Error: `data` and `reference` should be factors with the same levels. Confusion matrix for Logistic Regression
Error: `data` and `reference` should be factors with the same levels. Confusion matrix for Logistic Regression
关于这个特定错误，我已经看到了很多答案。我还没有找到任何关于我的特定问题的具体答案。所以，我的问题
我就是这样做的：
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"
)))
我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)
为了让您轻松找到问题，我也提供了 dput(head(train)) 和 dput(head(validate))
训练数据集：
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，我用逐步的前向方法建立了我的逻辑回归模型。
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")
然后我得到我的摘要模型并将预测存储在源数据框中。
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
然后我毫无问题地绘制了我的 ROC 曲线：
plot.roc(validate$real, validate$pred, col = "red", main = "ROC Validation Set", percent = TRUE, print.auc = TRUE)
然而，当我试图得到我的混淆矩阵时，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，错误就来了：
Error: `data` and `reference` should be factors with the same levels.
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。我已经逐步复制了我正在采取的确切方法。我没有得到答案。另外，为了以防万一，我也用 RMarkdown 标记了这个问题，连同插入符号和 R。
此外，使用的库是：
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)
尝试将您的预测概率转换为标签，然后运行您的混淆矩阵：
validate$pred <- predict(stepmodel, validate, type = "response")
validate$pred_label <- as.factor(ifelse(validate$pred >= 0.5, "Yes", "No"))
confusionMatrix(validate$real, validate$pred) # Error
confusionMatrix(validate$real, validate$pred_label) # This will work
检查您是否在 validate$pred_label 语句中正确分配了原始数据集中的标签。
我不是特别熟悉 confusionMatrix，但一般的想法是您对标签进行预测并与数据的实际标签进行比较。它抛出了一个错误，因为您正在将标签与概率进行比较——您需要分配标签。如果我在上面犯了概念错误或编码错误，请纠正我。
关于这个特定错误，我已经看到了很多答案。我还没有找到任何关于我的特定问题的具体答案。所以，我的问题
我就是这样做的：
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"
)))
我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)
为了让您轻松找到问题，我也提供了 dput(head(train)) 和 dput(head(validate))
训练数据集：
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，我用逐步的前向方法建立了我的逻辑回归模型。
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")
然后我得到我的摘要模型并将预测存储在源数据框中。
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
然后我毫无问题地绘制了我的 ROC 曲线：
plot.roc(validate$real, validate$pred, col = "red", main = "ROC Validation Set", percent = TRUE, print.auc = TRUE)
然而，当我试图得到我的混淆矩阵时，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，错误就来了：
Error: `data` and `reference` should be factors with the same levels.
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。我已经逐步复制了我正在采取的确切方法。我没有得到答案。另外，为了以防万一，我也用 RMarkdown 标记了这个问题，连同插入符号和 R。
此外，使用的库是：
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)
尝试将您的预测概率转换为标签，然后运行您的混淆矩阵：
validate$pred <- predict(stepmodel, validate, type = "response")
validate$pred_label <- as.factor(ifelse(validate$pred >= 0.5, "Yes", "No"))
confusionMatrix(validate$real, validate$pred) # Error
confusionMatrix(validate$real, validate$pred_label) # This will work
检查您是否在 validate$pred_label 语句中正确分配了原始数据集中的标签。
我不是特别熟悉 confusionMatrix，但一般的想法是您对标签进行预测并与数据的实际标签进行比较。它抛出了一个错误，因为您正在将标签与概率进行比较——您需要分配标签。如果我在上面犯了概念错误或编码错误，请纠正我。