LightGbmExtensions.LightGbm メソッド

public static Microsoft.ML.Trainers.LightGbm.LightGbmBinaryTrainer LightGbm (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, Microsoft.ML.Trainers.LightGbm.LightGbmBinaryTrainer.Options options);

static member LightGbm : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * Microsoft.ML.Trainers.LightGbm.LightGbmBinaryTrainer.Options -> Microsoft.ML.Trainers.LightGbm.LightGbmBinaryTrainer

<Extension()>
Public Function LightGbm (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, options As LightGbmBinaryTrainer.Options) As LightGbmBinaryTrainer

パラメーター

戻り値

例

using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers.LightGbm;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
    public static class LightGbmWithOptions
    {
        // This example requires installation of additional NuGet package for 
        // Microsoft.ML.FastTree at
        // https://www.nuget.org/packages/Microsoft.ML.FastTree/
        public static void Example()
        {
            // Create a new context for ML.NET operations. It can be used for
            // exception tracking and logging, as a catalog of available operations
            // and as the source of randomness. Setting the seed to a fixed number
            // in this example to make outputs deterministic.
            var mlContext = new MLContext(seed: 0);

            // Create a list of training data points.
            var dataPoints = GenerateRandomDataPoints(1000);

            // Convert the list of data points to an IDataView object, which is
            // consumable by ML.NET API.
            var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

            // Define trainer options.
            var options = new LightGbmBinaryTrainer.Options
            {
                Booster = new GossBooster.Options
                {
                    TopRate = 0.3,
                    OtherRate = 0.2
                }
            };

            // Define the trainer.
            var pipeline = mlContext.BinaryClassification.Trainers
                .LightGbm(options);

            // Train the model.
            var model = pipeline.Fit(trainingData);

            // Create testing data. Use different random seed to make it different
            // from training data.
            var testData = mlContext.Data
                .LoadFromEnumerable(GenerateRandomDataPoints(500, seed: 123));

            // Run the model on test data set.
            var transformedTestData = model.Transform(testData);

            // Convert IDataView object to a list.
            var predictions = mlContext.Data
                .CreateEnumerable<Prediction>(transformedTestData,
                reuseRowObject: false).ToList();

            // Print 5 predictions.
            foreach (var p in predictions.Take(5))
                Console.WriteLine($"Label: {p.Label}, "
                    + $"Prediction: {p.PredictedLabel}");

            // Expected output:
            //   Label: True, Prediction: True
            //   Label: False, Prediction: True
            //   Label: True, Prediction: True
            //   Label: True, Prediction: True
            //   Label: False, Prediction: False

            // Evaluate the overall metrics.
            var metrics = mlContext.BinaryClassification
                .Evaluate(transformedTestData);

            PrintMetrics(metrics);

            // Expected output:
            //   Accuracy: 0.71
            //   AUC: 0.76
            //   F1 Score: 0.70
            //   Negative Precision: 0.73
            //   Negative Recall: 0.71
            //   Positive Precision: 0.69
            //   Positive Recall: 0.71
            //
            //   TEST POSITIVE RATIO:    0.4760 (238.0/(238.0+262.0))
            //   Confusion table
            //             ||======================
            //   PREDICTED || positive | negative | Recall
            //   TRUTH     ||======================
            //    positive ||      168 |       70 | 0.7059
            //    negative ||       88 |      174 | 0.6641
            //             ||======================
            //   Precision ||   0.6563 |   0.7131 |
        }

        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
            int seed = 0)

        {
            var random = new Random(seed);
            float randomFloat() => (float)random.NextDouble();
            for (int i = 0; i < count; i++)
            {
                var label = randomFloat() > 0.5f;
                yield return new DataPoint
                {
                    Label = label,
                    // Create random features that are correlated with the label.
                    // For data points with false label, the feature values are
                    // slightly increased by adding a constant.
                    Features = Enumerable.Repeat(label, 50)
                        .Select(x => x ? randomFloat() : randomFloat() +
                        0.03f).ToArray()

                };
            }
        }

        // Example with label and 50 feature values. A data set is a collection of
        // such examples.
        private class DataPoint
        {
            public bool Label { get; set; }
            [VectorType(50)]
            public float[] Features { get; set; }
        }

        // Class used to capture predictions.
        private class Prediction
        {
            // Original label.
            public bool Label { get; set; }
            // Predicted label from the trainer.
            public bool PredictedLabel { get; set; }
        }

        // Pretty-print BinaryClassificationMetrics objects.
        private static void PrintMetrics(BinaryClassificationMetrics metrics)
        {
            Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
            Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
            Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
            Console.WriteLine($"Negative Precision: " +
                $"{metrics.NegativePrecision:F2}");

            Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
            Console.WriteLine($"Positive Precision: " +
                $"{metrics.PositivePrecision:F2}");

            Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}\n");
            Console.WriteLine(metrics.ConfusionMatrix.GetFormattedConfusionTable());
        }
    }
}

public static Microsoft.ML.Trainers.LightGbm.LightGbmMulticlassTrainer LightGbm (this Microsoft.ML.MulticlassClassificationCatalog.MulticlassClassificationTrainers catalog, Microsoft.ML.Trainers.LightGbm.LightGbmMulticlassTrainer.Options options);

static member LightGbm : Microsoft.ML.MulticlassClassificationCatalog.MulticlassClassificationTrainers * Microsoft.ML.Trainers.LightGbm.LightGbmMulticlassTrainer.Options -> Microsoft.ML.Trainers.LightGbm.LightGbmMulticlassTrainer

