1

将 recipes::step_dummy 与 caret::train 一起使用时出现以下错误（第一次尝试组合这两个包）：

错误：并非配方中的所有变量都存在于提供的训练集中

不确定是什么导致了错误，也不确定调试的最佳方法。帮助训练模型将不胜感激。

library(caret)
library(tidyverse)
library(recipes)
library(rsample)

data("credit_data")

## Split the data into training (75%) and test sets (25%)
set.seed(100)
train_test_split <- initial_split(credit_data)
credit_train <- training(train_test_split)
credit_test <- testing(train_test_split)

# Create recipe for data pre-processing
rec_obj <- recipe(Status ~ ., data = credit_train) %>%
  step_knnimpute(all_predictors()) %>%
  #step_other(Home, Marital, threshold = .2, other = "other") %>%
  #step_other(Job, threshold = .2, other = "others") %>%
  step_dummy(Records)  %>% 
  step_center(all_numeric())  %>%
  step_scale(all_numeric()) %>%
  prep(training = credit_train, retain = TRUE) 

train_data <- juice(rec_obj)
test_data  <- bake(rec_obj, credit_test)

set.seed(1055)
# the glm function models the second factor level.
lrfit <- train(rec_obj, data = train_data,
                     method = "glm",
                     trControl = trainControl(method = "repeatedcv", 
                                              repeats = 5))
4

2 回答 2

3

train在使用原始训练集之前不要准备食谱：

library(caret)
#> Loading required package: lattice
#> Loading required package: ggplot2
library(tidyverse)
library(recipes)
#> 
#> Attaching package: 'recipes'
#> The following object is masked from 'package:stringr':
#> 
#>     fixed
#> The following object is masked from 'package:stats':
#> 
#>     step
library(rsample)

data("credit_data")

## Split the data into training (75%) and test sets (25%)
set.seed(100)
train_test_split <- initial_split(credit_data)
credit_train <- training(train_test_split)
credit_test <- testing(train_test_split)

# Create recipe for data pre-processing
rec_obj <- 
  recipe(Status ~ ., data = credit_train) %>%
  step_knnimpute(all_predictors()) %>%
  #step_other(Home, Marital, threshold = .2, other = "other") %>%
  #step_other(Job, threshold = .2, other = "others") %>%
  step_dummy(Records)  %>% 
  step_center(all_numeric())  %>%
  step_scale(all_numeric()) 

set.seed(1055)
# the glm function models the second factor level.
lrfit <- train(rec_obj, data = credit_train,
               method = "glm",
               trControl = trainControl(method = "repeatedcv", 
                                        repeats = 5))
lrfit
#> Generalized Linear Model 
#> 
#> 3341 samples
#>   13 predictor
#>    2 classes: 'bad', 'good' 
#> 
#> Recipe steps: knnimpute, dummy, center, scale 
#> Resampling: Cross-Validated (10 fold, repeated 5 times) 
#> Summary of sample sizes: 3006, 3008, 3007, 3007, 3007, 3007, ... 
#> Resampling results:
#> 
#>   Accuracy   Kappa    
#>   0.7965349  0.4546223

由reprex 包（v0.2.1）于 2019 年 3 月 20 日创建

于 2019-03-20T21:38:10.523 回答
0

看来您仍然需要 train 函数中的公式（尽管已在食谱中列出）？...

glmfit <- train(Status ~ ., data = juice(rec_obj),
                     method = "glm",
                     trControl = trainControl(method = "repeatedcv", repeats = 5))
于 2019-03-13T01:10:53.920 回答