How can i calculate training and testing time of a model using classification learner app?

Question

VIJENDRA 2016-7-30

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/297797-how-can-i-calculate-training-and-testing-time-of-a-model-using-classification-learner-app

评论： Paul Ho 2021-2-25

I am using wine dataset for experiment

    % load wine_dataset
    % [dummy, Target] = max(wineTargets);
    % wineDataset = [wineInputs; Target];

I imported wineDataset matrix in classification learner app and train the data using Linear SVM and Quadratic SVM. How can I calculate training and testing time taken by model?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Image Analyst 2016-7-30

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/297797-how-can-i-calculate-training-and-testing-time-of-a-model-using-classification-learner-app#answer_230307

Export the code, and then use tic and toc.

3 个评论
显示 1更早的评论隐藏 1更早的评论

VIJENDRA 2016-7-30

在 MATLAB Online 中打开

function [trainedClassifier, validationAccuracy] = trainClassifier(datasetTable)
% Convert input to table
datasetTable = table(datasetTable');
datasetTable.Properties.VariableNames = {'row'};
% Split matrices in the input table into vectors
datasetTable.row_1 = datasetTable.row(:,1);
datasetTable.row_2 = datasetTable.row(:,2);
datasetTable.row_3 = datasetTable.row(:,3);
datasetTable.row_4 = datasetTable.row(:,4);
datasetTable.row_5 = datasetTable.row(:,5);
datasetTable.row_6 = datasetTable.row(:,6);
datasetTable.row_7 = datasetTable.row(:,7);
datasetTable.row_8 = datasetTable.row(:,8);
datasetTable.row_9 = datasetTable.row(:,9);
datasetTable.row_10 = datasetTable.row(:,10);
datasetTable.row_11 = datasetTable.row(:,11);
datasetTable.row_12 = datasetTable.row(:,12);
datasetTable.row_13 = datasetTable.row(:,13);
datasetTable.row_14 = datasetTable.row(:,14);
datasetTable.row = [];
% Extract predictors and response
predictorNames = {'row_1', 'row_2', 'row_3', 'row_4', 'row_5', 'row_6', 'row_7', 'row_8', 'row_9', 'row_10', 'row_11', 'row_12', 'row_13'};
predictors = datasetTable(:,predictorNames);
predictors = table2array(varfun(@double, predictors));
response = datasetTable.row_14;
% Train a classifier
template = templateSVM('KernelFunction', 'linear', 'PolynomialOrder', [], 'KernelScale', 'auto', 'BoxConstraint', 1, 'Standardize', 1);
trainedClassifier = fitcecoc(predictors, response, 'Learners', template, 'Coding', 'onevsone', 'PredictorNames', {'row_1' 'row_2' 'row_3' 'row_4' 'row_5' 'row_6' 'row_7' 'row_8' 'row_9' 'row_10' 'row_11' 'row_12' 'row_13'}, 'ResponseName', 'row_14', 'ClassNames', [1 2 3]);
% Perform cross-validation
partitionedModel = crossval(trainedClassifier, 'KFold', 5);
% Compute validation accuracy
validationAccuracy = 1 - kfoldLoss(partitionedModel, 'LossFun', 'ClassifError');
%%Uncomment this section to compute validation predictions and scores:
% % Compute validation predictions and scores
% [validationPredictions, validationScores] = kfoldPredict(partitionedModel);

Where should i put tic and toc as 'fitcecoc' function using all data i.e. 178 observations to train the model?

Image Analyst 2016-7-30

Put tic where you want to start the stop watch, and put toc where you want to stop the stop watch and discover the elapsed time.

Paul Ho 2021-2-25

I know this is an old post, but I can't seem to find where I can export MATLAB code from the classification learner app. (Of course I can just copy, paste and adapt the above, but it would be nice to know how it was generated)

If anyone could link me to any useful articles/ docs I would appreciate that too.

请先登录，再进行评论。