public void TestRealValuedWeightsVsRepeatWeighting()
{
var rvfes1 = new RealValueFileEventStream(Tests.OpenFile("opennlp/data/maxent/real-valued-weights-training-data.txt"));
var rvfes2 = new FileEventStream(Tests.OpenFile("opennlp/data/maxent/repeat-weighting-training-data.txt"));
var realModel = GIS.TrainModel(100, new OnePassRealValueDataIndexer(rvfes1, 1));
var repeatModel = GIS.TrainModel(100, new OnePassRealValueDataIndexer(rvfes2, 1));
rvfes1.Dispose();
rvfes2.Dispose();
Assert.NotNull(realModel);
Assert.NotNull(repeatModel);
var features2Classify = new[] { "feature2", "feature5" };
var realResults = realModel.Eval(features2Classify);
var repeatResults = repeatModel.Eval(features2Classify);
Assert.AreEqual(realResults.Length, repeatResults.Length);
for (var i = 0; i < realResults.Length; i++)
{
Assert.AreEqual(realResults[i], repeatResults[i], 0.01f);
}
features2Classify = new[] { "feature1", "feature2", "feature3", "feature4", "feature5" };
realResults = realModel.Eval(features2Classify, new[] { 5.5f, 6.1f, 9.1f, 4.0f, 1.8f });
repeatResults = repeatModel.Eval(features2Classify, new[] { 5.5f, 6.1f, 9.1f, 4.0f, 1.8f });
Assert.AreEqual(realResults.Length, repeatResults.Length);
for (var i = 0; i < realResults.Length; i++)
{
Assert.AreEqual(realResults[i], repeatResults[i], 0.01f);
}
}
public void TestScaleResults()
{
const string smallValues = "predA=0.1 predB=0.2 A\n" + "predB=0.3 predA=0.1 B\n";
const string largeValues = "predA=10 predB=20 A\n" + "predB=30 predA=10 B\n";
const string smallTest = "predA=0.2 predB=0.2";
const string largeTest = "predA=20 predB=20";
var smallReader = new StringReader(smallValues);
var smallEventStream = new RealBasicEventStream(new PlainTextByLineStream(smallReader));
var smallModel = GIS.TrainModel(100, new OnePassRealValueDataIndexer(smallEventStream, 0), false);
var contexts = smallTest.Split(new[] { ' ' }, StringSplitOptions.RemoveEmptyEntries);
var values = RealValueFileEventStream.ParseContexts(contexts);
var smallResults = smallModel.Eval(contexts, values);
var smallResultString = smallModel.GetAllOutcomes(smallResults);
Console.Out.WriteLine("smallResults: " + smallResultString);
var largeReader = new StringReader(largeValues);
var largeEventStream = new RealBasicEventStream(new PlainTextByLineStream(largeReader));
var largeModel = GIS.TrainModel(100, new OnePassRealValueDataIndexer(largeEventStream, 0), false);
contexts = largeTest.Split(new[] { ' ' }, StringSplitOptions.RemoveEmptyEntries);
values = RealValueFileEventStream.ParseContexts(contexts);
var largeResults = largeModel.Eval(contexts, values);
var largeResultString = smallModel.GetAllOutcomes(largeResults);
Console.Out.WriteLine("largeResults: " + largeResultString);
Assert.AreEqual(smallResults.Length, largeResults.Length);
for (var i = 0; i < smallResults.Length; i++)
{
/*
* System.out.println(string.format(
* "classify with smallModel: %1$s = %2$f", smallModel.getOutcome(i),
* smallResults[i]));
* System.out.println(string.format(
* "classify with largeModel: %1$s = %2$f", largeModel.getOutcome(i),
* largeResults[i])); */
Assert.AreEqual(smallResults[i], largeResults[i], 0.01f);
}
}
