KNN Class Prediction: Evaluate Existing Classifier

To evaluate an existing k-nearest-neighbors (KNN) classifier, run the KNN module with the classifier (model) file and a test data set.

Before you begin

Evaluating an existing classifier requires:

A *.knn.model file that contains the KNN classifier.
Example file: all_aml_train.preprocessed.knn.model.odf.
A gene expression data set against which to test the classifier:
- GCT or RES file that contains gene expression data.
  Example file: all_aml_test.gct.
- CLS file that identifies the class of each sample in the gene expression data.
  Example file: all_aml_test.cls.
learn more:
file formats

Step 1: KNN

To test a previously built KNN classifier, run the KNN module. Specify the classifier (*.knn.model) and the test data set. The module creates a prediction results file (*.pred.odf) that assesses the accuracy of the predictor.

learn more:
KNN

Step 2: View results

To view the prediction results file (*.pred.odf), use the PredictionResultsViewer module. The viewer lists each sample with its actual and predicted class.

Considerations

The PredictionResultsViewer provides an absolute error rate (incorrect cases/total cases) and an ROC error rate (fraction of true positives versus the fraction of false positives). Use the ROC error rate for comparing results across data sets.

learn more:
PredictionResultsViewer