<Extension()>
Public Function LightGbm (catalog As MulticlassClassificationCatalog.MulticlassClassificationTrainers, options As LightGbmMulticlassTrainer.Options) As LightGbmMulticlassTrainer

パラメーター

戻り値

例

using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers.LightGbm;

namespace Samples.Dynamic.Trainers.MulticlassClassification
{
    public static class LightGbmWithOptions
    {
        // This example requires installation of additional NuGet package for 
        // Microsoft.ML.FastTree at
        // https://www.nuget.org/packages/Microsoft.ML.FastTree/
        public static void Example()
        {
            // Create a new context for ML.NET operations. It can be used for
            // exception tracking and logging, as a catalog of available operations
            // and as the source of randomness. Setting the seed to a fixed number
            // in this example to make outputs deterministic.
            var mlContext = new MLContext(seed: 0);

            // Create a list of training data points.
            var dataPoints = GenerateRandomDataPoints(1000);

            // Convert the list of data points to an IDataView object, which is
            // consumable by ML.NET API.
            var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

            // Define trainer options.
            var options = new LightGbmMulticlassTrainer.Options
            {
                Booster = new DartBooster.Options()
                {
                    TreeDropFraction = 0.15,
                    XgboostDartMode = false
                }
            };

            // Define the trainer.
            var pipeline =
                // Convert the string labels into key types.
                mlContext.Transforms.Conversion.MapValueToKey("Label")
                // Apply LightGbm multiclass trainer.
                .Append(mlContext.MulticlassClassification.Trainers
                .LightGbm(options));

            // Train the model.
            var model = pipeline.Fit(trainingData);

            // Create testing data. Use different random seed to make it different
            // from training data.
            var testData = mlContext.Data
                .LoadFromEnumerable(GenerateRandomDataPoints(500, seed: 123));

            // Run the model on test data set.
            var transformedTestData = model.Transform(testData);

            // Convert IDataView object to a list.
            var predictions = mlContext.Data
                .CreateEnumerable<Prediction>(transformedTestData,
                reuseRowObject: false).ToList();

            // Look at 5 predictions
            foreach (var p in predictions.Take(5))
                Console.WriteLine($"Label: {p.Label}, " +
                    $"Prediction: {p.PredictedLabel}");

            // Expected output:
            //   Label: 1, Prediction: 1
            //   Label: 2, Prediction: 2
            //   Label: 3, Prediction: 3
            //   Label: 2, Prediction: 2
            //   Label: 3, Prediction: 3

            // Evaluate the overall metrics
            var metrics = mlContext.MulticlassClassification
                .Evaluate(transformedTestData);

            PrintMetrics(metrics);

            // Expected output:
            //   Micro Accuracy: 0.98
            //   Macro Accuracy: 0.98
            //   Log Loss: 0.07
            //   Log Loss Reduction: 0.94

            //   Confusion table
            //             ||========================
            //   PREDICTED ||     0 |     1 |     2 | Recall
            //   TRUTH     ||========================
            //           0 ||   156 |     0 |     4 | 0.9750
            //           1 ||     0 |   171 |     6 | 0.9661
            //           2 ||     1 |     0 |   162 | 0.9939
            //             ||========================
            //   Precision ||0.9936 |1.0000 |0.9419 |
        }

        // Generates random uniform doubles in [-0.5, 0.5)
        // range with labels 1, 2 or 3.
        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
            int seed = 0)

        {
            var random = new Random(seed);
            float randomFloat() => (float)(random.NextDouble() - 0.5);
            for (int i = 0; i < count; i++)
            {
                // Generate Labels that are integers 1, 2 or 3
                var label = random.Next(1, 4);
                yield return new DataPoint
                {
                    Label = (uint)label,
                    // Create random features that are correlated with the label.
                    // The feature values are slightly increased by adding a
                    // constant multiple of label.
                    Features = Enumerable.Repeat(label, 20)
                        .Select(x => randomFloat() + label * 0.2f).ToArray()

                };
            }
        }

        // Example with label and 20 feature values. A data set is a collection of
        // such examples.
        private class DataPoint
        {
            public uint Label { get; set; }
            [VectorType(20)]
            public float[] Features { get; set; }
        }

        // Class used to capture predictions.
        private class Prediction
        {
            // Original label.
            public uint Label { get; set; }
            // Predicted label from the trainer.
            public uint PredictedLabel { get; set; }
        }

        // Pretty-print MulticlassClassificationMetrics objects.
        public static void PrintMetrics(MulticlassClassificationMetrics metrics)
        {
            Console.WriteLine($"Micro Accuracy: {metrics.MicroAccuracy:F2}");
            Console.WriteLine($"Macro Accuracy: {metrics.MacroAccuracy:F2}");
            Console.WriteLine($"Log Loss: {metrics.LogLoss:F2}");
            Console.WriteLine(
                $"Log Loss Reduction: {metrics.LogLossReduction:F2}\n");

            Console.WriteLine(metrics.ConfusionMatrix.GetFormattedConfusionTable());
        }
    }
}

public static Microsoft.ML.Trainers.LightGbm.LightGbmRankingTrainer LightGbm (this Microsoft.ML.RankingCatalog.RankingTrainers catalog, Microsoft.ML.Trainers.LightGbm.LightGbmRankingTrainer.Options options);

static member LightGbm : Microsoft.ML.RankingCatalog.RankingTrainers * Microsoft.ML.Trainers.LightGbm.LightGbmRankingTrainer.Options -> Microsoft.ML.Trainers.LightGbm.LightGbmRankingTrainer

