how can I convert knnclassify to fitcknn

I have a script from a past graduate student that needs to be updated! i dont know matlab!

How do I swtich from knnclassify to fitcknn?

Answer 1

[Raunak Gupta]

Hi,

You can replace the bottommost line of the code that is

class = knnclassify(TestingMatrix,SCORE,group,8,'euclidean','nearest'); 

With the following code

Mdl = fitcknn(SCORE,group,'Distance','euclidean','NumNeighbors',8,'Standardize',1,'BreakTies','nearest'); 
class = predict(Mdl,TestingMatrix); 

For more information or insights for the functions you may look to the following documentations.

knnclassify , fitcknn , predict

[Rachel Parise]

Life saver! thank you so much!

[Frisda Sianipar]

@Raunak Gupta i have an error too sir about knn. Could you help me pleae?

This is the code :

x=readtable("datatraining.xlsx");
latih=x;
group=latih(:,3);
latih = [latih(:,1) latih(:,2)];
for i = 1 : 80
    y=readtable("datatesting.xlsx");
    sampel = y;
    test = [sampel(:,1) sampel(:,2)];
%sampel = [2.6136  0.1284 1.3017  -0.8089  0.0441  -0,2084];
    hasil=knnclassify(test,latih,group);
    Mdl=fitcknn(group,'Distance','euclidean','NumNeighbors',8,'Standardize',1,'BreakTies','nearest');
    hasil = predict(Mdl,latih);
end
nama = "hasil KNN.xlsx";
hasil = [sampel(:,1) sampel(:,2) sampel(:,3) hasil];
xlswrite(nama,hasil);

the error i got :

Error using knnclassify (line 79)
'knnclassify' has been removed. Use 'fitcknn' to fit
a KNN classification model and classify data using
'ClassificationKNN.predict'.

Error in KNN2 (line 10)
    hasil=knnclassify(test,latih,group);

[Walter Roberson]

Remove the line

    hasil=knnclassify(test,latih,group);

[Frisda Sianipar]

I've removed it, sir, and here are the results. and i got an error too sir

[Walter Roberson]

Please show the complete error message.

I checked, and the options you are using were all supported in your release, so I need the rest of the error.

[Frisda Sianipar]

Ok sir, this is the complete error messege.

Warning: Variable names were modified to make them valid MATLAB identifiers. The original names are saved in
the VariableDescriptions property. 
Warning: Variable names were modified to make them valid MATLAB identifiers. The original names are saved in
the VariableDescriptions property. 
Error using classreg.learning.internal.table2FitMatrix (line 83)
A table used as a response must contain exactly one variable.

Error in classreg.learning.classif.FullClassificationModel.prepareData (line 471)
            [X,Y,vrange,wastable,varargin] = classreg.learning.internal.table2FitMatrix(X,Y,varargin{:});

Error in ClassificationKNN.prepareData (line 878)
                [e-mail](X,Y,varargin{:},'OrdinalIsCategorical',true);
                
Error in classreg.learning.FitTemplate/fit (line 213)
                    this.PrepareData(X,Y,this.BaseFitObjectArgs{:});

Error in ClassificationKNN.fit (line 863)
            this = fit(temp,X,Y);

Error in fitcknn (line 261)
    this = ClassificationKNN.fit(X,Y,RemainingArgs{:});

Error in KNNPleaseFix (line 11)
   Mdl = fitcknn(test,latih,'NumNeighbors',5,'Standardize',1);
   
   
   
   
   

[Walter Roberson]

x = readtable("https://www.mathworks.com/matlabcentral/answers/uploaded_files/600525/datatraining.xlsx");
y = readtable("https://www.mathworks.com/matlabcentral/answers/uploaded_files/600520/datatesting.xlsx");

traindata = x{:,2};
traingroup = x{:,3};
testdata = y{:,2};
testgroup = y{:,3};

Mdl = fitcknn(traindata, traingroup,'Distance','euclidean','NumNeighbors',8,'Standardize',1,'BreakTies','nearest');
hasil = predict(Mdl, testdata);
nama = "hasil KNN.xlsx";
y.hasil = hasil;
writetable(y, nama)

does_it_match = strcmp(hasil, testgroup);
correct_percent = mean(does_it_match) * 100

correct_percent = 73.7500