ames_snippets.R

# Any changes to this code should trigger changes to the end-of-chapter summary
# sections (that include these in code chunks)

library(tidymodels)
data(ames)
ames <- mutate(ames, Sale_Price = log10(Sale_Price))

set.seed(502)
ames_split <- initial_split(ames, prop = 0.80, strata = Sale_Price)
ames_train <- training(ames_split)
ames_test  <-  testing(ames_split)

ames_rec <- 
  recipe(Sale_Price ~ Neighborhood + Gr_Liv_Area + Year_Built + Bldg_Type + 
           Latitude + Longitude, data = ames_train) %>%
  step_log(Gr_Liv_Area, base = 10) %>% 
  step_other(Neighborhood, threshold = 0.01) %>% 
  step_dummy(all_nominal_predictors()) %>% 
  step_interact( ~ Gr_Liv_Area:starts_with("Bldg_Type_") ) %>% 
  step_ns(Latitude, Longitude, deg_free = 20)

lm_model <- linear_reg() %>% set_engine("lm")

lm_wflow <- 
  workflow() %>% 
  add_model(lm_model) %>% 
  add_recipe(ames_rec)

# cached in RData/lm_fit.RData
# lm_fit <- fit(lm_wflow, ames_train)

rf_model <- 
  rand_forest(trees = 1000) %>% 
  set_engine("ranger") %>% 
  set_mode("regression")

rf_wflow <- 
  workflow() %>% 
  add_formula(
    Sale_Price ~ Neighborhood + Gr_Liv_Area + Year_Built + Bldg_Type + 
      Latitude + Longitude) %>% 
  add_model(rf_model) 

set.seed(1001)
ames_folds <- vfold_cv(ames_train, v = 10)

# cached in RData/resampling.RData from Ch 10
# rf_res <- rf_wflow %>% fit_resamples(resamples = ames_folds, control = keep_pred)