<Extension()>
Public Function LightGbm (catalog As RankingCatalog.RankingTrainers, options As LightGbmRankingTrainer.Options) As LightGbmRankingTrainer

パラメーター

戻り値

例

using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers.LightGbm;

namespace Samples.Dynamic.Trainers.Ranking
{
    public static class LightGbmWithOptions
    {
        // This example requires installation of additional NuGet package for 
        // Microsoft.ML.FastTree at
        // https://www.nuget.org/packages/Microsoft.ML.FastTree/
        public static void Example()
        {
            // Create a new context for ML.NET operations. It can be used for
            // exception tracking and logging, as a catalog of available operations
            // and as the source of randomness. Setting the seed to a fixed number
            // in this example to make outputs deterministic.
            var mlContext = new MLContext(seed: 0);

            // Create a list of training data points.
            var dataPoints = GenerateRandomDataPoints(1000);

            // Convert the list of data points to an IDataView object, which is
            // consumable by ML.NET API.
            var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

            // Define trainer options.
            var options = new LightGbmRankingTrainer.Options
            {
                NumberOfLeaves = 4,
                MinimumExampleCountPerGroup = 10,
                LearningRate = 0.1,
                NumberOfIterations = 2,
                Booster = new GradientBooster.Options
                {
                    FeatureFraction = 0.9
                },
                RowGroupColumnName = "GroupId"
            };

            // Define the trainer.
            var pipeline = mlContext.Ranking.Trainers.LightGbm(options);

            // Train the model.
            var model = pipeline.Fit(trainingData);

            // Create testing data. Use different random seed to make it different
            // from training data.
            var testData = mlContext.Data.LoadFromEnumerable(
                GenerateRandomDataPoints(500, seed: 123));

            // Run the model on test data set.
            var transformedTestData = model.Transform(testData);

            // Take the top 5 rows.
            var topTransformedTestData = mlContext.Data.TakeRows(
                transformedTestData, 5);

            // Convert IDataView object to a list.
            var predictions = mlContext.Data.CreateEnumerable<Prediction>(
                topTransformedTestData, reuseRowObject: false).ToList();

            // Print 5 predictions.
            foreach (var p in predictions)
                Console.WriteLine($"Label: {p.Label}, Score: {p.Score}");

            // Expected output:
            //   Label: 5, Score: 0.05836755
            //   Label: 1, Score: -0.06531862
            //   Label: 3, Score: -0.004557075
            //   Label: 3, Score: -0.009396422
            //   Label: 1, Score: -0.05871891

            // Evaluate the overall metrics.
            var metrics = mlContext.Ranking.Evaluate(transformedTestData);
            PrintMetrics(metrics);

            // Expected output:
            //   DCG: @1:28.83, @2:46.36, @3:56.18
            //   NDCG: @1:0.69, @2:0.72, @3:0.74
        }

        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
            int seed = 0, int groupSize = 10)
        {
            var random = new Random(seed);
            float randomFloat() => (float)random.NextDouble();
            for (int i = 0; i < count; i++)
            {
                var label = random.Next(0, 5);
                yield return new DataPoint
                {
                    Label = (uint)label,
                    GroupId = (uint)(i / groupSize),
                    // Create random features that are correlated with the label.
                    // For data points with larger labels, the feature values are
                    // slightly increased by adding a constant.
                    Features = Enumerable.Repeat(label, 50).Select(
                        x => randomFloat() + x * 0.1f).ToArray()
                };
            }
        }

        // Example with label, groupId, and 50 feature values. A data set is a
        // collection of such examples.
        private class DataPoint
        {
            [KeyType(5)]
            public uint Label { get; set; }
            [KeyType(100)]
            public uint GroupId { get; set; }
            [VectorType(50)]
            public float[] Features { get; set; }
        }

        // Class used to capture predictions.
        private class Prediction
        {
            // Original label.
            public uint Label { get; set; }
            // Score produced from the trainer.
            public float Score { get; set; }
        }

        // Pretty-print RankerMetrics objects.
        public static void PrintMetrics(RankingMetrics metrics)
        {
            Console.WriteLine("DCG: " + string.Join(", ",
                metrics.DiscountedCumulativeGains.Select(
                    (d, i) => (i + 1) + ":" + d + ":F2").ToArray()));
            Console.WriteLine("NDCG: " + string.Join(", ",
                metrics.NormalizedDiscountedCumulativeGains.Select(
                    (d, i) => (i + 1) + ":" + d + ":F2").ToArray()));
        }
    }
}

public static Microsoft.ML.Trainers.LightGbm.LightGbmRegressionTrainer LightGbm (this Microsoft.ML.RegressionCatalog.RegressionTrainers catalog, Microsoft.ML.Trainers.LightGbm.LightGbmRegressionTrainer.Options options);

static member LightGbm : Microsoft.ML.RegressionCatalog.RegressionTrainers * Microsoft.ML.Trainers.LightGbm.LightGbmRegressionTrainer.Options -> Microsoft.ML.Trainers.LightGbm.LightGbmRegressionTrainer

<Extension()>
Public Function LightGbm (catalog As RegressionCatalog.RegressionTrainers, options As LightGbmRegressionTrainer.Options) As LightGbmRegressionTrainer

