public Score Score(RecordSet data, bool parallel = true)
{
//NOTE: ignore parallel parameter
double[] sScores = Yarr.Repeat(double.NaN, data.NRows);
double[] bScores = Yarr.Repeat(double.NaN, data.NRows);
bool[] filter = Yarr.InlineNot(data.HasNaN(this.TargetFeatures));
var filteredData = data.Filter(filter);
data = null; // unlikely to let anything be GC'ed (lots of references to same obj) but it can't hurt
this._Score(
filteredData,
Yarr.Range(filteredData.NRows).MakeSlice(),
sScores,
bScores
);
return(new Score(sScores, bScores));
}
private static void MainMain()
{
Write("Running Random Forest ({0} trees)", NUM_MODELS);
Write("loading training data");
var traindata = Parser.LoadTrainData();
var featureCols = CsvRecord.FEATURE_COLS;
int[] colIndices = Yarr.Range(featureCols.Count);
WriteDone();
Write("creating random forest");
var treeCreator = new TreeCreator(traindata, colIndices, COLS_PER_MODEL);
var trees = treeCreator.MakeTreesParallel(NUM_MODELS);
ScoreAverager <Tree> forest = new ScoreAverager <Tree>(trees);
WriteDone();
Console.WriteLine(string.Format("\t\tcreated {0} trees", trees.Count));
Write("creating and tuning classifier (parallel2)");
PlayDingSound();
double bestCutoff = double.NaN;
double bestExponent = double.NaN;
double bestScore = double.NegativeInfinity;
var classifier = new Classifier(new ScoreCacher(forest));
foreach (double exponent in Yarr.XRange(-0.5, 0.6, 0.1))
{
double cutoff = Math.Exp(exponent);
classifier.Cutoff = cutoff;
double score = AMS(classifier.Classify(traindata, parallel: PARALLEL), traindata);
if (score > bestScore)
{
bestScore = score;
bestCutoff = cutoff;
bestExponent = exponent;
}
}
classifier = new Classifier(forest);
classifier.Cutoff = bestCutoff;
WriteDone();
Console.WriteLine(string.Format("\t\tpredicted ams: {0}", bestScore));
Console.WriteLine(string.Format("\t\tcutoff: {0} (e^{1})", bestCutoff, bestExponent));
if (bestScore < 3.5)
{
WriteDone();
PlayFailSound();
return;
}
Write("loading test data");
var testdata = Parser.LoadTestData();
WriteDone();
Write("scoring test data");
var predictions = classifier.Classify(testdata, parallel: PARALLEL);
var confidences = Yarr.Range(1, testdata.NRows + 1);
WriteDone();
Write("writing output");
Parser.WritePredictions(testdata.EventIds, predictions, confidences);
WriteDone();
WriteDone(); //whole-method timer
PlayWinSound();
}