予測と評価

Rで学ぶTree-Based ModelsによるMachine Learning

Sandro Raabe

Data Scientist

新規データへの予測

predict(model, new_data, type)

predict(model, new_data = test_data, 
               type = "class")

  .pred_class
  <fct>      
1 no         
2 no         
3 yes        
4 no

predict(model, new_data = test_data, 
               type = "prob")

     .pred_no  .pred_yes
     <dbl>     <dbl>
1    0.866     0.134
2    0.956     0.044
3    0.672     0.328
4    0.877     0.123

混同行列_1

混同行列_2

混同行列_3

混同行列_4

混同行列_4

# 予測と真値を結合
pred_combined <- predictions %>% 
   mutate(true_class = test_data$outcome)

pred_combined

  .pred_class  true_class
  <fct>        <fct>     
1 no           no        
2 no           yes       
3 no           no        
4 yes          yes

# 混同行列を計算
conf_mat(data = pred_combined,

         estimate = .pred_class,

         truth = true_class)

             Truth
Prediction    no   yes
        no   116    31
       yes    12    40

$$\text{accuracy} = \frac{\text{正解数}}{\text{予測総数}}$$

accuracy(pred_combined,
         estimate = .pred_class,
         truth = true_class)

  .metric     .estimate
  <chr>           <dbl>
1 accuracy        0.708

Rで学ぶTree-Based ModelsによるMachine Learning