パラメーター

戻り値

例

using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers.LightGbm;

namespace Samples.Dynamic.Trainers.Regression
{
    public static class LightGbmWithOptions
    {
        // This example requires installation of additional NuGet
        // package for Microsoft.ML.LightGBM
        // at https://www.nuget.org/packages/Microsoft.ML.LightGbm/
        public static void Example()
        {
            // Create a new context for ML.NET operations. It can be used for
            // exception tracking and logging, as a catalog of available operations
            // and as the source of randomness. Setting the seed to a fixed number
            // in this example to make outputs deterministic.
            var mlContext = new MLContext(seed: 0);

            // Create a list of training data points.
            var dataPoints = GenerateRandomDataPoints(1000);

            // Convert the list of data points to an IDataView object, which is
            // consumable by ML.NET API.
            var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

            // Define trainer options.
            var options = new LightGbmRegressionTrainer.Options
            {
                LabelColumnName = nameof(DataPoint.Label),
                FeatureColumnName = nameof(DataPoint.Features),
                // How many leaves a single tree should have.
                NumberOfLeaves = 4,
                // Each leaf contains at least this number of training data points.
                MinimumExampleCountPerLeaf = 6,
                // The step size per update. Using a large value might reduce the
                // training time but also increase the algorithm's numerical
                // stability.
                LearningRate = 0.001,
                Booster = new Microsoft.ML.Trainers.LightGbm.GossBooster.Options()
                {
                    TopRate = 0.3,
                    OtherRate = 0.2
                }
            };

            // Define the trainer.
            var pipeline =
                mlContext.Regression.Trainers.LightGbm(options);

            // Train the model.
            var model = pipeline.Fit(trainingData);

            // Create testing data. Use different random seed to make it different
            // from training data.
            var testData = mlContext.Data.LoadFromEnumerable(
                GenerateRandomDataPoints(5, seed: 123));

            // Run the model on test data set.
            var transformedTestData = model.Transform(testData);

            // Convert IDataView object to a list.
            var predictions = mlContext.Data.CreateEnumerable<Prediction>(
                transformedTestData, reuseRowObject: false).ToList();

            // Look at 5 predictions for the Label, side by side with the actual
            // Label for comparison.
            foreach (var p in predictions)
                Console.WriteLine($"Label: {p.Label:F3}, Prediction: {p.Score:F3}");

            // Expected output:
            //   Label: 0.985, Prediction: 0.866
            //   Label: 0.155, Prediction: 0.171
            //   Label: 0.515, Prediction: 0.470
            //   Label: 0.566, Prediction: 0.476
            //   Label: 0.096, Prediction: 0.140

            // Evaluate the overall metrics
            var metrics = mlContext.Regression.Evaluate(transformedTestData);
            PrintMetrics(metrics);

            // Expected output:
            //   Mean Absolute Error: 0.04
            //   Mean Squared Error: 0.00
            //   Root Mean Squared Error: 0.06
            //   RSquared: 0.97 (closer to 1 is better. The worst case is 0)
        }

        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
            int seed = 0)
        {
            var random = new Random(seed);
            for (int i = 0; i < count; i++)
            {
                float label = (float)random.NextDouble();
                yield return new DataPoint
                {
                    Label = label,
                    // Create random features that are correlated with the label.
                    Features = Enumerable.Repeat(label, 50).Select(
                        x => x + (float)random.NextDouble()).ToArray()
                };
            }
        }

        // Example with label and 50 feature values. A data set is a collection of
        // such examples.
        private class DataPoint
        {
            public float Label { get; set; }
            [VectorType(50)]
            public float[] Features { get; set; }
        }

        // Class used to capture predictions.
        private class Prediction
        {
            // Original label.
            public float Label { get; set; }
            // Predicted score from the trainer.
            public float Score { get; set; }
        }

        // Print some evaluation metrics to regression problems.
        private static void PrintMetrics(RegressionMetrics metrics)
        {
            Console.WriteLine("Mean Absolute Error: " + metrics.MeanAbsoluteError);
            Console.WriteLine("Mean Squared Error: " + metrics.MeanSquaredError);
            Console.WriteLine(
                "Root Mean Squared Error: " + metrics.RootMeanSquaredError);

            Console.WriteLine("RSquared: " + metrics.RSquared);
        }
    }
}

public static Microsoft.ML.Trainers.LightGbm.LightGbmBinaryTrainer LightGbm (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, System.IO.Stream lightGbmModel, string featureColumnName = "Features");

static member LightGbm : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * System.IO.Stream * string -> Microsoft.ML.Trainers.LightGbm.LightGbmBinaryTrainer

<Extension()>
Public Function LightGbm (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, lightGbmModel As Stream, Optional featureColumnName As String = "Features") As LightGbmBinaryTrainer

パラメーター

戻り値

public static Microsoft.ML.Trainers.LightGbm.LightGbmMulticlassTrainer LightGbm (this Microsoft.ML.MulticlassClassificationCatalog.MulticlassClassificationTrainers catalog, System.IO.Stream lightGbmModel, string featureColumnName = "Features");

static member LightGbm : Microsoft.ML.MulticlassClassificationCatalog.MulticlassClassificationTrainers * System.IO.Stream * string -> Microsoft.ML.Trainers.LightGbm.LightGbmMulticlassTrainer

<Extension()>
Public Function LightGbm (catalog As MulticlassClassificationCatalog.MulticlassClassificationTrainers, lightGbmModel As Stream, Optional featureColumnName As String = "Features") As LightGbmMulticlassTrainer

