我在运行混淆矩阵时遇到了一个问题。
我是这样做的。
rf <- caret::train(tested ~.,
data = training_data,
method = "rf",
trControl = ctrlInside,
metric = "ROC",
na.action = na.exclude)
rf
在我得到我的模型后,这是我的下一步。
evalResult.rf <- predict(rf, testing_data, type = "prob")
predict_rf <- as.factor(ifelse(evalResult.rf <0.5, "positive", "negative"))
然后我运行我的混淆矩阵。
cm_rf_forest <- confusionMatrix(predict_rf, testing_data$tested, "positive")
而错误是在我应用混淆矩阵之后出现的。
Error in table(data, reference, dnn = dnn, ...) :
all arguments must have the same length
尽管如此,我还是给你一些我的数据:
训练数据。
structure(list(tested = structure(c(1L, 1L, 1L, 1L, 1L,
1L), .Label = c("negative", "positive"), class = "factor"), Gender = structure(c(2L,
2L, 1L, 1L, 2L, 2L), .Label = c("Female", "Male", "Other"), class = "factor"),
Age = c(63, 23, 28, 40, 31, 60), number_days_symptoms = c(1,
1, 16, 1, 14, 1), care_home_worker = structure(c(1L, 2L,
1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
health_care_worker = structure(c(1L, 1L, 1L, 1L, 2L, 1L), .Label = c("No",
"Yes"), class = "factor"), how_unwell = c(1, 1, 6, 4, 2,
1), self_diagnosis = structure(c(1L, 1L, 2L, 1L, 2L, 1L), .Label = c("No",
"Yes"), class = "factor"), chills = structure(c(1L, 1L, 2L,
1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
cough = structure(c(1L, 1L, 2L, 2L, 1L, 1L), .Label = c("No",
"Yes"), class = "factor"), diarrhoea = structure(c(1L, 1L,
1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
fatigue = structure(c(1L, 2L, 2L, 2L, 2L, 1L), .Label = c("No",
"Yes"), class = "factor"), headache = structure(c(2L, 2L,
3L, 2L, 2L, 2L), .Label = c("Headcahe", "No", "Yes"), class = "factor"),
loss_smell_taste = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Yes"), class = "factor"), muscle_ache = structure(c(1L,
1L, 2L, 2L, 2L, 2L), .Label = c("No", "Yes"), class = "factor"),
nasal_congestion = structure(c(1L, 1L, 1L, 2L, 1L, 1L), .Label = c("No",
"Yes"), class = "factor"), nausea_vomiting = structure(c(1L,
1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
shortness_breath = structure(c(1L, 1L, 1L, 1L, 2L, 1L), .Label = c("No",
"Yes"), class = "factor"), sore_throat = structure(c(1L,
1L, 1L, 2L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
sputum = structure(c(1L, 1L, 2L, 2L, 1L, 1L), .Label = c("No",
"Yes"), class = "factor"), temperature = structure(c(4L,
4L, 4L, 4L, 1L, 4L), .Label = c("37.5-38", "38.1-39", "39.1-41",
"No"), 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, 2L), .Label = c("No", "Yes"), class = "factor"),
obesity = structure(c(1L, 2L, 2L, 1L, 1L, 1L), .Label = c("No",
"Yes"), class = "factor"), hypertension = structure(c(1L,
1L, 2L, 1L, 1L, 2L), .Label = c("No", "Yes"), class = "factor"),
heart_disease = structure(c(1L, 1L, 1L, 1L, 1L, 2L), .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")), row.names = c(1L,
3L, 4L, 5L, 6L, 7L), class = "data.frame")
这里是我的test_data:
structure(list(tested = structure(c(1L, 1L, 1L, 1L, 1L,
1L), .Label = c("negative", "positive"), class = "factor"), Gender = structure(c(1L,
2L, 1L, 1L, 1L, 2L), .Label = c("Female", "Male", "Other"), class = "factor"),
Age = c(19, 26, 30, 45, 40, 43), number_days_symptoms = c(20,
1, 1, 20, 14, 1), care_home_worker = structure(c(1L, 1L,
1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
health_care_worker = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Yes"), class = "factor"), how_unwell = c(7, 6, 6, 6, 6,
2), self_diagnosis = structure(c(2L, 1L, 1L, 2L, 2L, 1L), .Label = c("No",
"Yes"), class = "factor"), chills = structure(c(2L, 1L, 1L,
