[ConditionalFact(typeof(Environment), nameof(Environment.Is64BitProcess))] // LightGBM is 64-bit only
public void LightGbmBinaryClassification()
{
var env = new MLContext(seed: 0);
var dataPath = GetDataPath(TestDatasets.breastCancer.trainFilename);
var dataSource = new MultiFileSource(dataPath);
var ctx = new BinaryClassificationContext(env);
var reader = TextLoader.CreateReader(env,
c => (label: c.LoadBool(0), features: c.LoadFloat(1, 9)));
IPredictorWithFeatureWeights <float> pred = null;
var est = reader.MakeNewEstimator()
.Append(r => (r.label, preds: ctx.Trainers.LightGbm(r.label, r.features,
numBoostRound: 10,
numLeaves: 5,
learningRate: 0.01,
onFit: (p) => { pred = p; })));
var pipe = reader.Append(est);
Assert.Null(pred);
var model = pipe.Fit(dataSource);
Assert.NotNull(pred);
// 9 input features, so we ought to have 9 weights.
VBuffer <float> weights = new VBuffer <float>();
pred.GetFeatureWeights(ref weights);
Assert.Equal(9, weights.Length);
var data = model.Read(dataSource);
var metrics = ctx.Evaluate(data, r => r.label, r => r.preds);
// Run a sanity check against a few of the metrics.
Assert.InRange(metrics.Accuracy, 0, 1);
Assert.InRange(metrics.Auc, 0, 1);
Assert.InRange(metrics.Auprc, 0, 1);
}
private protected override IPredictorWithFeatureWeights <double []> CreateManagedPredictor()
{
var numClass = Objective.NumClass;
if (TrainedEnsemble.NumTrees % numClass != 0)
{
throw new Exception("Number of trees should be a multiple of number of classes.");
}
var isSoftMax = (Objective.Objective == ObjectiveType.MultiClass);
IPredictorWithFeatureWeights <double>[] predictors = new IPredictorWithFeatureWeights <double> [numClass];
var cali = isSoftMax ? null : new PlattCalibrator(-Objective.Sigmoid);
for (int i = 0; i < numClass; ++i)
{
var pred = CreateBinaryPredictor(i) as IPredictorWithFeatureWeights <double>;
predictors[i] = isSoftMax ? pred : new CalibratedPredictor(pred, cali);
}
return(OvaPredictor.Create(isSoftMax, predictors));
}
public void HogwildSGDBinaryClassification()
{
var env = new MLContext(seed: 0);
var dataPath = GetDataPath(TestDatasets.breastCancer.trainFilename);
var dataSource = new MultiFileSource(dataPath);
var ctx = new BinaryClassificationContext(env);
var reader = TextLoaderStatic.CreateReader(env,
c => (label: c.LoadBool(0), features: c.LoadFloat(1, 9)));
IPredictorWithFeatureWeights <float> pred = null;
var est = reader.MakeNewEstimator()
.Append(r => (r.label, preds: ctx.Trainers.StochasticGradientDescentClassificationTrainer(r.label, r.features,
l2Weight: 0,
onFit: (p) => { pred = p; },
advancedSettings: s => s.NumThreads = 1)));
var pipe = reader.Append(est);
Assert.Null(pred);
var model = pipe.Fit(dataSource);
Assert.NotNull(pred);
// 9 input features, so we ought to have 9 weights.
VBuffer <float> weights = new VBuffer <float>();
pred.GetFeatureWeights(ref weights);
Assert.Equal(9, weights.Length);
var data = model.Read(dataSource);
var metrics = ctx.Evaluate(data, r => r.label, r => r.preds);
// Run a sanity check against a few of the metrics.
Assert.InRange(metrics.Accuracy, 0, 1);
Assert.InRange(metrics.Auc, 0, 1);
Assert.InRange(metrics.Auprc, 0, 1);
}
public void TrainRegression()
{
var objectiveTypes =
new ObjectiveType[] {
ObjectiveType.Regression,
ObjectiveType.RegressionL1,
ObjectiveType.Huber,
ObjectiveType.Fair,
ObjectiveType.Poisson,
ObjectiveType.Quantile,
ObjectiveType.Mape,
ObjectiveType.Gamma,
ObjectiveType.Tweedie
};
var rand = new Random(Seed);
for (int test = 0; test < 5; ++test)
{
int numColumns = rand.Next(1, 10);
var objective = objectiveTypes[rand.Next(objectiveTypes.Length)];
var pms = GenerateParameters(rand, objective, numColumns);
if (rand.Next(2) == 0)
{
pms.Objective.RegSqrt = true;
}
var learningRateSchedule = (rand.Next(2) == 0) ? (Func <int, double>)null : (iter => pms.Learning.LearningRate * Math.Pow(0.99, iter));
try
{
Dictionary <int, int> categorical = null;
var trainData = CreateRandomDenseRegressionData(rand, ref categorical, pms.Dataset.UseMissing, numColumns);
var validData = (pms.Learning.EarlyStoppingRound > 0 || rand.Next(2) == 0) ? CreateRandomDenseRegressionData(rand, ref categorical, pms.Dataset.UseMissing, numColumns) : null;
pms.Dataset.CategoricalFeature = categorical.Keys.ToArray();
// make labels positive for certain objective types
if (objective == ObjectiveType.Poisson ||
objective == ObjectiveType.Gamma ||
