function [trainedClassifier, validationAccuracy] = trainClassifier(trainingData)
% [trainedClassifier, validationAccuracy] = trainClassifier(trainingData)
% Returns a trained classifier and its accuracy. This code recreates the
% classification model trained in Classification Learner app. Use the
% generated code to automate training the same model with new data, or to
% learn how to programmatically train models.
%
%  Input:
%      trainingData: A table containing the same predictor and response
%       columns as those imported into the app.
%
%  Output:
%      trainedClassifier: A struct containing the trained classifier. The
%       struct contains various fields with information about the trained
%       classifier.
%
%      trainedClassifier.predictFcn: A function to make predictions on new
%       data.
%
%      validationAccuracy: A double containing the accuracy as a
%       percentage. In the app, the Models pane displays this overall
%       accuracy score for each model.
%
% Use the code to train the model with new data. To retrain your
% classifier, call the function from the command line with your original
% data or new data as the input argument trainingData.
%
% For example, to retrain a classifier trained with the original data set
% T, enter:
%   [trainedClassifier, validationAccuracy] = trainClassifier(T)
%
% To make predictions with the returned 'trainedClassifier' on new data T2,
% use
%   yfit = trainedClassifier.predictFcn(T2)
%
% T2 must be a table containing at least the same predictor columns as used
% during training. For details, enter:
%   trainedClassifier.HowToPredict

% Auto-generated by MATLAB on 21-Nov-2023 19:10:35


% Extract predictors and response
% This code processes the data into the right shape for training the
% model.
inputTable = trainingData;
predictorNames = {'a01', 'a02', 'a03', 'a04', 'a05', 'a06', 'a07', 'a08', 'a09', 'a10', 'a11', 'a12', 'a13', 'a14', 'a15', 'a16', 'a17', 'a18', 'a19', 'a20', 'a21', 'a22', 'a23', 'a24', 'a25', 'a26', 'a27', 'a28', 'a29', 'a30', 'a31', 'a32', 'a33', 'a34'};
predictors = inputTable(:, predictorNames);
response = inputTable.class;
isCategoricalPredictor = [false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false];

% Feature Ranking and Selection
% Replace Inf/-Inf values with NaN to prepare data for normalization
predictors = standardizeMissing(predictors, {Inf, -Inf});
% Normalize data for feature ranking
predictorMatrix = normalize(predictors, "DataVariable", ~isCategoricalPredictor);

% Rank features using MRMR algorithm
featureIndex = fscmrmr(...
    predictorMatrix, ...
    response);
numFeaturesToKeep = 10;
includedPredictorNames = predictors.Properties.VariableNames(featureIndex(1:numFeaturesToKeep));
predictors = predictors(:,includedPredictorNames);
isCategoricalPredictor = isCategoricalPredictor(featureIndex(1:numFeaturesToKeep));

% Train a classifier
% This code specifies all the classifier options and trains the classifier.
classificationKernel = fitckernel(...
    predictors, ...
    response, ...
    'Learner', 'svm', ...
    'NumExpansionDimensions', 'auto', ...
    'Lambda', 'auto', ...
    'KernelScale', 'auto', ...
    'IterationLimit', 1000, ...
    'ClassNames', categorical({'b'; 'g'}));

% Create the result struct with predict function
predictorExtractionFcn = @(t) t(:, predictorNames);
featureSelectionFcn = @(x) x(:,includedPredictorNames);
kernelPredictFcn = @(x) predict(classificationKernel, x);
trainedClassifier.predictFcn = @(x) kernelPredictFcn(featureSelectionFcn(predictorExtractionFcn(x)));

