Common feature transformations

Feature Engineering in R

Jorge Zazueta

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

Two families of transformations

Box-Cox

Used to transform non-normal variable closer to normal
As a family, it includes inverse, log, square and cubic roots as special cases
Works for strictly positive values

Box-Cox transformation equation.

Yeo-Johnson

Similar properties as Box-Cox
Can handle zero and negative values
For positive $y$ is the same as Box-Cox of $y+1$

Yeo-Johnson transformation equation.

The loans_num dataset

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...

Applying transformations

Plain recipe

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)

Assess performance

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

Applying transformations

Box-Cox recipe

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)

Warning Message

Box-Cox is unable to process non-positive values

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

Applying transformations

Box-Cox recipe (take two)

Now, let's deselect CoappliantIncome to avoid the warning.

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)

Assess performance

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

Applying transformations

Yeo-Johnson recipe

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)

Assess performance

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

Let's practice!

Feature Engineering in R