パラメーター

戻り値

public static Microsoft.ML.Trainers.LightGbm.LightGbmRankingTrainer LightGbm (this Microsoft.ML.RankingCatalog.RankingTrainers catalog, System.IO.Stream lightGbmModel, string featureColumnName = "Features");

static member LightGbm : Microsoft.ML.RankingCatalog.RankingTrainers * System.IO.Stream * string -> Microsoft.ML.Trainers.LightGbm.LightGbmRankingTrainer

<Extension()>
Public Function LightGbm (catalog As RankingCatalog.RankingTrainers, lightGbmModel As Stream, Optional featureColumnName As String = "Features") As LightGbmRankingTrainer

パラメーター

戻り値

public static Microsoft.ML.Trainers.LightGbm.LightGbmRegressionTrainer LightGbm (this Microsoft.ML.RegressionCatalog.RegressionTrainers catalog, System.IO.Stream lightGbmModel, string featureColumnName = "Features");

static member LightGbm : Microsoft.ML.RegressionCatalog.RegressionTrainers * System.IO.Stream * string -> Microsoft.ML.Trainers.LightGbm.LightGbmRegressionTrainer

<Extension()>
Public Function LightGbm (catalog As RegressionCatalog.RegressionTrainers, lightGbmModel As Stream, Optional featureColumnName As String = "Features") As LightGbmRegressionTrainer

パラメーター

戻り値

public static Microsoft.ML.Trainers.LightGbm.LightGbmBinaryTrainer LightGbm (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, string labelColumnName = "Label", string featureColumnName = "Features", string exampleWeightColumnName = default, int? numberOfLeaves = default, int? minimumExampleCountPerLeaf = default, double? learningRate = default, int numberOfIterations = 100);

static member LightGbm : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * string * string * string * Nullable<int> * Nullable<int> * Nullable<double> * int -> Microsoft.ML.Trainers.LightGbm.LightGbmBinaryTrainer

<Extension()>
Public Function LightGbm (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, Optional labelColumnName As String = "Label", Optional featureColumnName As String = "Features", Optional exampleWeightColumnName As String = Nothing, Optional numberOfLeaves As Nullable(Of Integer) = Nothing, Optional minimumExampleCountPerLeaf As Nullable(Of Integer) = Nothing, Optional learningRate As Nullable(Of Double) = Nothing, Optional numberOfIterations As Integer = 100) As LightGbmBinaryTrainer

パラメーター

戻り値

例

using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
    public static class LightGbm
    {
        // This example requires installation of additional NuGet package for 
        // Microsoft.ML.FastTree at
        // https://www.nuget.org/packages/Microsoft.ML.FastTree/
        public static void Example()
        {
            // Create a new context for ML.NET operations. It can be used for
            // exception tracking and logging, as a catalog of available operations
            // and as the source of randomness. Setting the seed to a fixed number
            // in this example to make outputs deterministic.
            var mlContext = new MLContext(seed: 0);

            // Create a list of training data points.
            var dataPoints = GenerateRandomDataPoints(1000);

            // Convert the list of data points to an IDataView object, which is
            // consumable by ML.NET API.
            var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

            // Define the trainer.
            var pipeline = mlContext.BinaryClassification.Trainers
                .LightGbm();

            // Train the model.
            var model = pipeline.Fit(trainingData);

            // Create testing data. Use different random seed to make it different
            // from training data.
            var testData = mlContext.Data
                .LoadFromEnumerable(GenerateRandomDataPoints(500, seed: 123));

            // Run the model on test data set.
            var transformedTestData = model.Transform(testData);

            // Convert IDataView object to a list.
            var predictions = mlContext.Data
                .CreateEnumerable<Prediction>(transformedTestData,
                reuseRowObject: false).ToList();

            // Print 5 predictions.
            foreach (var p in predictions.Take(5))
                Console.WriteLine($"Label: {p.Label}, "
                    + $"Prediction: {p.PredictedLabel}");

            // Expected output:
            //   Label: True, Prediction: True
            //   Label: False, Prediction: False
            //   Label: True, Prediction: True
            //   Label: True, Prediction: True
            //   Label: False, Prediction: False

            // Evaluate the overall metrics.
            var metrics = mlContext.BinaryClassification
                .Evaluate(transformedTestData);

            PrintMetrics(metrics);

            // Expected output:
            //   Accuracy: 0.77
            //   AUC: 0.85
            //   F1 Score: 0.76
            //   Negative Precision: 0.79
            //   Negative Recall: 0.77
            //   Positive Precision: 0.75
            //   Positive Recall: 0.77
            //
            //   TEST POSITIVE RATIO:    0.4760 (238.0/(238.0+262.0))
            //   Confusion table
            //             ||======================
            //   PREDICTED || positive | negative | Recall
            //   TRUTH     ||======================
            //    positive ||      183 |       55 | 0.7689
            //    negative ||       60 |      202 | 0.7710
            //             ||======================
            //   Precision ||   0.7531 |   0.7860 |
        }

        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
            int seed = 0)

        {
            var random = new Random(seed);
            float randomFloat() => (float)random.NextDouble();
            for (int i = 0; i < count; i++)
            {
                var label = randomFloat() > 0.5f;
                yield return new DataPoint
                {
                    Label = label,
                    // Create random features that are correlated with the label.
                    // For data points with false label, the feature values are
                    // slightly increased by adding a constant.
                    Features = Enumerable.Repeat(label, 50)
                        .Select(x => x ? randomFloat() : randomFloat() +
                        0.03f).ToArray()

                };
            }
        }

        // Example with label and 50 feature values. A data set is a collection of
        // such examples.
        private class DataPoint
        {
            public bool Label { get; set; }
            [VectorType(50)]
            public float[] Features { get; set; }
        }

