train and test data using KNN classifier

Question

sehrish 2013-7-18

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/82522-train-and-test-data-using-knn-classifier

评论： Kathryn Hollowood 2019-3-12

HI I want to know how to train and test data using KNN classifier we cross validate data by 10 fold cross validation. there are different commands like KNNclassify or KNNclassification.Fit. Don't know how to accomplish task Plz help me Thanks

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Kathryn Hollowood 2019-3-12

This link: https://www.mathworks.com/help/stats/classification-using-nearest-neighbors.html#btap7k2

That he just shared also includes information about predicting the classification using knn. So you use the fitcknn to create the model (Mdl). So it would be like:

class = predict(Mdl, TestCase).

This should hopefully give you what you are looking for.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Shashank Prasanna 2013-7-18

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/82522-train-and-test-data-using-knn-classifier#answer_92184

Have you tried out the examples in the documentation?

http://www.mathworks.com/help/stats/classification-using-nearest-neighbors.html#btap7k2

I don't think we can help you any better than the examples in the doc. If you have specific questions then we can address that.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

sehrish 2013-7-19

编辑：sehrish 2013-7-19

在 MATLAB Online 中打开

Yes Shashank I have tried it but I could not understand where are its training and testing results? here is the code

% Classify the fisheriris data with a K-Nearest Neighbor classifier

load fisheriris

c = knnclassify(meas,meas,species,4,'euclidean','Consensus');

cp = classperf(species,c)

get(cp)

% 10-fold cross-validation on the fisheriris data using linear

% discriminant analysis and the third column as only feature for

% classification

load fisheriris

indices = crossvalind('Kfold',species,10);

cp = classperf(species); % initializes the CP object

for i = 1:10 test = (indices == i); train = ~test;

    class = classify(meas(test,3),meas(train,3),species(train));
    % updates the CP object with the current classification results
    classperf(cp,class,test)

end

cp.CorrectRate % queries for the correct classification rate

请先登录，再进行评论。

Answer 2

snehal jaipurkar 2018-1-26

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/82522-train-and-test-data-using-knn-classifier#answer_301851

Sir please reply soon.... can we use eucledian distance and hamming distance both in knn classifier at the same time??? I am working on a project where I have to classify gabor features using hamming distance and geometrical features using eucledian distance..... Is it possible sir?????