Tidymodels : R의 의사 결정 트리 학습-오류 : 변수 또는 용어가 선택되지 않았습니다.

Question

개요 :

저는 'FID'라는 데이터 프레임을 가지고 있으며이 튜토리얼 (아래 참조)을 따라 세 가지 모델을 생성하려고합니다. (1) Bagged tree; (2) 랜덤 포레스트; 및 (3) 부스트 트리.

지도 시간:

https://bcullen.rbind.io/post/2020-06-02-tidymodels-decision-tree-learning-in-r/

발행물

"fit_bag" , fit_rf , "fit_boost" 모델을 실행하려고 할 때 아래 오류 메시지가 표시됩니다. 문제는 전처리 단계에있을 수 있다고 생각합니다.

누구든지이 문제에 대해 조언 할 수 있습니까?

미리 감사드립니다.

오류-선택된 변수가 없습니다.

i Fold01: recipe
x Fold01: recipe: Error: No variables or terms were selected.
i Fold02: recipe
x Fold02: recipe: Error: No variables or terms were selected.
i Fold03: recipe
x Fold03: recipe: Error: No variables or terms were selected.
i Fold04: recipe
x Fold04: recipe: Error: No variables or terms were selected.
i Fold05: recipe
x Fold05: recipe: Error: No variables or terms were selected.
i Fold06: recipe
x Fold06: recipe: Error: No variables or terms were selected.
i Fold07: recipe
x Fold07: recipe: Error: No variables or terms were selected.
i Fold08: recipe
x Fold08: recipe: Error: No variables or terms were selected.
i Fold09: recipe
x Fold09: recipe: Error: No variables or terms were selected.
i Fold10: recipe
x Fold10: recipe: Error: No variables or terms were selected.
Warning message:
All models failed in [fit_resamples()]. See the `.notes` column. 

R 코드

    ##Open library packages
    library(tidymodels) 
    library(tidyverse) # manipulating data
    library(skimr) # data visualization
    library(baguette) # bagged trees
    library(future) # parallel processing & decrease computation time
    library(xgboost) # boosted trees
    
    # split the data
    split <- initial_split(Tidmodel_df)
    
    # extract the training data
    train <- training(split)
    
    # resample the data with 10-fold cross-validation (10-fold by default)
    cv <- vfold_cv(train)
    
##Preprocessing

rec <- recipe(Frequency~., data=train) %>% 
       update_role(contains("id"), Year, Month, Monsoon, Days, new_role = "id vars") %>% # declare ID variables
       step_nzv(all_predictors(), freq_cut = 0, unique_cut = 0) %>% # remove variables with zero variances
       step_novel(all_nominal()) %>% # prepares test data to handle previously unseen factor levels 
       step_medianimpute(all_numeric(), -all_outcomes(), -has_role("id vars"))  %>% # replaces missing numeric observations with the median
       step_dummy(all_nominal(), -has_role("id vars")) # dummy codes categorical variables
    
    ###########################################################
    ##Create Models
    ###########################################################

    #####Bagged Trees
    mod_bag <- bag_tree() %>%
                set_mode("regression") %>%
                 set_engine("rpart", times = 10) # 10 bootstrap resamples
    
    ##Create workflow
    wflow_bag <- workflow() %>% 
                       add_recipe(rec) %>%
                           add_model(mod_bag)
    
    ##Fit the model
    plan(multisession)
    
    fit_bag <- fit_resamples(
                       wflow_bag,
                       cv,
                       metrics = metric_set(rmse, rsq),
                       control = control_resamples(verbose = TRUE,
                       save_pred = TRUE,
                       extract = function(x) extract_model(x)))
    
    ##Random forests
    
    mod_rf <-rand_forest() %>%
                          set_engine("ranger",
                          num.threads = parallel::detectCores(), 
                          importance = "permutation", 
                          verbose = TRUE) %>% 
                          set_mode("regression") %>% 
                          set_args(trees = 1000)
    
    ##Create Workflow
    
    wflow_rf <- workflow() %>% 
                   add_model(mod_rf) %>% 
                         add_recipe(rec)
    
