错误：`data`和`reference`应该是具有相同水平的因子。 Logistic回归的混淆矩阵

Question

我已经看到许多有关此特定错误的答案。对于我的特定问题，我尚未找到任何答案。因此，我的问题

这是我的工作：

    shortness_breath_data <- data_categ_nosev %>%
dplyr::select(shortness_breath, obesity, asthma, diabetes_type_one, diabetes_type_two, obesity, hypertension, heart_disease, lung_condition, liver_disease, kidney_disease, Covid_tested, Gender) 

这是put(head(shortness_breath_data))：

structure(list(shortness_breath = structure(c(1L, 2L, 1L, 1L, 
1L, 2L), .Label = c("No", "Yes"), class = "factor"), obesity = structure(c(1L, 
1L, 2L, 2L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    asthma = structure(c(2L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), diabetes_type_one = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    diabetes_type_two = structure(c(2L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), hypertension = structure(c(1L, 
    1L, 1L, 2L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    heart_disease = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), lung_condition = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    liver_disease = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), kidney_disease = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    Covid_tested = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("negative", 
    "positive"), class = "factor"), Gender = structure(c(2L, 
    1L, 2L, 1L, 1L, 2L), .Label = c("Female", "Male", "Other"
    ), class = "factor")), row.names = c(NA, -6L), class = c("tbl_df", 
"tbl", "data.frame"), problems = structure(list(row = c(2910L, 
35958L), col = c("how_unwell", "how_unwell"), expected = c("a double", 
"a double"), actual = c("How Unwell", "How Unwell"), file = c("'/Users/gabrielburcea/Rprojects/data/data_lev_categorical_no_sev.csv'", 
"'/Users/gabrielburcea/Rprojects/data/data_lev_categorical_no_sev.csv'"
)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"
)))

然后将其分为训练和测试数据集。

shortness_breath_data$shortness_breath <- as.factor(shortness_breath_data$shortness_breath)

n <- nrow(shortness_breath_data)
set.seed(22)
trainingdx <- sample(1:n, 0.7 * n)

train <- shortness_breath_data[trainingdx,]
validate <- shortness_breath_data[-trainingdx,]

train %>% distinct(shortness_breath)
validate %>% distinct(shortness_breath)

[为了避免麻烦，我也提供了dput(head(train))和dput(head(validate))]进行同样的操作>

火车数据集：

structure(list(shortness_breath = structure(c(1L, 1L, 1L, 1L, 
1L, 1L), .Label = c("No", "Yes"), class = "factor"), obesity = structure(c(2L, 
1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    asthma = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), diabetes_type_one = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    diabetes_type_two = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), hypertension = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    heart_disease = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), lung_condition = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    liver_disease = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), kidney_disease = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    Covid_tested = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("negative", 
    "positive"), class = "factor"), Gender = structure(c(1L, 
    1L, 1L, 2L, 1L, 2L), .Label = c("Female", "Male", "Other"
    ), class = "factor")), row.names = c(NA, -6L), class = c("tbl_df", 
"tbl", "data.frame"), problems = structure(list(row = c(2910L, 
35958L), col = c("how_unwell", "how_unwell"), expected = c("a double", 
"a double"), actual = c("How Unwell", "How Unwell"), file = c("'/Users/gabrielburcea/Rprojects/data/data_lev_categorical_no_sev.csv'", 
"'/Users/gabrielburcea/Rprojects/data/data_lev_categorical_no_sev.csv'"
)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"
)))
验证数据集：

structure(list(shortness_breath = structure(c(1L, 2L, 2L, 1L, 
1L, 1L), .Label = c("No", "Yes"), class = "factor"), obesity = structure(c(1L, 
1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    asthma = structure(c(2L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), diabetes_type_one = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    diabetes_type_two = structure(c(2L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), hypertension = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    heart_disease = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), lung_condition = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    liver_disease = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No", 
    "Yes"), class = "factor"), kidney_disease = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"), 
    Covid_tested = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("negative", 
    "positive"), class = "factor"), Gender = structure(c(2L, 
    1L, 2L, 2L, 1L, 1L), .Label = c("Female", "Male", "Other"
    ), class = "factor")), row.names = c(NA, -6L), class = c("tbl_df", 
"tbl", "data.frame"), problems = structure(list(row = c(2910L, 
35958L), col = c("how_unwell", "how_unwell"), expected = c("a double", 
"a double"), actual = c("How Unwell", "How Unwell"), file = c("'/Users/gabrielburcea/Rprojects/data/data_lev_categorical_no_sev.csv'", 
"'/Users/gabrielburcea/Rprojects/data/data_lev_categorical_no_sev.csv'"
)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"
)))
然后，我使用逐步，向前的方法建立逻辑回归模型。 

null_model <- glm(shortness_breath ~ 1, data = train, family = "binomial")

fm_shortness_breath <- glm(shortness_breath ~., data = train, family = "binomial")

stepmodel <- step(null_model, scope = list(lower = null_model, upper = fm_shortness_breath), direction = "forward")
然后，我得到摘要模型，并将预测结果存储在源数据框中。 

summary(stepmodel)

validate$pred <- predict(stepmodel, validate, type = "response")

validate$real <- validate$shortness_breath

train$pred <- predict(stepmodel, train, type = "response")
train$real <- train$shortness_breath
然后我可以毫无问题地绘制我的ROC曲线：

plot.roc(validate$real, validate$pred, col = "red", main = "ROC Validation Set", percent = TRUE, print.auc = TRUE)
但是，当我尝试获取混淆矩阵时，这就是我得到错误的地方。但这是我的代码：

cm_stepmodel <- confusionMatrix(stepmodel, validate)
然后出现错误：

Error: `data` and `reference` should be factors with the same levels.
带有显示回溯：

3.
stop("`data` and `reference` should be factors with the same levels.", call. = FALSE)
2.
confusionMatrix.default(stepmodel, validate)
1.
confusionMatrix(stepmodel, validate)
我根本看不出问题所在。并尝试了其他几种选择，但没有用。我已逐步复制了我所采取的确切方法。而且我没有得到答案。另外，我也用RMarkdown，脱字符号和R标记了此问题，以防万一。 

此外，使用的库为：

library(tidyverse)
library(conflicted)
library(tidymodels)
library(ggrepel)
library(corrplot)
library(dplyr)
library(corrr) 
library(themis)
library(rsample)
library(caret)
library(forcats)
library(rcompanion)
library(MASS)
library(pROC)
library(ROCR)
library(data.table)

我已经看到许多有关此特定错误的答案。对于我的特定问题，我尚未找到任何答案。因此，我的问题是我该怎么做：...

Answer 1

[尝试将您的预测概率转换为标签，然后在其上运行confusionMatrix：