        // Class used to capture predictions.
        private class Prediction
        {
            // Original label.
            public bool Label { get; set; }
            // Predicted label from the trainer.
            public bool PredictedLabel { get; set; }
        }

        // Pretty-print BinaryClassificationMetrics objects.
        private static void PrintMetrics(BinaryClassificationMetrics metrics)
        {
            Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
            Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
            Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
            Console.WriteLine($"Negative Precision: " +
                $"{metrics.NegativePrecision:F2}");

            Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
            Console.WriteLine($"Positive Precision: " +
                $"{metrics.PositivePrecision:F2}");

            Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}\n");
            Console.WriteLine(metrics.ConfusionMatrix.GetFormattedConfusionTable());
        }
    }
}

public static Microsoft.ML.Trainers.LightGbm.LightGbmMulticlassTrainer LightGbm (this Microsoft.ML.MulticlassClassificationCatalog.MulticlassClassificationTrainers catalog, string labelColumnName = "Label", string featureColumnName = "Features", string exampleWeightColumnName = default, int? numberOfLeaves = default, int? minimumExampleCountPerLeaf = default, double? learningRate = default, int numberOfIterations = 100);

static member LightGbm : Microsoft.ML.MulticlassClassificationCatalog.MulticlassClassificationTrainers * string * string * string * Nullable<int> * Nullable<int> * Nullable<double> * int -> Microsoft.ML.Trainers.LightGbm.LightGbmMulticlassTrainer

<Extension()>
Public Function LightGbm (catalog As MulticlassClassificationCatalog.MulticlassClassificationTrainers, Optional labelColumnName As String = "Label", Optional featureColumnName As String = "Features", Optional exampleWeightColumnName As String = Nothing, Optional numberOfLeaves As Nullable(Of Integer) = Nothing, Optional minimumExampleCountPerLeaf As Nullable(Of Integer) = Nothing, Optional learningRate As Nullable(Of Double) = Nothing, Optional numberOfIterations As Integer = 100) As LightGbmMulticlassTrainer

パラメーター

戻り値

例

using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.MulticlassClassification
{
    public static class LightGbm
    {
        // This example requires installation of additional NuGet package for 
        // Microsoft.ML.FastTree at
        // https://www.nuget.org/packages/Microsoft.ML.FastTree/
        public static void Example()
        {
            // Create a new context for ML.NET operations. It can be used for
            // exception tracking and logging, as a catalog of available operations
            // and as the source of randomness. Setting the seed to a fixed number
            // in this example to make outputs deterministic.
            var mlContext = new MLContext(seed: 0);

            // Create a list of training data points.
            var dataPoints = GenerateRandomDataPoints(1000);

            // Convert the list of data points to an IDataView object, which is
            // consumable by ML.NET API.
            var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

            // Define the trainer.
            var pipeline =
                // Convert the string labels into key types.
                mlContext.Transforms.Conversion
                .MapValueToKey(nameof(DataPoint.Label))
                // Apply LightGbm multiclass trainer.
                .Append(mlContext.MulticlassClassification.Trainers
                .LightGbm());

            // Train the model.
            var model = pipeline.Fit(trainingData);

            // Create testing data. Use different random seed to make it different
            // from training data.
            var testData = mlContext.Data
                .LoadFromEnumerable(GenerateRandomDataPoints(500, seed: 123));

            // Run the model on test data set.
            var transformedTestData = model.Transform(testData);

            // Convert IDataView object to a list.
            var predictions = mlContext.Data
                .CreateEnumerable<Prediction>(transformedTestData,
                reuseRowObject: false).ToList();

            // Look at 5 predictions
            foreach (var p in predictions.Take(5))
                Console.WriteLine($"Label: {p.Label}, " +
                    $"Prediction: {p.PredictedLabel}");

            // Expected output:
            //   Label: 1, Prediction: 1
            //   Label: 2, Prediction: 2
            //   Label: 3, Prediction: 3
            //   Label: 2, Prediction: 2
            //   Label: 3, Prediction: 3

            // Evaluate the overall metrics
            var metrics = mlContext.MulticlassClassification
                .Evaluate(transformedTestData);

            PrintMetrics(metrics);

            // Expected output:
            //   Micro Accuracy: 0.99
            //   Macro Accuracy: 0.99
            //   Log Loss: 0.05
            //   Log Loss Reduction: 0.95

            //   Confusion table
            //             ||========================
            //   PREDICTED ||     0 |     1 |     2 | Recall
            //   TRUTH     ||========================
            //           0 ||   156 |     0 |     4 | 0.9750
            //           1 ||     0 |   176 |     1 | 0.9944
            //           2 ||     1 |     0 |   162 | 0.9939
            //             ||========================
            //   Precision ||0.9936 |1.0000 |0.9701 |
        }

        // Generates random uniform doubles in [-0.5, 0.5)
        // range with labels 1, 2 or 3.
        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
            int seed = 0)

        {
            var random = new Random(seed);
            float randomFloat() => (float)(random.NextDouble() - 0.5);
            for (int i = 0; i < count; i++)
            {
                // Generate Labels that are integers 1, 2 or 3
                var label = random.Next(1, 4);
                yield return new DataPoint
                {
                    Label = (uint)label,
                    // Create random features that are correlated with the label.
                    // The feature values are slightly increased by adding a
                    // constant multiple of label.
                    Features = Enumerable.Repeat(label, 20)
                        .Select(x => randomFloat() + label * 0.2f).ToArray()