    ##Fit the model
    
    plan(multisession)
    
    fit_rf <- fit_resamples(
                         wflow_rf,
                         cv,
                         metrics = metric_set(rmse, rsq),
                         control = control_resamples(verbose = TRUE,
                         save_pred = TRUE,
                         extract = function(x) x)
                         )
    
    ##Boosted Trees
    
    mod_boost <- boost_tree() %>% 
                  set_engine("xgboost", nthreads = parallel::detectCores()) %>% 
                  set_mode("regression")
    
    ##Create workflow
    
    wflow_boost <- workflow() %>% 
                      add_recipe(rec) %>% 
                      add_model(mod_boost)
    
    ##Fit model
    
    plan(multisession)
    
    fit_boost <- fit_resamples(
                           wflow_boost, 
                           cv,
                           metrics = metric_set(rmse, rsq),
                           control = control_resamples(verbose = TRUE,
                           save_pred = TRUE)
                           )

데이터 프레임-FID

structure(list(Year = c(2015, 2015, 2015, 2015, 2015, 2015, 2015, 
2015, 2015, 2015, 2015, 2015, 2016, 2016, 2016, 2016, 2016, 2016, 
2016, 2016, 2016, 2016, 2016, 2016, 2017, 2017, 2017, 2017, 2017, 
2017, 2017, 2017, 2017, 2017, 2017, 2017), Month = structure(c(1L, 
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 1L, 2L, 3L, 4L, 
5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 
8L, 9L, 10L, 11L, 12L), .Label = c("January", "February", "March", 
"April", "May", "June", "July", "August", "September", "October", 
"November", "December"), class = "factor"), Monsoon = structure(c(2L, 
2L, 1L, 1L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 2L, 2L, 2L, 1L, 1L, 4L, 
4L, 4L, 4L, 4L, 3L, 3L, 2L, 2L, 2L, 1L, 1L, 4L, 4L, 4L, 4L, 4L, 
3L, 3L, 2L), .Label = c("First_Inter_Monssoon", "North_Monsoon", 
"Second_Inter_Monsoon", "South_Monsson"), class = "factor"), 
    Frequency = c(36, 28, 39, 46, 5, 0, 0, 22, 10, 15, 8, 
    33, 33, 29, 31, 23, 8, 9, 7, 40, 41, 41, 30, 30, 44, 37, 
    41, 42, 20, 0, 7, 27, 35, 27, 43, 38), Days = c(31, 
    28, 31, 30, 6, 0, 0, 29, 15, 29, 29, 31, 31, 29, 30, 30, 
    7, 0, 7, 30, 30, 31, 30, 27, 31, 28, 30, 30, 21, 0, 7, 26, 
    29, 27, 29, 29)), row.names = c(NA, -36L), class = "data.frame")

Answer 1

문제는 여기에 사용할 때입니다 update_role(contains("id"), Year, Month, Monsoon, Days, new_role = "id vars"), 당신과 같은 모든 변수의 역할 업데이트 Year, Month, Monsoon, 등이 될를 "id vars"하고 그들이 예측은 더 이상 없습니다. 레시피가 다음 전처리 단계로 이동하면 예측 변수가 전혀 없음을 발견합니다.

이러한 변수를 예측 변수로 사용하려면 역할을 그대로두고 다음과 같이 변경하지 마십시오 "id vars".

