public static void FastTreeRegression()
{
// Downloading a regression dataset from github.com/dotnet/machinelearning
// this will create a housing.txt file in the filsystem this code will run
// you can open the file to see the data.
string dataFile = SamplesUtils.DatasetUtils.DownloadHousingRegressionDataset();
// Creating the ML.Net IHostEnvironment object, needed for the pipeline
var env = new LocalEnvironment(seed: 0);
// Creating the ML context, based on the task performed.
var regressionContext = new RegressionContext(env);
// Creating a data reader, based on the format of the data
var reader = TextLoader.CreateReader(env, c => (
label: c.LoadFloat(0),
features: c.LoadFloat(1, 6)
),
separator: '\t', hasHeader: true);
// Read the data, and leave 10% out, so we can use them for testing
var data = reader.Read(new MultiFileSource(dataFile));
// The predictor that gets produced out of training
FastTreeRegressionPredictor pred = null;
// Create the estimator
var learningPipeline = reader.MakeNewEstimator()
.Append(r => (r.label, score: regressionContext.Trainers.FastTree(
r.label,
r.features,
numTrees: 100, // try: (int) 20-2000
numLeaves: 20, // try: (int) 2-128
minDatapointsInLeafs: 10, // try: (int) 1-100
learningRate: 0.2, // try: (float) 0.025-0.4
onFit: p => pred = p)
)
);
var cvResults = regressionContext.CrossValidate(data, learningPipeline, r => r.label, numFolds: 5);
var averagedMetrics = (
L1 : cvResults.Select(r => r.metrics.L1).Average(),
L2 : cvResults.Select(r => r.metrics.L2).Average(),
LossFn : cvResults.Select(r => r.metrics.LossFn).Average(),
Rms : cvResults.Select(r => r.metrics.Rms).Average(),
RSquared : cvResults.Select(r => r.metrics.RSquared).Average()
);
Console.WriteLine($"L1 - {averagedMetrics.L1}");
Console.WriteLine($"L2 - {averagedMetrics.L2}");
Console.WriteLine($"LossFunction - {averagedMetrics.LossFn}");
Console.WriteLine($"RMS - {averagedMetrics.Rms}");
Console.WriteLine($"RSquared - {averagedMetrics.RSquared}");
}
public static void FastTreeRegression()
{
// Downloading a regression dataset from github.com/dotnet/machinelearning
// this will create a housing.txt file in the filsystem this code will run
// you can open the file to see the data.
string dataFile = SamplesUtils.DatasetUtils.DownloadHousingRegressionDataset();
// Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging,
// as well as the source of randomness.
var mlContext = new MLContext();
// Creating a data reader, based on the format of the data
var reader = TextLoader.CreateReader(mlContext, c => (
label: c.LoadFloat(0),
features: c.LoadFloat(1, 6)
),
separator: '\t', hasHeader: true);
// Read the data, and leave 10% out, so we can use them for testing
var data = reader.Read(dataFile);
// The predictor that gets produced out of training
FastTreeRegressionPredictor pred = null;
// Create the estimator
var learningPipeline = reader.MakeNewEstimator()
.Append(r => (r.label, score: mlContext.Regression.Trainers.FastTree(
r.label,
r.features,
numTrees: 100, // try: (int) 20-2000
numLeaves: 20, // try: (int) 2-128
minDatapointsInLeaves: 10, // try: (int) 1-100
learningRate: 0.2, // try: (float) 0.025-0.4
onFit: p => pred = p)
)
);
var cvResults = mlContext.Regression.CrossValidate(data, learningPipeline, r => r.label, numFolds: 5);
var averagedMetrics = (
L1 : cvResults.Select(r => r.metrics.L1).Average(),
L2 : cvResults.Select(r => r.metrics.L2).Average(),
LossFn : cvResults.Select(r => r.metrics.LossFn).Average(),
Rms : cvResults.Select(r => r.metrics.Rms).Average(),
RSquared : cvResults.Select(r => r.metrics.RSquared).Average()
);
Console.WriteLine($"L1 - {averagedMetrics.L1}"); // 3.091095
Console.WriteLine($"L2 - {averagedMetrics.L2}"); // 20.351073
Console.WriteLine($"LossFunction - {averagedMetrics.LossFn}"); // 20.351074
Console.WriteLine($"RMS - {averagedMetrics.Rms}"); // 4.478358
Console.WriteLine($"RSquared - {averagedMetrics.RSquared}"); // 0.754977
}
public void FastTreeRegression()
{
var env = new MLContext(seed: 0);
var dataPath = GetDataPath(TestDatasets.generatedRegressionDataset.trainFilename);
var dataSource = new MultiFileSource(dataPath);
var ctx = new RegressionContext(env);
var reader = TextLoader.CreateReader(env,
c => (label: c.LoadFloat(11), features: c.LoadFloat(0, 10)),
separator: ';', hasHeader: true);
FastTreeRegressionPredictor pred = null;
var est = reader.MakeNewEstimator()
.Append(r => (r.label, score: ctx.Trainers.FastTree(r.label, r.features,
numTrees: 10,
numLeaves: 5,
onFit: (p) => { pred = p; })));
var pipe = reader.Append(est);
Assert.Null(pred);
var model = pipe.Fit(dataSource);
Assert.NotNull(pred);
// 11 input features, so we ought to have 11 weights.
VBuffer <float> weights = new VBuffer <float>();
pred.GetFeatureWeights(ref weights);
Assert.Equal(11, weights.Length);
var data = model.Read(dataSource);
var metrics = ctx.Evaluate(data, r => r.label, r => r.score, new PoissonLoss());
// Run a sanity check against a few of the metrics.
Assert.InRange(metrics.L1, 0, double.PositiveInfinity);
Assert.InRange(metrics.L2, 0, double.PositiveInfinity);
Assert.InRange(metrics.Rms, 0, double.PositiveInfinity);
Assert.Equal(metrics.Rms * metrics.Rms, metrics.L2, 5);
Assert.InRange(metrics.LossFn, 0, double.PositiveInfinity);
}
