Check for missing argument or incorrect argument data type in call to function 'predict'.

I am trying to predict values of cross-validated model using training data.But I am getting this error -

Check for missing argument or incorrect argument data type in call to function 'predict'.

The code I am using is as below -

mdlCv= fitctree(bank_Train,'y','KFold',10); %bank_Train is the training data

[label,scores] = predict(mdlCv,bank_Test); %bank_Test is the testing data

If I try to use below code then also I am getting the error

[label,scores] = predict(mdlCv.Trained{1},bank_Test);

Error using classreg.learning.internal.table2PredictMatrix>makeXMatrix (line 97)

Table variable job is not a valid predictor.

Error in classreg.learning.internal.table2PredictMatrix (line 47)

Xout = makeXMatrix(X,CategoricalPredictors,vrange,pnames);

Error in classreg.learning.classif.CompactClassificationTree/predict (line 894)

X = classreg.learning.internal.table2PredictMatrix(X,[],[],...

Answer 1

[Walter Roberson]

For cross-validated classification trees, create a classification partitioned object, https://www.mathworks.com/help/stats/classreg.learning.partition.classificationpartitionedmodel-class.html using fitctree https://www.mathworks.com/help/stats/fitctree.html#bt6cr7t-tree and use kfoldPredict https://www.mathworks.com/help/stats/classificationpartitionedmodel.kfoldpredict.html

You are using 'KFold' so you are creating a classification partitioned object and need to use kfoldPredict() instead of predict()

See also https://www.mathworks.com/matlabcentral/answers/427309-classify-requires-at-least-3-arguments#answer_445205

[Tejal Mehta]

Thanks .

If I want to predict using test data then do I have to create model on test data and then use kfoldPredict ?

I cannot directly use predict function with test_data?

Like I saw somewhere this below code works if all columns are numeric -

[label,scores] = predict(mdlCv.Trained{1},bank_Test); %bank_Test is the testing data

for me this is not working as I have got few categorical columns as well and it is throwing error stating

Error using classreg.learning.internal.table2PredictMatrix>makeXMatrix (line 97)

Table variable job is not a valid predictor.