public Model(MultinomialLogisticRegression regression, Featurizer featurizer, FeatureSpace featureSpace, HashSet<Target> targets)
{
this.regression = regression;
this.FeatureSpace = featureSpace;
this.Featurizer = featurizer;
this.Targets = targets;
}
public Model Learn(IEnumerable<MLEntity> entities, int numberOfEntities, FeatureSpace featureSpace, HashSet<Target> targets)
{
var featureMatrix = new double[numberOfEntities][];
var labels = new int[numberOfEntities];
int counter = 0;
var targetToInt = Model.GetTargetToInt(targets);
foreach (var entity in entities)
{
featureMatrix[counter] = this.featurizer.CreateFeatureVector(entity.WebSite, featureSpace);
labels[counter] = targetToInt[entity.Label];
++counter;
}
Logger.Log("Features extracted");
var regression = new MultinomialLogisticRegression(inputs: featureSpace.Size, categories: targets.Count);
LowerBoundNewtonRaphson lbnr = new LowerBoundNewtonRaphson(regression);
double delta;
int iteration = 0;
do
{
Logger.Log("Iteration: {0}", iteration);
delta = lbnr.Run(featureMatrix, labels);
iteration++;
} while (iteration < 10 && delta > 1e-6);
return new Model(regression, this.featurizer, featureSpace, targets);
}
public static FeatureSpace LoadFromFile(string path)
{
int count = 0;
var featureSpace = new FeatureSpace();
foreach (var line in System.IO.File.ReadLines(path))
{
featureSpace.features.Add(line, count);
++count;
}
return featureSpace;
}
