我想在配方中计算出第 X 个 PCA 组件后选择它们。然后我想在工作流程中添加这个配方。
请参阅下面的示例数据。
library(tidymodels)
x1 <- c(1, 6, 4, 2, 3, 4, 5, 7, 8, 2)
x2 <- c(1, 3, 4, 2, 3, 4, 5, 7, 8, 2)
x3 <- c(1, 3, 4, 2, 3, 4, 5, 7, 8, 2)
x4 <- c(1, 3, 4, 2, 3, 4, 5, 7, 8, 2)
id <- c(1:10)
y <- c(1, 4, 2, 5, 6, 2, 3, 6, 2, 4)
df1_train <- tibble(x1, x2, x3, x4, id, y)
step_PCA_PREPROCESSING = 4
selectXfirstPCA = 3
# My recipe
df1_train_recipe <- df1_train %>%
recipes::recipe(y ~ .) %>%
recipes::update_role(id, new_role = "id variable") %>%
recipes::step_pca(., recipes::all_predictors(), num_comp = step_PCA_PREPROCESSING) %>%
recipes::update_role(tidyselect::num_range("PC", 1:selectXfirstPCA), new_role = "predictor")
# To then continue like below:
# Model specifications
model_spec <- parsnip::linear_reg() %>%
parsnip::set_engine("glmnet")
# Create workflow (to know variable roles from recipes)
df1_workflow <- workflows::workflow() %>%
workflows::add_recipe(df1_train_recipe) %>%
workflows::add_model(model_spec)
# Fit model
mod <- parsnip::fit(df1_workflow, data = df1_train)