R textrecipes step_word_embeddings 令牌的预训练词嵌入

step_word_embeddings(
  recipe,
  ...,
  role = "predictor",
  trained = FALSE,
  columns = NULL,
  embeddings,
  aggregation = c("sum", "mean", "min", "max"),
  aggregation_default = 0,
  prefix = "wordembed",
  keep_original_cols = FALSE,
  skip = FALSE,
  id = rand_id("word_embeddings")
)

step_tokenize() 将字符转换为tokens

来自标记的数字变量的其他步骤：step_lda()、step_texthash()、step_tfidf()、step_tf()

library(recipes)

embeddings <- tibble(
  tokens = c("the", "cat", "ran"),
  d1 = c(1, 0, 0),
  d2 = c(0, 1, 0),
  d3 = c(0, 0, 1)
)

sample_data <- tibble(
  text = c(
    "The.",
    "The cat.",
    "The cat ran."
  ),
  text_label = c("fragment", "fragment", "sentence")
)

rec <- recipe(text_label ~ ., data = sample_data) %>%
  step_tokenize(text) %>%
  step_word_embeddings(text, embeddings = embeddings)

obj <- rec %>%
  prep()

bake(obj, sample_data)
#> # A tibble: 3 × 4
#>   text_label wordembed_text_d1 wordembed_text_d2 wordembed_text_d3
#>   <fct>                  <dbl>             <dbl>             <dbl>
#> 1 fragment                   1                 0                 0
#> 2 fragment                   1                 1                 0
#> 3 sentence                   1                 1                 1

tidy(rec, number = 2)
#> # A tibble: 1 × 4
#>   terms embeddings_rows aggregation id                   
#>   <chr>           <int> <chr>       <chr>                
#> 1 text                3 sum         word_embeddings_HUbJD
tidy(obj, number = 2)
#> # A tibble: 1 × 4
#>   terms embeddings_rows aggregation id                   
#>   <chr>           <int> <chr>       <chr>                
#> 1 text                3 sum         word_embeddings_HUbJD