正如 Shane 所说，Weka 可以很容易地从 C# 中使用，使用 IKVM 和一些“胶水代码”。按照weka page的教程创建weka的'.Net版本'，然后你可以尝试运行以下测试：
[Fact]
public void BuildAndClassify()
{
var classifier = BuildClassifier();
AssertCanClassify(classifier);
}
[Fact]
public void DeserializeAndClassify()
{
BuildClassifier().Serialize("test.weka");
var classifier = Classifier.Deserialize<LinearRegression>("test.weka");
AssertCanClassify(classifier);
}
private static void AssertCanClassify(LinearRegression classifier)
{
var result = classifier.Classify(-402, -1);
Assert.InRange(result, 255.8d, 255.9d);
}
private static LinearRegression BuildClassifier()
{
var trainingSet = new TrainingSet("attribute1", "attribute2", "class")
.AddExample(-173, 3, -31)
.AddExample(-901, 1, 807)
.AddExample(-901, 1, 807)
.AddExample(-94, -2, -86);
return Classifier.Build<LinearRegression>(trainingSet);
}
第一个测试展示了如何构建分类器并使用它对新示例进行分类，第二个测试展示了如何使用文件中的持久分类器对示例进行分类。如果您需要太支持离散属性，则需要进行一些修改。上面的代码使用了 2 个辅助类：
public class TrainingSet
{
private readonly List<string> _attributes = new List<string>();
private readonly List<List<object>> _examples = new List<List<object>>();
public TrainingSet(params string[] attributes)
{
_attributes.AddRange(attributes);
}
public int AttributesCount
{
get { return _attributes.Count; }
}
public int ExamplesCount
{
get { return _examples.Count; }
}
public TrainingSet AddExample(params object[] example)
{
if (example.Length != _attributes.Count)
{
throw new InvalidOperationException(
String.Format("Invalid number of elements in example. Should be {0}, was {1}.", _attributes.Count,
_examples.Count));
}
_examples.Add(new List<object>(example));
return this;
}
public static implicit operator Instances(TrainingSet trainingSet)
{
var attributes = trainingSet._attributes.Select(x => new Attribute(x)).ToArray();
var featureVector = new FastVector(trainingSet.AttributesCount);
foreach (var attribute in attributes)
{
featureVector.addElement(attribute);
}
var instances = new Instances("Rel", featureVector, trainingSet.ExamplesCount);
instances.setClassIndex(trainingSet.AttributesCount - 1);
foreach (var example in trainingSet._examples)
{
var instance = new Instance(trainingSet.AttributesCount);
for (var i = 0; i < example.Count; i++)
{
instance.setValue(attributes[i], Convert.ToDouble(example[i]));
}
instances.add(instance);
}
return instances;
}
}
public static class Classifier
{
public static TClassifier Build<TClassifier>(TrainingSet trainingSet)
where TClassifier : weka.classifiers.Classifier, new()
{
var classifier = new TClassifier();
classifier.buildClassifier(trainingSet);
return classifier;
}
public static TClassifier Deserialize<TClassifier>(string filename)
{
return (TClassifier)SerializationHelper.read(filename);
}
public static void Serialize(this weka.classifiers.Classifier classifier, string filename)
{
SerializationHelper.write(filename, classifier);
}
public static double Classify(this weka.classifiers.Classifier classifier, params object[] example)
{
// instance lenght + 1, because class variable is not included in example
var instance = new Instance(example.Length + 1);
for (int i = 0; i < example.Length; i++)
{
instance.setValue(i, Convert.ToDouble(example[i]));
}
return classifier.classifyInstance(instance);
}
}