library(tidymodels) 
library(baguette) # bagged trees

fid_df <- structure(list(Year = c(2015, 2015, 2015, 2015, 2015, 2015, 2015, 
                                  2015, 2015, 2015, 2015, 2015, 2016, 2016, 2016, 2016, 2016, 2016, 
                                  2016, 2016, 2016, 2016, 2016, 2016, 2017, 2017, 2017, 2017, 2017, 
                                  2017, 2017, 2017, 2017, 2017, 2017, 2017), Month = structure(c(1L, 
                                                                                                 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 1L, 2L, 3L, 4L, 
                                                                                                 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 
                                                                                                 8L, 9L, 10L, 11L, 12L), .Label = c("January", "February", "March", 
                                                                                                                                    "April", "May", "June", "July", "August", "September", "October", 
                                                                                                                                    "November", "December"), class = "factor"), Monsoon = structure(c(2L, 
                                                                                                                                                                                                      2L, 1L, 1L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 2L, 2L, 2L, 1L, 1L, 4L, 
                                                                                                                                                                                                      4L, 4L, 4L, 4L, 3L, 3L, 2L, 2L, 2L, 1L, 1L, 4L, 4L, 4L, 4L, 4L, 
                                                                                                                                                                                                      3L, 3L, 2L), .Label = c("First_Inter_Monssoon", "North_Monsoon", 
                                                                                                                                                                                                                              "Second_Inter_Monsoon", "South_Monsson"), class = "factor"), 
                         Frequency = c(36, 28, 39, 46, 5, 0, 0, 22, 10, 15, 8, 
                                       33, 33, 29, 31, 23, 8, 9, 7, 40, 41, 41, 30, 30, 44, 37, 
                                       41, 42, 20, 0, 7, 27, 35, 27, 43, 38), Days = c(31, 
                                                                                       28, 31, 30, 6, 0, 0, 29, 15, 29, 29, 31, 31, 29, 30, 30, 
                                                                                       7, 0, 7, 30, 30, 31, 30, 27, 31, 28, 30, 30, 21, 0, 7, 26, 
                                                                                       29, 27, 29, 29)), row.names = c(NA, -36L), class = "data.frame")

# split the data
fid_split <- initial_split(fid_df)

# extract the training data
fid_train <- training(fid_split)

# resample the data with 10-fold cross-validation (10-fold by default)
cv <- vfold_cv(fid_train)

##Preprocessing

rec <- recipe(Frequency ~ ., data = fid_df) %>% 
  step_nzv(all_predictors(), freq_cut = 0, unique_cut = 0) %>% # remove variables with zero variances
  step_novel(all_nominal()) %>% # prepares test data to handle previously unseen factor levels 
  step_medianimpute(all_numeric(), -all_outcomes(), -has_role("id vars"))  %>% # replaces missing numeric observations with the median
  step_dummy(all_nominal(), -has_role("id vars")) # dummy codes categorical variables


rf_spec <- rand_forest(trees = 1e3) %>%
  set_engine("ranger", importance = "permutation") %>% 
  set_mode("regression")

wflow_rf <- workflow() %>% 
  add_model(rf_spec) %>% 
  add_recipe(rec)

fit_resamples(
  wflow_rf,
  cv,
  metrics = metric_set(rmse, rsq),
  control = control_resamples(save_pred = TRUE)
)
#> 
#> Attaching package: 'rlang'
#> The following objects are masked from 'package:purrr':
#> 
#>     %@%, as_function, flatten, flatten_chr, flatten_dbl, flatten_int,
#>     flatten_lgl, flatten_raw, invoke, list_along, modify, prepend,
#>     splice
#> 
#> Attaching package: 'vctrs'
#> The following object is masked from 'package:tibble':
#> 
#>     data_frame
#> The following object is masked from 'package:dplyr':
#> 
#>     data_frame
#> # Resampling results
#> # 10-fold cross-validation 
#> # A tibble: 10 x 5
#>    splits         id     .metrics         .notes           .predictions    
#>    <list>         <chr>  <list>           <list>           <list>          
#>  1 <split [24/3]> Fold01 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [3 × 4]>
#>  2 <split [24/3]> Fold02 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [3 × 4]>
#>  3 <split [24/3]> Fold03 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [3 × 4]>
#>  4 <split [24/3]> Fold04 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [3 × 4]>
#>  5 <split [24/3]> Fold05 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [3 × 4]>
#>  6 <split [24/3]> Fold06 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [3 × 4]>
#>  7 <split [24/3]> Fold07 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [3 × 4]>
#>  8 <split [25/2]> Fold08 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [2 × 4]>
#>  9 <split [25/2]> Fold09 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [2 × 4]>
#> 10 <split [25/2]> Fold10 <tibble [2 × 4]> <tibble [0 × 1]> <tibble [2 × 4]>

^{reprex 패키지 (v0.3.0.9001)에 의해 2020-11-18에 생성됨}