Main Content

Check Classifier Performance Using Test Set in Classification Learner App

This example shows how to train multiple models in Classification Learner, and determine the best-performing models based on their validation accuracy. Check the test accuracy for the best-performing models trained on the full data set, including training and validation data.

  1. In the MATLAB® Command Window, load the ionosphere data set, and create a table containing the data. Separate the table into training and test sets.

    load ionosphere
    tbl = array2table(X);
    tbl.Y = Y;
    
    rng("default") % For reproducibility of the data split
    partition = cvpartition(Y,"Holdout",0.15);
    idxTrain = training(partition); % Indices for the training set
    tblTrain = tbl(idxTrain,:);
    tblTest = tbl(~idxTrain,:);

    Alternatively, you can create a test set later on when you import data into the app. For more information, see (optional) Reserve Data for Testing.

  2. Open Classification Learner. Click the Apps tab, and then click the arrow at the right of the Apps section to open the apps gallery. In the Machine Learning and Deep Learning group, click Classification Learner.

  3. On the Classification Learner tab, in the File section, click New Session and select From Workspace.

  4. In the New Session from Workspace dialog box, select the tblTrain table from the Data Set Variable list.

    As shown in the dialog box, the app selects the response and predictor variables. The default response variable is Y. To protect against overfitting, the default validation option is 5-fold cross-validation. For this example, do not change the default settings.

    New Session from Workspace dialog box

  5. To accept the default options and continue, click Start Session.

  6. Train all preset models. On the Classification Learner tab, in the Models section, click the arrow to open the gallery. In the Get Started group, click All. In the Train section, click Train All and select Train All. The app trains one of each preset model type, along with the default fine tree model, and displays the models in the Models pane.

    Note

    • If you have Parallel Computing Toolbox™, then the app has the Use Parallel button toggled on by default. After you click Train All and select Train All or Train Selected, the app opens a parallel pool of workers. During this time, you cannot interact with the software. After the pool opens, you can continue to interact with the app while models train in parallel.

    • If you do not have Parallel Computing Toolbox, then the app has the Use Background Training check box in the Train All menu selected by default. After you click to train models, the app opens a background pool. After the pool opens, you can continue to interact with the app while models train in the background.

  7. Sort the trained models based on the validation accuracy. In the Models pane, open the Sort by list and select Accuracy (Validation).

  8. In the Models pane, click the star icons next to the three models with the highest validation accuracy. The app highlights the highest validation accuracy by outlining it in a box. In this example, the trained Medium Gaussian SVM model has the highest validation accuracy.

    Validation confusion matrix of the ionosphere data modeled by a fine tree model

    The app displays a validation confusion matrix for the second fine tree model (model 2.1). Blue values indicate correct classifications, and red values indicate incorrect classifications. The Models pane on the left shows the validation accuracy for each model.

    Note

    Validation introduces some randomness into the results. Your model validation results can vary from the results shown in this example.

  9. Check the test set performance of the best-performing models. Begin by importing test data into the app.

    On the Classification Learner tab, in the Test section, click Test Data and select From Workspace.

  10. In the Import Test Data dialog box, select the tblTest table from the Test Data Set Variable list.

    As shown in the dialog box, the app identifies the response and predictor variables.

    Import Test Data dialog box

  11. Click Import.

  12. Compute the accuracy of the best preset models on the tblTest data. For convenience, compute the test set accuracy for all models at once. On the Classification Learner tab, in the Test section, click Test All and select Test All. The app computes the test set performance of the model trained on the full data set, including training and validation data.

  13. Sort the models based on the test set accuracy. In the Models pane, open the Sort by list and select Accuracy (Test). The app still outlines the metric for the model with the highest validation accuracy, despite displaying the test accuracy.

  14. Visually check the test set performance of the models. For each starred model, select the model in the Models pane. On the Classification Learner tab, in the Plots section, click the arrow to open the gallery, and then click Confusion Matrix (Test) in the Test Results group.

  15. Rearrange the layout of the plots to better compare them. First, close the summary and plot tabs for Model 1 and Model 2.1. Then, click the Document Actions arrow located to the far right of the model plot tabs. Select the Tile All option and specify a 1-by-3 layout. Click the Hide plot options button at the top right of the plots to make more room for the plots.

    In this example, the trained Medium Gaussian SVM model remains one of the best-performing models on the test set data.

    Test set confusion matrices for the starred models

    To return to the original layout, you can click the Layout button in the Plots section and select Single model (Default).

  16. Compare the validation and test accuracy for the trained Medium Gaussian SVM model. In the Models pane, double-click the model. In the model Summary tab, compare the Accuracy (Validation) value under Training Results to the Accuracy (Test) value under Test Results. In this example, the validation accuracy is higher than the test accuracy, which indicates that the validation accuracy is perhaps overestimating the performance of this model.

Related Topics