"Error: Matrix must have equal dimensions" despite seemingly equal dimensions-CodePudding

pred <- predict(fit, x, type="response", s=cv$lambda.min)

confusion_matrix <- confusionMatrix(data = pred, reference = testXsp)

Error in confusionMatrix.matrix(data = pred, reference = testXsp) : matrix must have equal dimensions

dim(pred)
[1] 751864 1

dim(testXsp)
[1] 751864 1

dim(testXsp) == dim(pred)
[1] TRUE TRUE

The dimensions seem to be the same, then why am I getting this error message?

CodePudding user response：

confusionMatrix argument data must be square if it is a matrix.

> caret:::confusionMatrix.matrix
function (data, positive = NULL, prevalence = NULL, mode = "sens_spec", 
    ...) 
{
    if (length(unique(dim(data))) != 1) {
        stop("matrix must have equal dimensions")
    }
    classTable <- as.table(data, ...)
    confusionMatrix(classTable, positive, prevalence = prevalence, 
        mode = mode)
}
<bytecode: 0x126452f88>
<environment: namespace:caret>

Note that the method for class matrix does not even take a reference argument. It is the default method that uses reference. Perhaps you should review the help page for confusionMatrix?

CodePudding user response：

One possibility here is that there are one or more NA values contained in your prediction matrix. Try using the following command:

    na.omit(pred)

Afterwards, rerun the above code. If this does not work, please post the package you are using to fit your model. This will allow for a more detailed solution!

Best wishes, -Matt