close all; clear; clc;

% Lire la base de données
load fisheriris
X = meas;    
Y = species; 
rng(10)


% Construire le modèle KNN
% MonModele = fitcknn(X,Y,'NumNeighbors',4);

rng(1)
MonModele = fitcknn(X,Y,'OptimizeHyperparameters','auto',...
    'HyperparameterOptimizationOptions',...
    struct('AcquisitionFunctionName','expected-improvement-plus'))

%MonModele= fitcknn(X,Y,'NSMethod','exhaustive','Distance','euclidean');
MonModele.NumNeighbors = 3;

% Examine the resubstitution loss, which, by default, 
% is the fraction of misclassifications from the predictions of Mdl. 
% (For nondefault cost, weights, or priors, see loss.).
rloss = resubLoss(MonModele)

% % Construct a cross-validated classifier from the model.
% MonModele_CV = crossval(MonModele,'KFold',10);
% kloss = kfoldLoss(MonModele_CV)


% Predict or test
flwr = mean(X*2); % an average flower
flwrClass = predict(MonModele,flwr)