Ошибка в таблице (данные, ссылка, dnn = dnn, ...): все аргументы должны иметь одинаковую длину при запуске confusionMatrix с кареткой в ​​R

Question

У меня проблема с запуском confusionMatrix.

вот что я делаю:

rf <- caret::train(tested ~., 
                               data = training_data, 
                               method = "rf",
                               trControl = ctrlInside,
                               metric = "ROC", 
                               na.action = na.exclude)

rf

После того, как я получу свою модель, я делаю следующий шаг:

evalResult.rf <- predict(rf, testing_data, type = "prob")
predict_rf <- as.factor(ifelse(evalResult.rf <0.5, "positive", "negative"))

И тут я начинаю путаться матрица.

cm_rf_forest <- confusionMatrix(predict_rf, testing_data$tested, "positive") 

И ошибка возникает после того, как я применяю confusionMatrix:

Error in table(data, reference, dnn = dnn, ...) : 
  all arguments must have the same length

Тем не менее, я даю вам биты своих данных.

данные поезда:

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")

и вот мои 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")

Кроме того, я выполняю класс балансировки сглаживания на подвыборке в ctrInside.

Это моя функция сглаживания:

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)

И ctrlInside это:

ctrlInside <- trainControl(method = "repeatedcv", 
                           number = 10,
                           repeats = 5,
                           summaryFunction = twoClassSummary,
                           classProbs = TRUE,
                           savePredictions = TRUE, 
                           search = "grid",
                           sampling = smotest)

Эти функции даны только для того, чтобы вы имели представление о том, что я делаю в целом. Есть ли причина, по которой это происходит?

Answer 1

Вы можете использовать complete.cases для предсказания только тех, у которых нет nas, также вы должны работать с матрицей, как я покажу ниже. Используя пример набора данных, я делаю 10 переменных в столбце NA и тренируюсь:

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)

Выполните результат оценки, и вы увидите, что я получаю ту же ошибку:

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

Итак, есть два источника ошибок: 1. У вас есть NA, и они не могут это предсказать, и, во-вторых, evalResult.rf возвращает матрицу вероятностей, первый столбец - это вероятность отрицательного класса, второй - положительный:

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

Чтобы получить классы, вы должны получить столбец с максимальным значением для каждой строки и вернуть соответствующее имя столбца, которым является класс:

colnames(evalResult.rf)[max.col(evalResult.rf)]

Теперь мы делаем:

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