Punând totul laolaltă

Ingineria caracteristicilor în R

Jorge Zazueta

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

Un flux stilizat al procesului de modelare

Etapele tipice de modelare la nivel înalt.

Diagramă a procesului de modelare.

Un flux stilizat al procesului de modelare

Etapele tipice de modelare la nivel înalt.

Flux al procesului de modelare, evidențiind ingineria caracteristicilor.

Pregătire

Pregătiri de bază și configurarea împărțirilor.

loans <- # Basic housekeeping
  loans %>%
  mutate(across(where(is_character),
                  as_factor)) %>%
  mutate(across(Credit_History,
                  as_factor))

set.seed(123) # Set up splits
split <- initial_split(loans, 
        strata = Loan_Status)
test <- testing(split)
train <- training(split)

glimpse(train)

Rows: 460
Columns: 13
$ Loan_ID           <fct> LP001003...
$ Gender            <fct> Male, Ma...
$ Married           <fct> Yes, No,...
$ Dependents        <fct> 1, 0, 0,...
$ Education         <fct> Graduate...
$ Self_Employed     <fct> No, No, ...
$ ApplicantIncome   <dbl> 4583, 18...
$ CoapplicantIncome <dbl> 1508, 28...
$ LoanAmount        <dbl> 128, 114...
$ Loan_Amount_Term  <dbl> 360, 360...
$ Credit_History    <fct> 1, 1, 0,...
$ Property_Area     <fct> Rural, R...
$ Loan_Status       <fct> N, N, N,...

Preprocesare

Rețeta poate fi simplă sau complexă.

recipe <- recipe(Loan_Status ~ .,
data = train) %>%
  update_role(Loan_ID, 
  new_role = "ID") %>%
  step_normalize(all_numeric_predictors()) %>% 
  step_impute_knn(all_predictors()) %>%
  step_dummy(all_nominal_predictors())

recipe

Recipe

Inputs:

      role #variables
        ID          1
   outcome          1
 predictor         11

Operations:

Centering and scaling for all_numeric_predictors()
K-nearest neighbor imputation for all_predictors()
Dummy variables from all_nominal_predictors()

Model

Configurarea fluxului de lucru

lr_model <- logistic_reg() %>%
  set_engine("glmnet") %>%
  set_args(mixture = 1, penalty = tune())

lr_penalty_grid <- grid_regular(
  penalty(range = c(-3, 1)),
  levels = 30)

lr_workflow <-
  workflow() %>%
  add_model(lr_model) %>%
  add_recipe(recipe)

lr_workflow

--Workflow -------------------------------
Preprocessor: Recipe
Model: logistic_reg()

-- Preprocessor --------------------------
3 Recipe Steps
- step_normalize()
- step_impute_knn()
- step_dummy()

-- Model ---------------------------------
Logistic Regression Model Specification (classification)

Main Arguments:
  penalty = tune()
  mixture = 1
Computational engine: glmnet

Evaluare

Ajustarea penalizării pentru Lasso

lr_tune_output <- tune_grid( 
  lr_workflow,
  resamples = vfold_cv(train, v = 5),
  metrics = metric_set(roc_auc),
  grid = penalty_grid)

autoplot(tune_output)

ROC_AUC față de regularizare

Grafic ROC_AUC față de regularizare.

Evaluare

Antrenarea modelului final

best_penalty <-
select_by_one_std_err(lr_tune_output,
metric = 'roc_auc', desc(penalty)) 

lr_final_fit<-
finalize_workflow(lr_workflow, best_penalty) %>%
  fit(data = train)

lr_final_fit %>%
  augment(test) %>% 
  class_evaluate(truth = Loan_Status,
              estimate = .pred_class,
                         .pred_Y)

Metricile de performanță

# A tibble: 2 × 3
  .metric  .estimator .estimate
  <chr>    <chr>          <dbl>
1 accuracy binary         0.818
2 roc_auc  binary         0.813

Să exersăm!

Ingineria caracteristicilor în R