StandardTrainersCatalog.AveragedPerceptron Yöntem

  • Başvuru

Tanım

Ad Alanı:
Microsoft.ML
Bütünleştirilmiş Kod:
Microsoft.ML.StandardTrainers.dll
Paket:
Microsoft.ML v3.0.1
Paket:
Microsoft.ML v1.0.0
Paket:
Microsoft.ML v1.1.0
Paket:
Microsoft.ML v1.2.0
Paket:
Microsoft.ML v1.3.1
Paket:
Microsoft.ML v1.4.0
Paket:
Microsoft.ML v1.5.5
Paket:
Microsoft.ML v1.6.0
Paket:
Microsoft.ML v1.7.0
Paket:
Microsoft.ML v2.0.0

Aşırı Yüklemeler

AveragedPerceptron(BinaryClassificationCatalog+BinaryClassificationTrainers, AveragedPerceptronTrainer+Options)

AveragedPerceptronTrainer Boole etiket verileri üzerinde eğitilen doğrusal ikili sınıflandırma modelini kullanarak hedefi tahmin eden gelişmiş seçeneklerle bir oluşturun.
AveragedPerceptron(BinaryClassificationCatalog+BinaryClassificationTrainers, String, String, IClassificationLoss, Single, Boolean, Single, Int32)

AveragedPerceptronTrainerBoole etiket verileri üzerinde eğitilmiş bir doğrusal ikili sınıflandırma modeli kullanarak hedefi tahmin eden bir oluşturun.

AveragedPerceptron(BinaryClassificationCatalog+BinaryClassificationTrainers, AveragedPerceptronTrainer+Options)

AveragedPerceptronTrainer Boole etiket verileri üzerinde eğitilen doğrusal ikili sınıflandırma modelini kullanarak hedefi tahmin eden gelişmiş seçeneklerle bir oluşturun.

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

Parametreler

catalog
BinaryClassificationCatalog.BinaryClassificationTrainers

İkili sınıflandırma kataloğu eğitmen nesnesi.

options
AveragedPerceptronTrainer.Options

Eğitmen seçenekleri.

Döndürülenler

AveragedPerceptronTrainer

Örnekler

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 AveragedPerceptronWithOptions
    {
        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 AveragedPerceptronTrainer.Options
            {
                LossFunction = new SmoothedHingeLoss(),
                LearningRate = 0.1f,
                LazyUpdate = false,
                RecencyGain = 0.1f,
                NumberOfIterations = 10
            };

            // Define the trainer.
            var pipeline = mlContext.BinaryClassification.Trainers
                .AveragedPerceptron(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: False
            //   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: 0.89
            //   AUC: 0.96
            //   F1 Score: 0.88
            //   Negative Precision: 0.87
            //   Negative Recall: 0.92
            //   Positive Precision: 0.91
            //   Positive Recall: 0.85
            //
            // TEST POSITIVE RATIO:    0.4760 (238.0/(238.0+262.0))
            //   Confusion table
            //             ||======================
            //   PREDICTED || positive | negative | Recall
            //   TRUTH     ||======================
            //    positive ||      151 |       87 | 0.6345
            //    negative ||       53 |      209 | 0.7977
            //             ||======================
            //   Precision ||   0.7402 |   0.7061 |
        }

        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());
        }
    }
}

Şunlara uygulanır

AveragedPerceptron(BinaryClassificationCatalog+BinaryClassificationTrainers, String, String, IClassificationLoss, Single, Boolean, Single, Int32)

AveragedPerceptronTrainerBoole etiket verileri üzerinde eğitilmiş bir doğrusal ikili sınıflandırma modeli kullanarak hedefi tahmin eden bir oluşturun.

public static Microsoft.ML.Trainers.AveragedPerceptronTrainer AveragedPerceptron (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, string labelColumnName = "Label", string featureColumnName = "Features", Microsoft.ML.Trainers.IClassificationLoss lossFunction = default, float learningRate = 1, bool decreaseLearningRate = false, float l2Regularization = 0, int numberOfIterations = 10);
public static Microsoft.ML.Trainers.AveragedPerceptronTrainer AveragedPerceptron (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, string labelColumnName = "Label", string featureColumnName = "Features", Microsoft.ML.Trainers.IClassificationLoss lossFunction = default, float learningRate = 1, bool decreaseLearningRate = false, float l2Regularization = 0, int numberOfIterations = 1);
static member AveragedPerceptron : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * string * string * Microsoft.ML.Trainers.IClassificationLoss * single * bool * single * int -> Microsoft.ML.Trainers.AveragedPerceptronTrainer
<Extension()>
Public Function AveragedPerceptron (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, Optional labelColumnName As String = "Label", Optional featureColumnName As String = "Features", Optional lossFunction As IClassificationLoss = Nothing, Optional learningRate As Single = 1, Optional decreaseLearningRate As Boolean = false, Optional l2Regularization As Single = 0, Optional numberOfIterations As Integer = 10) As AveragedPerceptronTrainer
<Extension()>
Public Function AveragedPerceptron (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, Optional labelColumnName As String = "Label", Optional featureColumnName As String = "Features", Optional lossFunction As IClassificationLoss = Nothing, Optional learningRate As Single = 1, Optional decreaseLearningRate As Boolean = false, Optional l2Regularization As Single = 0, Optional numberOfIterations As Integer = 1) As AveragedPerceptronTrainer

Parametreler

catalog
BinaryClassificationCatalog.BinaryClassificationTrainers

İkili sınıflandırma kataloğu eğitmen nesnesi.

labelColumnName
String

Etiket sütununun adı. Sütun verileri olmalıdır Boolean.

featureColumnName
String

Özellik sütununun adı. Sütun verileri bilinen boyutlu bir vektör Singleolmalıdır.

lossFunction
IClassificationLoss

Eğitim sürecinde en aza indirgenen kayıp işlevi. HingeLoss ise nullkullanılır ve maksimum marj ortalamalı bir algı eğitmenine yol açar.

learningRate
Single

SGD tarafından kullanılan ilk öğrenme oranı.

decreaseLearningRate
Boolean

true yinelemeler ilerledikçe değerini azaltmak learningRate için; aksi takdirde , false. false varsayılan değerdir.

l2Regularization
Single

Düzenlileştirme için L2 ağırlığı.

numberOfIterations
Int32

Eğitim veri kümesinden geçen geçişlerin sayısı.

Döndürülenler

AveragedPerceptronTrainer

Örnekler

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

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

            // 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: False
            //   Label: False, Prediction: False

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

            PrintMetrics(metrics);

            // Expected output:
            //   Accuracy: 0.72
            //   AUC: 0.79
            //   F1 Score: 0.68
            //   Negative Precision: 0.71
            //   Negative Recall: 0.80
            //   Positive Precision: 0.74
            //   Positive Recall: 0.63
            //
            //   TEST POSITIVE RATIO:    0.4760 (238.0/(238.0+262.0))
            //   Confusion table
            //             ||======================
            //   PREDICTED || positive | negative | Recall
            //   TRUTH     ||======================
            //    positive ||      151 |       87 | 0.6345
            //    negative ||       53 |      209 | 0.7977
            //             ||======================
            //   Precision ||   0.7402 |   0.7061 |
        }

        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());
        }
    }
}

Şunlara uygulanır