objective == ObjectiveType.Tweedie)
{
for (var i = 0; i < trainData.Labels.Length; i++)
{
trainData.Labels[i] = Math.Abs(trainData.Labels[i]);
}
if (validData != null)
{
for (var i = 0; i < validData.Labels.Length; i++)
{
validData.Labels[i] = Math.Abs(validData.Labels[i]);
}
}
}
// uncomment to select particular iteration
//if (test != 3)
// continue;
using (var datasets = (rand.Next(2) == 0) ? new Datasets(pms.Common, pms.Dataset, trainData, validData) :
new Datasets(pms.Common, pms.Dataset, Dense2Sparse(trainData), Dense2Sparse(validData)))
using (var trainer = new RegressionTrainer(pms.Learning, pms.Objective))
{
//if (true)
// trainer.ToCommandLineFiles(datasets);
var model = trainer.Train(datasets, learningRateSchedule);
model.Managed.MaxThreads = rand.Next(1, Environment.ProcessorCount);
// possibly use subset of trees
var numIterations = -1;
if (rand.Next(2) == 0)
{
numIterations = rand.Next(1, model.Managed.MaxNumTrees);
model.Managed.MaxNumTrees = numIterations;
model.Native.MaxNumTrees = numIterations;
}
IPredictorWithFeatureWeights <double> model2 = null;
using (var ms = new System.IO.MemoryStream())
using (var writer = new System.IO.BinaryWriter(ms))
using (var reader = new System.IO.BinaryReader(ms))
{
PredictorPersist.Save(model.Managed, writer);
ms.Position = 0;
model2 = PredictorPersist.Load <double>(reader);
Assert.Equal(ms.Position, ms.Length);
}
IPredictorWithFeatureWeights <double> model2native = null;
using (var ms = new System.IO.MemoryStream())
using (var writer = new System.IO.BinaryWriter(ms))
using (var reader = new System.IO.BinaryReader(ms))
{
NativePredictorPersist.Save(model.Native, writer);
ms.Position = 0;
model2native = NativePredictorPersist.Load <double>(reader);
Assert.Equal(ms.Position, ms.Length);
}
var output3s = trainer.Evaluate(Booster.PredictType.Normal, trainData.Features, numIterations);
Assert.Equal(trainData.Features.Length, output3s.GetLength(0));
Assert.Equal(1, output3s.GetLength(1));
var output3natives = model.Native.GetOutputs(trainData.Features);
Assert.Equal(trainData.Features.Length, output3s.Length);
for (int i = 0; i < trainData.Features.Length; i++)
{
var row = trainData.Features[i];
double output = 0;
var input = new VBuffer <float>(row.Length, row);
model.Managed.GetOutput(ref input, ref output);
Assert.False(double.IsNaN(output));
double output2 = 0;
model2.GetOutput(ref input, ref output2);
Compare(output, output2);
var output3 = trainer.Evaluate(Booster.PredictType.Normal, row, numIterations);
Assert.Single(output3);
Assert.Equal(output3[0], output3s[i, 0]);
Assert.Equal(output3[0], output3natives[i]);
Compare(output, output3[0]);
//Console.WriteLine(trainer.GetModelString());
//throw new Exception($"Output mismatch {output} vs {output3[0]} (error: {Math.Abs(output - output3[0])}) input: {String.Join(", ", row)}");
double outputNative = 0;
model.Native.GetOutput(ref input, ref outputNative);
Assert.Equal(outputNative, output3[0]);
model2native.GetOutput(ref input, ref outputNative);
Assert.Equal(outputNative, output3[0]);
}
var normalise = rand.Next(2) == 0;
var getSplits = rand.Next(2) == 0;
var gains = model.Managed.GetFeatureWeights(normalise, getSplits);
var gainsNative = model.Native.GetFeatureWeights(normalise, getSplits);
Assert.Equal(gains.Count, gainsNative.Count);
foreach (var kv in gains)
{
Assert.True(0 <= kv.Key && kv.Key < trainData.NumColumns);
Assert.True(0.0 <= kv.Value);
Compare(kv.Value, gainsNative[kv.Key]);
}
if (!getSplits && !normalise)
{
var totGain1 = gains.Values.Sum();
var totGain2 = Enumerable.Range(0, trainData.NumColumns).SelectMany(i => model.Managed.GetFeatureGains(i)).Sum();
Compare(totGain1, totGain2);
}
}
}
catch (Exception e)
{
throw new Exception($"Failed: {Seed} #{test} {pms}", e);
}
}
}
protected override BinaryPredictionTransformer <IPredictorWithFeatureWeights <float> > MakeTransformer(IPredictorWithFeatureWeights <float> model, Schema trainSchema) => new BinaryPredictionTransformer <IPredictorWithFeatureWeights <float> >(Host, model, trainSchema, FeatureColumn.Name);
public Predictors(IPredictorWithFeatureWeights <TOutput> managed, IVectorisedPredictorWithFeatureWeights <TOutput> native)
{
Managed = managed;
Native = native;
}
public CalibratedPredictor(IPredictorWithFeatureWeights <double> predictor, ICalibrator calibrator)
{
SubPredictor = predictor;
Calibrator = calibrator;
}