StandardTrainersCatalog.LdSvm Méthode

  • Référence

Définition

Espace de noms:
Microsoft.ML
Assembly:
Microsoft.ML.StandardTrainers.dll
Paquet:
Microsoft.ML v3.0.1
Paquet:
Microsoft.ML v1.5.5
Paquet:
Microsoft.ML v1.6.0
Paquet:
Microsoft.ML v1.7.0
Paquet:
Microsoft.ML v2.0.0

Surcharges

LdSvm(BinaryClassificationCatalog+BinaryClassificationTrainers, LdSvmTrainer+Options)

Créez LdSvmTrainer avec des options avancées, ce qui prédit une cible à l’aide d’un modèle SVM deep local.
LdSvm(BinaryClassificationCatalog+BinaryClassificationTrainers, String, String, String, Int32, Int32, Boolean, Boolean)

Créez LdSvmTrainer, ce qui prédit une cible à l’aide d’un modèle SVM Deep Local.

LdSvm(BinaryClassificationCatalog+BinaryClassificationTrainers, LdSvmTrainer+Options)

Créez LdSvmTrainer avec des options avancées, ce qui prédit une cible à l’aide d’un modèle SVM deep local.

public static Microsoft.ML.Trainers.LdSvmTrainer LdSvm (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, Microsoft.ML.Trainers.LdSvmTrainer.Options options);
static member LdSvm : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * Microsoft.ML.Trainers.LdSvmTrainer.Options -> Microsoft.ML.Trainers.LdSvmTrainer
<Extension()>
Public Function LdSvm (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, options As LdSvmTrainer.Options) As LdSvmTrainer

Paramètres

catalog
BinaryClassificationCatalog.BinaryClassificationTrainers

Le BinaryClassificationCatalog.

options
LdSvmTrainer.Options

Options de formateur.

Retours

LdSvmTrainer

Exemples

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

namespace Samples.Dynamic.Trainers.BinaryClassification
{
    public static class LdSvmWithOptions
    {
        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 LdSvmTrainer.Options
            {
                TreeDepth = 5,
                NumberOfIterations = 10000,
                Sigma = 0.1f,
            };

            // Define the trainer.
            var pipeline = mlContext.BinaryClassification.Trainers
                .LdSvm(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
                .EvaluateNonCalibrated(transformedTestData);

            PrintMetrics(metrics);

            // Expected output:
            //   Accuracy: 0.80
            //   AUC: 0.89
            //   F1 Score: 0.79
            //   Negative Precision: 0.81
            //   Negative Recall: 0.81
            //   Positive Precision: 0.79
            //   Positive Recall: 0.79

            //   TEST POSITIVE RATIO:    0.4760 (238.0/(238.0+262.0))
            //   Confusion table
            //             ||======================
            //   PREDICTED || positive | negative | Recall
            //   TRUTH     ||======================
            //    positive ||      189 |       49 | 0.7941
            //    negative ||       50 |      212 | 0.8092
            //             ||======================
            //   Precision ||   0.7908 |   0.8123 |
        }

        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() +
                        0.1f).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());
        }
    }
}

S’applique à

LdSvm(BinaryClassificationCatalog+BinaryClassificationTrainers, String, String, String, Int32, Int32, Boolean, Boolean)

Créez LdSvmTrainer, ce qui prédit une cible à l’aide d’un modèle SVM Deep Local.

public static Microsoft.ML.Trainers.LdSvmTrainer LdSvm (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, string labelColumnName = "Label", string featureColumnName = "Features", string exampleWeightColumnName = default, int numberOfIterations = 15000, int treeDepth = 3, bool useBias = true, bool useCachedData = true);
static member LdSvm : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * string * string * string * int * int * bool * bool -> Microsoft.ML.Trainers.LdSvmTrainer
<Extension()>
Public Function LdSvm (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, Optional labelColumnName As String = "Label", Optional featureColumnName As String = "Features", Optional exampleWeightColumnName As String = Nothing, Optional numberOfIterations As Integer = 15000, Optional treeDepth As Integer = 3, Optional useBias As Boolean = true, Optional useCachedData As Boolean = true) As LdSvmTrainer

Paramètres

catalog
BinaryClassificationCatalog.BinaryClassificationTrainers

Le BinaryClassificationCatalog.

labelColumnName
String

Nom de la colonne d’étiquette.

featureColumnName
String

Nom de la colonne de fonctionnalité. Les données de colonne doivent être un vecteur de taille connue de Single.

exampleWeightColumnName
String

Nom de l’exemple de colonne de poids (facultatif).

numberOfIterations
Int32

Nombre d'itérations.

treeDepth
Int32

Profondeur d’une arborescence SVM deep locale.

useBias
Boolean

Indique si le modèle doit avoir un terme de biais.

useCachedData
Boolean

Indique si nous devons itérer sur les données à l’aide d’un cache.

Retours

LdSvmTrainer

Exemples

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

namespace Samples.Dynamic.Trainers.BinaryClassification
{
    public static class LdSvm
    {
        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
                .LdSvm();

            // 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
                .EvaluateNonCalibrated(transformedTestData);

            PrintMetrics(metrics);

            // Expected output:
            // Accuracy: 0.82
            // AUC: 0.85
            // F1 Score: 0.81
            // Negative Precision: 0.82
            // Negative Recall: 0.82
            // Positive Precision: 0.81
            // Positive Recall: 0.81

            // TEST POSITIVE RATIO:    0.4760 (238.0/(238.0+262.0))
            // Confusion table
            //           ||======================
            // PREDICTED || positive | negative | Recall
            // TRUTH     ||======================
            //  positive ||      192 |       46 | 0.8067
            //  negative ||       46 |      216 | 0.8244
            //           ||======================
            // Precision ||   0.8067 |   0.8244 |
        }

        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() +
                        0.1f).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());
        }
    }
}

S’applique à