1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
cough = structure(c(2L, 1L, 1L, 2L, 2L, 1L), .Label = c("No",
"Yes"), class = "factor"), diarrhoea = structure(c(2L, 1L,
1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
fatigue = structure(c(2L, 1L, 1L, 2L, 2L, 1L), .Label = c("No",
"Yes"), class = "factor"), headache = structure(c(2L, 2L,
2L, 3L, 2L, 3L), .Label = c("Headcahe", "No", "Yes"), class = "factor"),
loss_smell_taste = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Yes"), class = "factor"), muscle_ache = structure(c(2L,
1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
nasal_congestion = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Yes"), class = "factor"), nausea_vomiting = structure(c(1L,
1L, 1L, 1L, 1L, 1L), .Label = c("No", "Yes"), class = "factor"),
shortness_breath = structure(c(2L, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Yes"), class = "factor"), sore_throat = structure(c(1L,
1L, 1L, 2L, 1L, 2L), .Label = c("No", "Yes"), class = "factor"),
sputum = structure(c(2L, 1L, 1L, 2L, 1L, 2L), .Label = c("No",
"Yes"), class = "factor"), temperature = structure(c(4L,
4L, 4L, 1L, 1L, 4L), .Label = c("37.5-38", "38.1-39", "39.1-41",
"No"), 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"),
obesity = 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")), row.names = c(2L,
8L, 11L, 14L, 20L, 27L), class = "data.frame")
此外,我还在ctrInside的子样本上 进行了一个smote平衡类。
这是我的smote函数。
smotest <- list(name = "SMOTE with more neighbors!",
func = function (x, y) {
115
library(DMwR)
dat <- if (is.data.frame(x)) x else as.data.frame(x)
dat$.y <- y
dat <- SMOTE(.y ~ ., data = dat, k = 3, perc.over = 100, perc.under =
200)
list(x = dat[, !grepl(".y", colnames(dat), fixed = TRUE)],
y = dat$.y) },
first = TRUE)
ctrlInside是这样的
ctrlInside <- trainControl(method = "repeatedcv",
number = 10,
repeats = 5,
summaryFunction = twoClassSummary,
classProbs = TRUE,
savePredictions = TRUE,
search = "grid",
sampling = smotest)
给出这些函数只是为了让你了解我对每个整体所做的事情。有什么原因会发生这种情况吗?
你可以使用complete.cases来预测只有那些没有na的,也必须对矩阵进行操作,我将在下面展示。使用一个例子的数据集,我使10的变量在一列NAs,并训练。
idx = sample(nrow(iris),100)
data = iris
data$Petal.Length[sample(nrow(data),10)] = NA
data$tested = factor(ifelse(data$Species=="versicolor","positive","negative"))
data = data[,-5]
training_data = data[idx,]
testing_data= data[-idx,]
rf <- caret::train(tested ~., data = training_data,
method = "rf",
trControl = ctrlInside,
metric = "ROC",
na.action = na.exclude)
做评估结果,你可以看到我得到同样的错误。
evalResult.rf <- predict(rf, testing_data, type = "prob")
predict_rf <- as.factor(ifelse(evalResult.rf <0.5, "positive", "negative"))
cm_rf_forest <- confusionMatrix(predict_rf, testing_data$tested, "positive")
Error in table(data, reference, dnn = dnn, ...) :
all arguments must have the same length
所以,有两个错误的来源,1. . 你有NAS和他们不能预测,第二,evalResult. rf返回一个概率矩阵,第一列是概率是负类,第二是后置。
head(evalResult.rf)
negative positive
3 1.000 0.000
6 1.000 0.000
9 0.948 0.052
12 1.000 0.000
13 0.976 0.024
19 0.998 0.002
为了得到类,你要做的是,得到每行最大值的那一列,然后返回相应的列名,也就是类。
colnames(evalResult.rf)[max.col(evalResult.rf)]
我们现在就这样做。
testing_data = testing_data[complete.cases(testing_data),]
evalResult.rf <- predict(rf, testing_data, type = "prob")
predict_rf <- factor(colnames(evalResult.rf)[max.col(evalResult.rf)])
cm_rf_forest <- confusionMatrix(predict_rf, testing_data$tested, "positive")
Confusion Matrix and Statistics
Reference
Prediction negative positive
negative 33 1
positive 0 11
Accuracy : 0.9778
95% CI : (0.8823, 0.9994)
No Information Rate : 0.7333
P-Value [Acc > NIR] : 1.507e-05
Kappa : 0.9416