Tidymodels 工作流使用 add_formula() 或 add_variables() 但不使用 add_recipe()

如何解决Tidymodels 工作流使用 add_formula() 或 add_variables() 但不使用 add_recipe()

我在使用 naiveBayes 分类器从有效文本中区分垃圾邮件的方法和工作流程中遇到了一些奇怪的行为。我试图使用 tidymodels 和工作流复制机器学习与 R 一书的第 4 章的结果：https://github.com/PacktPublishing/Machine-Learning-with-R-Second-Edition/blob/master/Chapter%2004/MLwR_v2_04.r

虽然我可以使用 add_variables() 或 add_formula() 或不使用工作流重现分析，但使用 add_recipe() 函数的工作流不起作用。

library(RCurl)
library(tidyverse)
library(tidymodels)
library(textrecipes)
library(tm)
library(snowballC) 
library(discrim) 


sms_raw <- getURL("https://raw.githubusercontent.com/stedy/Machine-Learning-with-R-datasets/master/sms_spam.csv")
sms_raw <- read_csv(sms_raw)
sms_raw$type <- factor(sms_raw$type)

set.seed(123)
split <- initial_split(sms_raw,prop = 0.8,strata = "type")
nb_train_sms <- training(split)
nb_test_sms <- testing(split)

# Text preprocessing
reci_sms <- 
  recipe(type ~.,data = nb_train_sms) %>% 
  step_mutate(text = str_to_lower(text)) %>% 
  step_mutate(text = removeNumbers(text)) %>% 
  step_mutate(text = removePunctuation(text)) %>% 
  step_tokenize(text) %>% 
  step_stopwords(text,custom_stopword_source = stopwords()) %>% 
  step_stem(text) %>% 
  step_tokenfilter(text,min_times = 6,max_tokens = 1500) %>% 
  step_tf(text,weight_scheme = "binary") %>% 
  step_mutate_at(contains("tf"),fn =function(x){ifelse(x == TRUE,"Yes","No")}) %>% 
  prep()


df_training <- juice(reci_sms)
df_testing <- bake(reci_sms,new_data = nb_test_sms)

nb_model <- naive_Bayes() %>% 
  set_engine("klaR") 

以下是三个实际产生有效输出的代码示例

# --------- works but slow -----
nb_fit <- nb_fit <- workflow() %>%
  add_model(nb_model) %>%
  add_formula(type~.) %>%
  fit(df_training)
nb_tidy_pred <- nb_fit %>% predict(df_testing)


# --------- works  -----
nb_fit <- nb_model %>% fit(type ~.,df_training)
nb_tidy_pred <- nb_fit %>% predict(df_testing)


# --------- works  -----

nb_fit <- workflow() %>%
  add_model(nb_model) %>%
  add_variables(outcomes = type,predictors = everything()) %>%
  fit(df_training)

nb_tidy_pred <- nb_fit %>% predict(df_testing)

虽然下面的代码不起作用

nb_fit <- workflow() %>%
  add_model(nb_model) %>%
  add_recipe(reci_sms) %>%
  fit(data = df_training)

nb_tidy_pred <- nb_fit %>% predict(df_testing)

它也抛出以下错误，但我真的不明白使用 rlang::last_error() 时发生了什么

Not all variables in the recipe are present in the supplied training set: 'text'.
Run `rlang::last_error()` to see where the error occurred.

谁能告诉我我错过了什么？

解决方法

当您在工作流程中使用配方时，您可以将预处理步骤与模型拟合相结合。在拟合该工作流程时，您需要使用配方预期的数据 (nb_train_sms)，而不是欧洲防风草模型预期的数据。

此外，它是 not recommended to pass a prepped recipe to a workflow，所以在使用 prep() 将其添加到工作流程之前，看看我们如何不add_recipe()。

library(RCurl)
library(tidyverse)
library(tidymodels)
library(textrecipes)
library(tm) 
library(discrim)

sms_raw <- getURL("https://raw.githubusercontent.com/stedy/Machine-Learning-with-R-datasets/master/sms_spam.csv")
sms_raw <- read_csv(sms_raw)
sms_raw$type <- factor(sms_raw$type)

set.seed(123)
split <- initial_split(sms_raw,prop = 0.8,strata = "type")
nb_train_sms <- training(split)
nb_test_sms <- testing(split)

# Text preprocessing
reci_sms <- 
  recipe(type ~.,data = nb_train_sms) %>% 
  step_mutate(text = str_to_lower(text)) %>% 
  step_mutate(text = removeNumbers(text)) %>% 
  step_mutate(text = removePunctuation(text)) %>% 
  step_tokenize(text) %>% 
  step_stopwords(text,custom_stopword_source = stopwords()) %>% 
  step_stem(text) %>% 
  step_tokenfilter(text,min_times = 6,max_tokens = 1500) %>% 
  step_tf(text,weight_scheme = "binary")  %>% 
  step_mutate_at(contains("tf"),fn = function(x){ifelse(x == TRUE,"Yes","No")})

nb_model <- naive_Bayes() %>% 
  set_engine("klaR") 

nb_fit <- workflow() %>%
  add_model(nb_model) %>%
  add_recipe(reci_sms) %>%
  fit(data = nb_train_sms)
#> Warning: max_features was set to '1500',but only 1141 was available and
#> selected.

nb_tidy_pred <- nb_fit %>% predict(nb_train_sms)

^{由 reprex package (v1.0.0) 于 2021 年 4 月 19 日创建}