공통 특성 변환

R로 배우는 Feature Engineering

Jorge Zazueta

Research Professor and Head of the Modeling Group at the School of Economics, UASLP

두 가지 변환 계열

Box-Cox

비정규 분포 변수를 정규에 가깝게 변환
역수, 로그, 제곱·세제곱근을 특수 사례로 포함
양의 값에만 적용 가능

Box-Cox 변환 식.

Yeo-Johnson

Box-Cox와 유사한 성질
0 및 음수도 처리 가능
양의 $y$에서는 $y+1$에 Box-Cox를 적용한 것과 동일

Yeo-Johnson 변환 식.

loans_num 데이터셋

glimpse(loans_num)

Rows: 480
Columns: 6
$ Loan_Status       <fct> N, Y, Y, Y, Y, Y, N, Y, N, Y, Y, N, Y, Y, N...
$ ApplicantIncome   <dbl> 4583, 3000, 2583, 6000, 5417, 2333, 3036, 4...
$ CoapplicantIncome <dbl> 1508, 0, 2358, 0, 4196, 1516, 2504, 1526, 1...
$ LoanAmount        <dbl> 128, 66, 120, 141, 267, 95, 158, 168, 349, ...
$ Loan_Amount_Term  <dbl> 360, 360, 360, 360, 360, 360, 360, 360, 360...
$ Credit_History    <fct> 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0...

변환 적용하기

기본 레시피

lr_recipe_plain <- # Define recipe
  recipe(Loan_Status ~., data = train)
lr_workflow_plain <- # Bundle workflows
  workflow() %>%
  add_model(lr_model) %>%
  add_recipe(lr_recipe_plain)
lr_fit_plain <- # fit and augment
  lr_workflow_plain %>%
  fit(train)

성능 평가

lr_aug_plain %>% # Assess
  class_evaluate(truth = Loan_Status,
                 estimate = .pred_class,
                 .pred_N)

# A tibble: 2 × 3
  .metric  .estimator .estimate
  <chr>    <chr>          <dbl>
1 accuracy binary         0.817
2 roc_auc  binary         0.641

변환 적용하기

Box-Cox 레시피

lr_recipe_BC <- # Define recipe
  recipe(Loan_Status ~., data = train) %>%
  step_BoxCox(all_numeric())
lr_workflow_BC <- # Bundle workflows
  workflow() %>%
  add_model(lr_model) %>%
  add_recipe(lr_recipe_BC)
lr_fit_BC <- # fit and augment
  lr_workflow_BC %>%
  fit(train)

경고 메시지

Box-Cox는 0 이하 값을 처리할 수 없습니다

Warning messages:
1: Non-positive values in selected
variable. 
2: No Box-Cox transformation could be 
estimated for: `CoapplicantIncome`

변환 적용하기

Box-Cox 레시피(두 번째 시도)

경고를 피하려면 CoappliantIncome 선택을 해제하겠습니다.

lr_recipe_BC <- # Define recipe
  recipe(Loan_Status ~., data = train) %>%
  step_BoxCox(all_numeric(), 
              -CoapplicantIncome)
lr_workflow_BC <- # Bundle workflows
  workflow() %>%
  add_model(lr_model) %>%
  add_recipe(lr_recipe_BC)
lr_fit_BC <- # fit and augment
  lr_workflow_BC %>%
  fit(train)

성능 평가

lr_aug_BC %>% # Assess
  class_evaluate(truth = Loan_Status,
                 estimate = .pred_class,
                 .pred_N)

# A tibble: 2 × 3
  .metric  .estimator .estimate
  <chr>    <chr>          <dbl>
1 accuracy binary         0.817
2 roc_auc  binary         0.599

변환 적용하기

Yeo-Johnson 레시피

lr_recipe_YJ <- # Define recipe
  recipe(Loan_Status ~., data = train) %>%
  step_YeoJohnson(all_numeric())
lr_workflow_YJ <- # Bundle workflows
  workflow() %>%
  add_model(lr_model) %>%
  add_recipe(lr_recipe_YJ)
lr_fit_YJ <- # fit and augment
  lr_workflow_YJ %>%
  fit(train)

성능 평가

lr_aug_YJ %>% # Assess
  class_evaluate(truth = Loan_Status,
                 estimate = .pred_class,
                 .pred_N)

# A tibble: 2 × 3
  .metric  .estimator .estimate
  <chr>    <chr>          <dbl>
1 accuracy binary         0.817
2 roc_auc  binary         0.700

연습해 봅시다!

R로 배우는 Feature Engineering