                };
            }
        }

        // Example with label and 20 feature values. A data set is a collection of
        // such examples.
        private class DataPoint
        {
            public uint Label { get; set; }
            [VectorType(20)]
            public float[] Features { get; set; }
        }

        // Class used to capture predictions.
        private class Prediction
        {
            // Original label.
            public uint Label { get; set; }
            // Predicted label from the trainer.
            public uint PredictedLabel { get; set; }
        }

        // Pretty-print MulticlassClassificationMetrics objects.
        public static void PrintMetrics(MulticlassClassificationMetrics metrics)
        {
            Console.WriteLine($"Micro Accuracy: {metrics.MicroAccuracy:F2}");
            Console.WriteLine($"Macro Accuracy: {metrics.MacroAccuracy:F2}");
            Console.WriteLine($"Log Loss: {metrics.LogLoss:F2}");
            Console.WriteLine(
                $"Log Loss Reduction: {metrics.LogLossReduction:F2}\n");

            Console.WriteLine(metrics.ConfusionMatrix.GetFormattedConfusionTable());
        }
    }
}

public static Microsoft.ML.Trainers.LightGbm.LightGbmRegressionTrainer LightGbm (this Microsoft.ML.RegressionCatalog.RegressionTrainers catalog, string labelColumnName = "Label", string featureColumnName = "Features", string exampleWeightColumnName = default, int? numberOfLeaves = default, int? minimumExampleCountPerLeaf = default, double? learningRate = default, int numberOfIterations = 100);

static member LightGbm : Microsoft.ML.RegressionCatalog.RegressionTrainers * string * string * string * Nullable<int> * Nullable<int> * Nullable<double> * int -> Microsoft.ML.Trainers.LightGbm.LightGbmRegressionTrainer

<Extension()>
Public Function LightGbm (catalog As RegressionCatalog.RegressionTrainers, Optional labelColumnName As String = "Label", Optional featureColumnName As String = "Features", Optional exampleWeightColumnName As String = Nothing, Optional numberOfLeaves As Nullable(Of Integer) = Nothing, Optional minimumExampleCountPerLeaf As Nullable(Of Integer) = Nothing, Optional learningRate As Nullable(Of Double) = Nothing, Optional numberOfIterations As Integer = 100) As LightGbmRegressionTrainer

パラメーター

戻り値

例

using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.Regression
{
    public static class LightGbm
    {
        // This example requires installation of additional NuGet
        // package for Microsoft.ML.LightGBM
        // at https://www.nuget.org/packages/Microsoft.ML.LightGbm/
        public static void Example()
        {
            // Create a new context for ML.NET operations. It can be used for
            // exception tracking and logging, as a catalog of available operations
            // and as the source of randomness. Setting the seed to a fixed number
            // in this example to make outputs deterministic.
            var mlContext = new MLContext(seed: 0);

            // Create a list of training data points.
            var dataPoints = GenerateRandomDataPoints(1000);

            // Convert the list of data points to an IDataView object, which is
            // consumable by ML.NET API.
            var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

            // Define the trainer.
            var pipeline = mlContext.Regression.Trainers.
                LightGbm(
                labelColumnName: nameof(DataPoint.Label),
                featureColumnName: nameof(DataPoint.Features));

            // Train the model.
            var model = pipeline.Fit(trainingData);

            // Create testing data. Use different random seed to make it different
            // from training data.
            var testData = mlContext.Data.LoadFromEnumerable(
                GenerateRandomDataPoints(5, seed: 123));

            // Run the model on test data set.
            var transformedTestData = model.Transform(testData);

            // Convert IDataView object to a list.
            var predictions = mlContext.Data.CreateEnumerable<Prediction>(
                transformedTestData, reuseRowObject: false).ToList();

            // Look at 5 predictions for the Label, side by side with the actual
            // Label for comparison.
            foreach (var p in predictions)
                Console.WriteLine($"Label: {p.Label:F3}, Prediction: {p.Score:F3}");

            // Expected output:
            //   Label: 0.985, Prediction: 0.864
            //   Label: 0.155, Prediction: 0.164
            //   Label: 0.515, Prediction: 0.470
            //   Label: 0.566, Prediction: 0.501
            //   Label: 0.096, Prediction: 0.138

            // Evaluate the overall metrics
            var metrics = mlContext.Regression.Evaluate(transformedTestData);
            PrintMetrics(metrics);

            // Expected output:
            //   Mean Absolute Error: 0.10
            //   Mean Squared Error: 0.01
            //   Root Mean Squared Error: 0.11
            //   RSquared: 0.89 (closer to 1 is better. The worst case is 0)
        }

        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
            int seed = 0)
        {
            var random = new Random(seed);
            for (int i = 0; i < count; i++)
            {
                float label = (float)random.NextDouble();
                yield return new DataPoint
                {
                    Label = label,
                    // Create random features that are correlated with the label.
                    Features = Enumerable.Repeat(label, 50).Select(
                        x => x + (float)random.NextDouble()).ToArray()
                };
            }
        }

        // Example with label and 50 feature values. A data set is a collection of
        // such examples.
        private class DataPoint
        {
            public float Label { get; set; }
            [VectorType(50)]
            public float[] Features { get; set; }
        }

        // Class used to capture predictions.
        private class Prediction
        {
            // Original label.
            public float Label { get; set; }
            // Predicted score from the trainer.
            public float Score { get; set; }
        }

