R themis step_smote 应用SMOTE算法

step_smote(
  recipe,
  ...,
  role = NA,
  trained = FALSE,
  column = NULL,
  over_ratio = 1,
  neighbors = 5,
  skip = TRUE,
  seed = sample.int(10^5, 1),
  id = rand_id("smote")
)

smote() 直接实现

过采样的其他步骤：step_adasyn()、step_bsmote()、step_rose()、step_smotenc()、step_upsample()

library(recipes)
library(modeldata)
data(hpc_data)

hpc_data0 <- hpc_data %>%
  select(-protocol, -day)

orig <- count(hpc_data0, class, name = "orig")
orig
#> # A tibble: 4 × 2
#>   class  orig
#>   <fct> <int>
#> 1 VF     2211
#> 2 F      1347
#> 3 M       514
#> 4 L       259

up_rec <- recipe(class ~ ., data = hpc_data0) %>%
  # Bring the minority levels up to about 1000 each
  # 1000/2211 is approx 0.4523
  step_smote(class, over_ratio = 0.4523) %>%
  prep()

training <- up_rec %>%
  bake(new_data = NULL) %>%
  count(class, name = "training")
training
#> # A tibble: 4 × 2
#>   class training
#>   <fct>    <int>
#> 1 VF        2211
#> 2 F         1347
#> 3 M         1000
#> 4 L         1000

# Since `skip` defaults to TRUE, baking the step has no effect
baked <- up_rec %>%
  bake(new_data = hpc_data0) %>%
  count(class, name = "baked")
baked
#> # A tibble: 4 × 2
#>   class baked
#>   <fct> <int>
#> 1 VF     2211
#> 2 F      1347
#> 3 M       514
#> 4 L       259

# Note that if the original data contained more rows than the
# target n (= ratio * majority_n), the data are left alone:
orig %>%
  left_join(training, by = "class") %>%
  left_join(baked, by = "class")
#> # A tibble: 4 × 4
#>   class  orig training baked
#>   <fct> <int>    <int> <int>
#> 1 VF     2211     2211  2211
#> 2 F      1347     1347  1347
#> 3 M       514     1000   514
#> 4 L       259     1000   259

library(ggplot2)

ggplot(circle_example, aes(x, y, color = class)) +
  geom_point() +
  labs(title = "Without SMOTE")


recipe(class ~ x + y, data = circle_example) %>%
  step_smote(class) %>%
  prep() %>%
  bake(new_data = NULL) %>%
  ggplot(aes(x, y, color = class)) +
  geom_point() +
  labs(title = "With SMOTE")