% Add additional fields to the result struct
trainedClassifier.RequiredVariables = {'a01', 'a02', 'a03', 'a04', 'a05', 'a06', 'a07', 'a08', 'a09', 'a10', 'a11', 'a12', 'a13', 'a14', 'a15', 'a16', 'a17', 'a18', 'a19', 'a20', 'a21', 'a22', 'a23', 'a24', 'a25', 'a26', 'a27', 'a28', 'a29', 'a30', 'a31', 'a32', 'a33', 'a34'};
trainedClassifier.ClassificationKernel = classificationKernel;
trainedClassifier.About = 'This struct is a trained model exported from Classification Learner R2022b.';
trainedClassifier.HowToPredict = sprintf('To make predictions on a new table, T, use: \n  yfit = c.predictFcn(T) \nreplacing ''c'' with the name of the variable that is this struct, e.g. ''trainedModel''. \n \nThe table, T, must contain the variables returned by: \n  c.RequiredVariables \nVariable formats (e.g. matrix/vector, datatype) must match the original training data. \nAdditional variables are ignored. \n \nFor more information, see <a href="matlab:helpview(fullfile(docroot, ''stats'', ''stats.map''), ''appclassification_exportmodeltoworkspace'')">How to predict using an exported model</a>.');

% Extract predictors and response
% This code processes the data into the right shape for training the
% model.
inputTable = trainingData;
predictorNames = {'a01', 'a02', 'a03', 'a04', 'a05', 'a06', 'a07', 'a08', 'a09', 'a10', 'a11', 'a12', 'a13', 'a14', 'a15', 'a16', 'a17', 'a18', 'a19', 'a20', 'a21', 'a22', 'a23', 'a24', 'a25', 'a26', 'a27', 'a28', 'a29', 'a30', 'a31', 'a32', 'a33', 'a34'};
predictors = inputTable(:, predictorNames);
response = inputTable.class;
isCategoricalPredictor = [false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false];

% Perform cross-validation
KFolds = 5;
cvp = cvpartition(response, 'KFold', KFolds);
% Initialize the predictions to the proper sizes
validationPredictions = response;
numObservations = size(predictors, 1);
numClasses = 2;
validationScores = NaN(numObservations, numClasses);
for fold = 1:KFolds
    trainingPredictors = predictors(cvp.training(fold), :);
    trainingResponse = response(cvp.training(fold), :);
    foldIsCategoricalPredictor = isCategoricalPredictor;

    % Feature Ranking and Selection
    % Replace Inf/-Inf values with NaN to prepare data for normalization
    trainingPredictors = standardizeMissing(trainingPredictors, {Inf, -Inf});
    % Normalize data for feature ranking
    predictorMatrix = normalize(trainingPredictors, "DataVariable", ~foldIsCategoricalPredictor);

    % Rank features using MRMR algorithm
    featureIndex = fscmrmr(...
        predictorMatrix, ...
        trainingResponse);
    numFeaturesToKeep = 10;
    includedPredictorNames = trainingPredictors.Properties.VariableNames(featureIndex(1:numFeaturesToKeep));
    trainingPredictors = trainingPredictors(:,includedPredictorNames);
    foldIsCategoricalPredictor = foldIsCategoricalPredictor(featureIndex(1:numFeaturesToKeep));

    % Train a classifier
    % This code specifies all the classifier options and trains the classifier.
    classificationKernel = fitckernel(...
        trainingPredictors, ...
        trainingResponse, ...
        'Learner', 'svm', ...
        'NumExpansionDimensions', 'auto', ...
        'Lambda', 'auto', ...
        'KernelScale', 'auto', ...
        'IterationLimit', 1000, ...
        'ClassNames', categorical({'b'; 'g'}));

    % Create the result struct with predict function
    featureSelectionFcn = @(x) x(:,includedPredictorNames);
    kernelPredictFcn = @(x) predict(classificationKernel, x);
    validationPredictFcn = @(x) kernelPredictFcn(featureSelectionFcn(x));

    % Add additional fields to the result struct

    % Compute validation predictions
    validationPredictors = predictors(cvp.test(fold), :);
    [foldPredictions, foldScores] = validationPredictFcn(validationPredictors);

    % Store predictions in the original order
    validationPredictions(cvp.test(fold), :) = foldPredictions;
    validationScores(cvp.test(fold), :) = foldScores;
end

% Compute validation accuracy
correctPredictions = (validationPredictions == response);
isMissing = ismissing(response);
correctPredictions = correctPredictions(~isMissing);
validationAccuracy = sum(correctPredictions)/length(correctPredictions);