        // Print some evaluation metrics to regression problems.
        private static void PrintMetrics(RegressionMetrics metrics)
        {
            Console.WriteLine("Mean Absolute Error: " + metrics.MeanAbsoluteError);
            Console.WriteLine("Mean Squared Error: " + metrics.MeanSquaredError);
            Console.WriteLine(
                "Root Mean Squared Error: " + metrics.RootMeanSquaredError);

            Console.WriteLine("RSquared: " + metrics.RSquared);
        }
    }
}

public static Microsoft.ML.Trainers.LightGbm.LightGbmRankingTrainer LightGbm (this Microsoft.ML.RankingCatalog.RankingTrainers catalog, string labelColumnName = "Label", string featureColumnName = "Features", string rowGroupColumnName = "GroupId", string exampleWeightColumnName = default, int? numberOfLeaves = default, int? minimumExampleCountPerLeaf = default, double? learningRate = default, int numberOfIterations = 100);

static member LightGbm : Microsoft.ML.RankingCatalog.RankingTrainers * string * string * string * string * Nullable<int> * Nullable<int> * Nullable<double> * int -> Microsoft.ML.Trainers.LightGbm.LightGbmRankingTrainer

<Extension()>
Public Function LightGbm (catalog As RankingCatalog.RankingTrainers, Optional labelColumnName As String = "Label", Optional featureColumnName As String = "Features", Optional rowGroupColumnName As String = "GroupId", Optional exampleWeightColumnName As String = Nothing, Optional numberOfLeaves As Nullable(Of Integer) = Nothing, Optional minimumExampleCountPerLeaf As Nullable(Of Integer) = Nothing, Optional learningRate As Nullable(Of Double) = Nothing, Optional numberOfIterations As Integer = 100) As LightGbmRankingTrainer

パラメーター

戻り値

例

using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.Ranking
{
    public static class LightGbm
    {
        // This example requires installation of additional NuGet package for 
        // Microsoft.ML.FastTree at
        // https://www.nuget.org/packages/Microsoft.ML.FastTree/
        public static void Example()
        {
            // Create a new context for ML.NET operations. It can be used for
            // exception tracking and logging, as a catalog of available operations
            // and as the source of randomness. Setting the seed to a fixed number
            // in this example to make outputs deterministic.
            var mlContext = new MLContext(seed: 0);

            // Create a list of training data points.
            var dataPoints = GenerateRandomDataPoints(1000);

            // Convert the list of data points to an IDataView object, which is
            // consumable by ML.NET API.
            var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

            // Define the trainer.
            var pipeline = mlContext.Ranking.Trainers.LightGbm();

            // Train the model.
            var model = pipeline.Fit(trainingData);

            // Create testing data. Use different random seed to make it different
            // from training data.
            var testData = mlContext.Data.LoadFromEnumerable(
                GenerateRandomDataPoints(500, seed: 123));

            // Run the model on test data set.
            var transformedTestData = model.Transform(testData);

            // Take the top 5 rows.
            var topTransformedTestData = mlContext.Data.TakeRows(
                transformedTestData, 5);

            // Convert IDataView object to a list.
            var predictions = mlContext.Data.CreateEnumerable<Prediction>(
                topTransformedTestData, reuseRowObject: false).ToList();

            // Print 5 predictions.
            foreach (var p in predictions)
                Console.WriteLine($"Label: {p.Label}, Score: {p.Score}");

            // Expected output:
            //   Label: 5, Score: 2.493263
            //   Label: 1, Score: -4.528436
            //   Label: 3, Score: -3.002865
            //   Label: 3, Score: -2.151812
            //   Label: 1, Score: -4.089102

            // Evaluate the overall metrics.
            var metrics = mlContext.Ranking.Evaluate(transformedTestData);
            PrintMetrics(metrics);

            // Expected output:
            //   DCG: @1:41.95, @2:63.76, @3:75.97
            //   NDCG: @1:0.99, @2:0.99, @3:0.99
        }

        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
            int seed = 0, int groupSize = 10)
        {
            var random = new Random(seed);
            float randomFloat() => (float)random.NextDouble();
            for (int i = 0; i < count; i++)
            {
                var label = random.Next(0, 5);
                yield return new DataPoint
                {
                    Label = (uint)label,
                    GroupId = (uint)(i / groupSize),
                    // Create random features that are correlated with the label.
                    // For data points with larger labels, the feature values are
                    // slightly increased by adding a constant.
                    Features = Enumerable.Repeat(label, 50).Select(
                        x => randomFloat() + x * 0.1f).ToArray()
                };
            }
        }

        // Example with label, groupId, and 50 feature values. A data set is a
        // collection of such examples.
        private class DataPoint
        {
            [KeyType(5)]
            public uint Label { get; set; }
            [KeyType(100)]
            public uint GroupId { get; set; }
            [VectorType(50)]
            public float[] Features { get; set; }
        }

        // Class used to capture predictions.
        private class Prediction
        {
            // Original label.
            public uint Label { get; set; }
            // Score produced from the trainer.
            public float Score { get; set; }
        }

        // Pretty-print RankerMetrics objects.
        public static void PrintMetrics(RankingMetrics metrics)
        {
            Console.WriteLine("DCG: " + string.Join(", ",
                metrics.DiscountedCumulativeGains.Select(
                    (d, i) => (i + 1) + ":" + d + ":F2").ToArray()));
            Console.WriteLine("NDCG: " + string.Join(", ",
                metrics.NormalizedDiscountedCumulativeGains.Select(
                    (d, i) => (i + 1) + ":" + d + ":F2").ToArray()));
        }
    }
}