public void SimpleExampleTest()
{
RunMTAThread(() =>
{
string dataFilename = GetDataPath(TestDatasets.msm.trainFilename);
///********* Training a model *******//
// assume data is in memory in matrix/vector form. Sparse format also supported.
Float[][] data;
Float[] labels;
// below just reads some actual data into these arrays
PredictionUtil.ReadInstancesAsArrays(dataFilename, out data, out labels);
// Create an Instances dataset.
ListInstances instances = new ListInstances();
for (int i = 0; i < data.Length; i++)
{
instances.AddInst(data[i], labels[i]);
}
instances.CopyMetadata(null);
// Create a predictor and specify some non-default settings
var sub = new SubComponent <ITrainer <Instances, IPredictor <Instance, Float> >, SignatureOldBinaryClassifierTrainer>(
"FastRank", "nl=5 lr =0.25 iter= 20");
var trainer = sub.CreateInstance(new TrainHost(new Random(1), 0));
// Train a predictor
trainer.Train(instances);
var predictor = trainer.CreatePredictor();
///********* Several ways to save models. Only binary can be used to-reload in TLC. *******//
// Save the model in internal binary format that can be used for loading it.
string modelFilename = Path.GetTempFileName();
PredictorUtils.Save(modelFilename, predictor, instances, null);
// Save the model as a plain-text description
string modelFilenameText = Path.GetTempFileName();
PredictorUtils.SaveText(predictor, instances.Schema.FeatureNames, modelFilenameText);
// Save the model in Bing's INI format
string modelFilenameIni = Path.GetTempFileName();
PredictorUtils.SaveIni(predictor, instances.Schema.FeatureNames, modelFilenameIni);
///********* Loading and making predictions with a previously saved model *******//
// Note: there are several alternative ways to construct instances
// For example, see FactoryExampleTest below that demonstrates named-feature : value pairs.
// Load saved model
IDataModel dataModel;
IDataStats dataStats;
var pred = PredictorUtils.LoadPredictor <Float>(out dataModel, out dataStats, modelFilename);
var dp = pred as IDistributionPredictor <Instance, Float, Float>;
// Get predictions for instances
Float[] probPredictions = new Float[instances.Count];
Float[] rawPredictions = new Float[instances.Count];
Float[] rawPredictions1 = new Float[instances.Count];
for (int i = 0; i < instances.Count; i++)
{
probPredictions[i] = dp.PredictDistribution(instances[i], out rawPredictions[i]);
rawPredictions1[i] = dp.Predict(new Instance(data[i]));
}
Float[] bulkPredictions = ((IBulkPredictor <Instance, Instances, Float, Float[]>)pred).BulkPredict(instances);
Assert.Equal(rawPredictions.Length, bulkPredictions.Length);
Assert.Equal(rawPredictions.Length, rawPredictions1.Length);
for (int i = 0; i < rawPredictions.Length; i++)
{
Assert.Equal(rawPredictions[i], bulkPredictions[i]);
}
for (int i = 0; i < rawPredictions.Length; i++)
{
Assert.Equal(rawPredictions[i], rawPredictions1[i]);
}
//test new testers
{
var results = new ClassifierTester(new ProbabilityPredictorTesterArguments()).Test(pred, instances);
// Get metric names and print them alongside numbers
for (int i = 0; i < results.Length; i++)
{
Log("{0,-30} {1}", results[i].Name, results[i].Value);
}
// sanity check vs. original predictor
var results2 = new ClassifierTester(new ProbabilityPredictorTesterArguments()).Test(predictor, instances);
Assert.Equal(results.Length, results2.Length);
for (int i = 0; i < results.Length; i++)
{
Assert.Equal(results[i].Name, results2[i].Name);
Assert.Equal(results[i].Value, results2[i].Value);
}
}
File.Delete(modelFilename);
File.Delete(modelFilenameText);
File.Delete(modelFilenameIni);
});
Done();
}
static double Test(IHypothesis<Matrix, Vector> network, IDataSet<Matrix, Vector> dataSet, double oldcost = Double.PositiveInfinity)
{
var rtester = new RegressionTester<Matrix>(network);
var cost = rtester.Test(dataSet);
var classifier = new MaxFitClassifier<Matrix>(network);
var ctester = new ClassifierTester<Matrix, Vector, int>(classifier, x => x.IndexOfMax);
var accuracy = ctester.Test(dataSet);
Console.Write("C {0} | {1}%", cost, accuracy * 100);
if (oldcost < cost)
{
Console.WriteLine();
Console.WriteLine("Warning: probably weights will divergent!");
}
return cost;
}
