我遇到了一些奇怪的行为,使用一个配方和一个工作流来区分垃圾邮件和使用 naiveBayes 分类器的有效文本。我试图使用 tidymodels 和工作流程来复制本书第 4 章机器学习与 R 的结果:https ://github.com/PacktPublishing/Machine-Learning-with-R-Second-Edition/blob/master/Chapter %2004/MLwR_v2_04.r
虽然我能够在有add_variables()
或add_formula()
没有工作流的情况下重现分析,但使用该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)
虽然以下代码不起作用
nb_fit <- workflow() %>%
add_model(nb_model) %>%
add_recipe(reci_sms) %>%
fit(data = df_training)
nb_tidy_pred <- nb_fit %>% predict(df_testing)
它还会引发以下错误,但我不太明白使用时发生了什么rlang::last_error()
Not all variables in the recipe are present in the supplied training set: 'text'.
Run `rlang::last_error()` to see where the error occurred.
有人能告诉我我错过了什么吗?