public void TrainAndPredictIrisModelWithStringLabelTest()
{
string dataPath = GetDataPath("iris.data");
var pipeline = new LearningPipeline();
pipeline.Add(new TextLoader(dataPath).CreateFrom <IrisDataWithStringLabel>(useHeader: false, separator: ','));
pipeline.Add(new Dictionarizer("Label")); // "IrisPlantType" is used as "Label" because of column attribute name on the field.
pipeline.Add(new ColumnConcatenator(outputColumn: "Features",
"SepalLength", "SepalWidth", "PetalLength", "PetalWidth"));
pipeline.Add(new StochasticDualCoordinateAscentClassifier());
PredictionModel <IrisDataWithStringLabel, IrisPrediction> model = pipeline.Train <IrisDataWithStringLabel, IrisPrediction>();
string[] scoreLabels;
model.TryGetScoreLabelNames(out scoreLabels);
Assert.NotNull(scoreLabels);
Assert.Equal(3, scoreLabels.Length);
Assert.Equal("Iris-setosa", scoreLabels[0]);
Assert.Equal("Iris-versicolor", scoreLabels[1]);
Assert.Equal("Iris-virginica", scoreLabels[2]);
IrisPrediction prediction = model.Predict(new IrisDataWithStringLabel()
{
SepalLength = 3.3f,
SepalWidth = 1.6f,
PetalLength = 0.2f,
PetalWidth = 5.1f,
});
Assert.Equal(1, prediction.PredictedLabels[0], 2);
Assert.Equal(0, prediction.PredictedLabels[1], 2);
Assert.Equal(0, prediction.PredictedLabels[2], 2);
prediction = model.Predict(new IrisDataWithStringLabel()
{
SepalLength = 3.1f,
SepalWidth = 5.5f,
PetalLength = 2.2f,
PetalWidth = 6.4f,
});
Assert.Equal(0, prediction.PredictedLabels[0], 2);
Assert.Equal(0, prediction.PredictedLabels[1], 2);
Assert.Equal(1, prediction.PredictedLabels[2], 2);
prediction = model.Predict(new IrisDataWithStringLabel()
{
SepalLength = 3.1f,
SepalWidth = 2.5f,
PetalLength = 1.2f,
PetalWidth = 4.4f,
});
Assert.Equal(.2, prediction.PredictedLabels[0], 1);
Assert.Equal(.8, prediction.PredictedLabels[1], 1);
Assert.Equal(0, prediction.PredictedLabels[2], 2);
// Note: Testing against the same data set as a simple way to test evaluation.
// This isn't appropriate in real-world scenarios.
string testDataPath = GetDataPath("iris.data");
var testData = new TextLoader(testDataPath).CreateFrom <IrisDataWithStringLabel>(useHeader: false, separator: ',');
var evaluator = new ClassificationEvaluator();
evaluator.OutputTopKAcc = 3;
ClassificationMetrics metrics = evaluator.Evaluate(model, testData);
Assert.Equal(.98, metrics.AccuracyMacro);
Assert.Equal(.98, metrics.AccuracyMicro, 2);
Assert.Equal(.06, metrics.LogLoss, 2);
Assert.InRange(metrics.LogLossReduction, 94, 96);
Assert.Equal(1, metrics.TopKAccuracy);
Assert.Equal(3, metrics.PerClassLogLoss.Length);
Assert.Equal(0, metrics.PerClassLogLoss[0], 1);
Assert.Equal(.1, metrics.PerClassLogLoss[1], 1);
Assert.Equal(.1, metrics.PerClassLogLoss[2], 1);
ConfusionMatrix matrix = metrics.ConfusionMatrix;
Assert.Equal(3, matrix.Order);
Assert.Equal(3, matrix.ClassNames.Count);
Assert.Equal("Iris-setosa", matrix.ClassNames[0]);
Assert.Equal("Iris-versicolor", matrix.ClassNames[1]);
Assert.Equal("Iris-virginica", matrix.ClassNames[2]);
Assert.Equal(50, matrix[0, 0]);
Assert.Equal(50, matrix["Iris-setosa", "Iris-setosa"]);
Assert.Equal(0, matrix[0, 1]);
Assert.Equal(0, matrix["Iris-setosa", "Iris-versicolor"]);
Assert.Equal(0, matrix[0, 2]);
Assert.Equal(0, matrix["Iris-setosa", "Iris-virginica"]);
Assert.Equal(0, matrix[1, 0]);
Assert.Equal(0, matrix["Iris-versicolor", "Iris-setosa"]);
Assert.Equal(48, matrix[1, 1]);
Assert.Equal(48, matrix["Iris-versicolor", "Iris-versicolor"]);
Assert.Equal(2, matrix[1, 2]);
Assert.Equal(2, matrix["Iris-versicolor", "Iris-virginica"]);
Assert.Equal(0, matrix[2, 0]);
Assert.Equal(0, matrix["Iris-virginica", "Iris-setosa"]);
Assert.Equal(1, matrix[2, 1]);
Assert.Equal(1, matrix["Iris-virginica", "Iris-versicolor"]);
Assert.Equal(49, matrix[2, 2]);
Assert.Equal(49, matrix["Iris-virginica", "Iris-virginica"]);
}
