = c("year")) %>%
    step_rm(date) %>%
    step_downsample(legal_status)

tree_prep <- prep(tree_rec)
juiced    <- bake(tree_prep, newdata = NULL)

tune_spec <- rand_forest(
    mtry = tune(),
    trees = 1000,
    min_n = tune()
) %>%
    set_mode("classification") %>%
    set_engine("ranger")

tune_wf <- workflow() %>%
    add_recipe(tree_rec) %>%
    add_model(tune_spec)

set.seed(234)
trees_folds <- vfold_cv(trees_train)

set.seed(345)
tune_res <- tune_grid(
    tune_wf,
    resamples = trees_folds,
    grid = 20
)
tune_res