R workflowsets workflow_map 处理一系列工作流程

workflow_map(
  object,
  fn = "tune_grid",
  verbose = FALSE,
  seed = sample.int(10^4, 1),
  ...
)

workflow_set() , as_workflow_set() , extract_workflow_set_result()

library(workflowsets)
library(workflows)
library(modeldata)
library(recipes)
library(parsnip)
library(dplyr)
library(rsample)
library(tune)
library(yardstick)
#> For binary classification, the first factor level is assumed to be the event.
#> Use the argument `event_level = "second"` to alter this as needed.
library(dials)
#> Loading required package: scales
#> 
#> Attaching package: ‘scales’
#> The following object is masked from ‘package:purrr’:
#> 
#>     discard

# An example of processed results
chi_features_res
#> # A workflow set/tibble: 3 × 4
#>   wflow_id         info             option    result   
#>   <chr>            <list>           <list>    <list>   
#> 1 date_lm          <tibble [1 × 4]> <opts[2]> <rsmp[+]>
#> 2 plus_holidays_lm <tibble [1 × 4]> <opts[2]> <rsmp[+]>
#> 3 plus_pca_lm      <tibble [1 × 4]> <opts[3]> <tune[+]>

# Recreating them:

# ---------------------------------------------------------------------------
data(Chicago)
Chicago <- Chicago[1:1195,]

time_val_split <-
   sliding_period(
      Chicago,
      date,
      "month",
      lookback = 38,
      assess_stop = 1
   )

# ---------------------------------------------------------------------------

base_recipe <-
   recipe(ridership ~ ., data = Chicago) %>%
   # create date features
   step_date(date) %>%
   step_holiday(date) %>%
   # remove date from the list of predictors
   update_role(date, new_role = "id") %>%
   # create dummy variables from factor columns
   step_dummy(all_nominal()) %>%
   # remove any columns with a single unique value
   step_zv(all_predictors()) %>%
   step_normalize(all_predictors())

date_only <-
   recipe(ridership ~ ., data = Chicago) %>%
   # create date features
   step_date(date) %>%
   update_role(date, new_role = "id") %>%
   # create dummy variables from factor columns
   step_dummy(all_nominal()) %>%
   # remove any columns with a single unique value
   step_zv(all_predictors())

date_and_holidays <-
   recipe(ridership ~ ., data = Chicago) %>%
   # create date features
   step_date(date) %>%
   step_holiday(date) %>%
   # remove date from the list of predictors
   update_role(date, new_role = "id") %>%
   # create dummy variables from factor columns
   step_dummy(all_nominal()) %>%
   # remove any columns with a single unique value
   step_zv(all_predictors())

date_and_holidays_and_pca <-
   recipe(ridership ~ ., data = Chicago) %>%
   # create date features
   step_date(date) %>%
   step_holiday(date) %>%
   # remove date from the list of predictors
   update_role(date, new_role = "id") %>%
   # create dummy variables from factor columns
   step_dummy(all_nominal()) %>%
   # remove any columns with a single unique value
   step_zv(all_predictors()) %>%
   step_pca(!!stations, num_comp = tune())

# ---------------------------------------------------------------------------

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

# ---------------------------------------------------------------------------

pca_param <-
   parameters(num_comp()) %>%
   update(num_comp = num_comp(c(0, 20)))

# ---------------------------------------------------------------------------

chi_features_set <-
   workflow_set(
      preproc = list(date = date_only,
                     plus_holidays = date_and_holidays,
                     plus_pca = date_and_holidays_and_pca),
      models = list(lm = lm_spec),
      cross = TRUE
   )

# ---------------------------------------------------------------------------

chi_features_res_new <-
   chi_features_set %>%
   option_add(param_info = pca_param, id = "plus_pca_lm") %>%
   workflow_map(resamples = time_val_split, grid = 21, seed = 1, verbose = TRUE)
#> i	No tuning parameters. `fit_resamples()` will be attempted
#> i 1 of 3 resampling: date_lm
#> → A | warning: prediction from a rank-deficient fit may be misleading
#> There were issues with some computations   A: x1
#> There were issues with some computations   A: x1
#> 
#> ✔ 1 of 3 resampling: date_lm (547ms)
#> i	No tuning parameters. `fit_resamples()` will be attempted
#> i 2 of 3 resampling: plus_holidays_lm
#> → A | warning: prediction from a rank-deficient fit may be misleading
#> There were issues with some computations   A: x1
#> There were issues with some computations   A: x1
#> 
#> ✔ 2 of 3 resampling: plus_holidays_lm (601ms)
#> i 3 of 3 tuning:     plus_pca_lm
#> → A | warning: prediction from a rank-deficient fit may be misleading
#> There were issues with some computations   A: x4
#> There were issues with some computations   A: x10
#> There were issues with some computations   A: x16
#> There were issues with some computations   A: x18
#> 
#> ✔ 3 of 3 tuning:     plus_pca_lm (8.9s)

chi_features_res_new
#> # A workflow set/tibble: 3 × 4
#>   wflow_id         info             option    result   
#>   <chr>            <list>           <list>    <list>   
#> 1 date_lm          <tibble [1 × 4]> <opts[2]> <rsmp[+]>
#> 2 plus_holidays_lm <tibble [1 × 4]> <opts[2]> <rsmp[+]>
#> 3 plus_pca_lm      <tibble [1 × 4]> <opts[3]> <tune[+]>