FactorizationMachineExtensions.FieldAwareFactorizationMachine Метод

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

static member FieldAwareFactorizationMachine : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * Microsoft.ML.Trainers.FieldAwareFactorizationMachineTrainer.Options -> Microsoft.ML.Trainers.FieldAwareFactorizationMachineTrainer

<Extension()>
Public Function FieldAwareFactorizationMachine (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, options As FieldAwareFactorizationMachineTrainer.Options) As FieldAwareFactorizationMachineTrainer

Параметры

Возвращаемое значение

Примеры

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 FieldAwareFactorizationMachineWithOptions
    {
        // This example first train a field-aware factorization to binary
        // classification, measure the trained model's quality, and finally
        // use the trained model to make prediction.
        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.
            IEnumerable<DataPoint> data = GenerateRandomDataPoints(500);

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

            // Define trainer options.
            var options = new FieldAwareFactorizationMachineTrainer.Options
            {
                FeatureColumnName = nameof(DataPoint.Field0),
                ExtraFeatureColumns =
                new[] { nameof(DataPoint.Field1), nameof(DataPoint.Field2) },

                LabelColumnName = nameof(DataPoint.Label),
                LambdaLatent = 0.01f,
                LambdaLinear = 0.001f,
                LatentDimension = 16,
                NumberOfIterations = 50,
                LearningRate = 0.5f
            };

            // Define the trainer.
            // This trainer trains field-aware factorization (FFM)
            // for binary classification.
            // See https://www.csie.ntu.edu.tw/~cjlin/papers/ffm.pdf for the theory
            // behind and
            // https://github.com/wschin/fast-ffm/blob/master/fast-ffm.pdf for the
            // training algorithm implemented in ML.NET.
            var pipeline = mlContext.BinaryClassification.Trainers
                .FieldAwareFactorizationMachine(options);

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

            // Run the model on training data set.
            var transformedTrainingData = model.Transform(trainingData);

            // Measure the quality of the trained model.
            var metrics = mlContext.BinaryClassification
                .Evaluate(transformedTrainingData);

            // Show the quality metrics.
            PrintMetrics(metrics);

            // Expected output:
            //   Accuracy: 0.99
            //   AUC: 1.00
            //   F1 Score: 0.99
            //   Negative Precision: 1.00
            //   Negative Recall: 0.98
            //   Positive Precision: 0.98
            //   Positive Recall: 1.00
            //   Log Loss: 0.17
            //   Log Loss Reduction: 0.83
            //   Entropy: 1.00
            //
            //  TEST POSITIVE RATIO:    0.4760 (238.0/(238.0+262.0))
            //  Confusion table
            //            ||======================
            //  PREDICTED || positive | negative | Recall
            //  TRUTH     ||======================
            //   positive ||      199 |       39 | 0.8361
            //   negative ||       69 |      193 | 0.7366
            //            ||======================
            //  Precision ||   0.7425 |   0.8319 |

            // Create prediction function from the trained model.
            var engine = mlContext.Model
                .CreatePredictionEngine<DataPoint, Result>(model);

            // Make some predictions.
            foreach (var dataPoint in data.Take(5))
            {
                var result = engine.Predict(dataPoint);
                Console.WriteLine($"Actual label: {dataPoint.Label}, "
                    + $"predicted label: {result.PredictedLabel}, "
                    + $"score of being positive class: {result.Score}, "
                    + $"and probability of beling positive class: "
                    + $"{result.Probability}.");

            }

            // Expected output:
            //   Actual label: True, predicted label: True, score of being positive class: 1.115094, and probability of being positive class: 0.7530775.
            //   Actual label: False, predicted label: False, score of being positive class: -3.478797, and probability of being positive class: 0.02992158.
            //   Actual label: True, predicted label: True, score of being positive class: 3.191896, and probability of being positive class: 0.9605282.
            //   Actual label: False, predicted label: False, score of being positive class: -3.400863, and probability of being positive class: 0.03226851.
            //   Actual label: True, predicted label: True, score of being positive class: 4.06056, and probability of being positive class: 0.9830528.
        }

        // Number of features per field.
        const int featureLength = 5;

        // This class defines objects fed to the trained model.
        private class DataPoint
        {
            // Label.
            public bool Label { get; set; }

            // Features from the first field. Note that different fields can have
            // different numbers of features.
            [VectorType(featureLength)]
            public float[] Field0 { get; set; }

            // Features from the second field. 
            [VectorType(featureLength)]
            public float[] Field1 { get; set; }

            // Features from the thrid field. 
            [VectorType(featureLength)]
            public float[] Field2 { get; set; }
        }

        // This class defines objects produced by trained model. The trained model
        // maps a DataPoint to a Result.
        public class Result
        {
            // Label.
            public bool Label { get; set; }
            // Predicted label.
            public bool PredictedLabel { get; set; }
            // Predicted score.
            public float Score { get; set; }
            // Probability of belonging to positive class.
            public float Probability { get; set; }
        }

        // Function used to create toy data sets.
        private static IEnumerable<DataPoint> GenerateRandomDataPoints(
            int exampleCount, int seed = 0)

        {
            var rnd = new Random(seed);
            var data = new List<DataPoint>();
            for (int i = 0; i < exampleCount; ++i)
            {
                // Initialize an example with a random label and an empty feature
                // vector.
                var sample = new DataPoint()
                {
                    Label = rnd.Next() % 2 == 0,
                    Field0 = new float[featureLength],
                    Field1 = new float[featureLength],
                    Field2 = new float[featureLength]
                };

                // Fill feature vectors according the assigned label.
                // Notice that features from different fields have different biases
                // and therefore different distributions. In practices such as game
                // recommendation, one may use one field to store features from user
                // profile and another field to store features from game profile.
                for (int j = 0; j < featureLength; ++j)
                {
                    var value0 = (float)rnd.NextDouble();
                    // Positive class gets larger feature value.
                    if (sample.Label)
                        value0 += 0.2f;
                    sample.Field0[j] = value0;

                    var value1 = (float)rnd.NextDouble();
                    // Positive class gets smaller feature value.
                    if (sample.Label)
                        value1 -= 0.2f;
                    sample.Field1[j] = value1;

                    var value2 = (float)rnd.NextDouble();
                    // Positive class gets larger feature value.
                    if (sample.Label)
                        value2 += 0.8f;
                    sample.Field2[j] = value2;
                }

                data.Add(sample);
            }
            return data;
        }

        // Function used to show evaluation metrics such as accuracy of predictions.
        private static void PrintMetrics(
            CalibratedBinaryClassificationMetrics 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($"Positive Recall: {metrics.PositiveRecall:F2}");
            Console.WriteLine($"Log Loss: {metrics.LogLoss:F2}");
            Console.WriteLine($"Log Loss Reduction: {metrics.LogLossReduction:F2}");
            Console.WriteLine($"Entropy: {metrics.Entropy:F2}");
        }
    }
}

public static Microsoft.ML.Trainers.FieldAwareFactorizationMachineTrainer FieldAwareFactorizationMachine (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, string featureColumnName = "Features", string labelColumnName = "Label", string exampleWeightColumnName = default);

static member FieldAwareFactorizationMachine : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * string * string * string -> Microsoft.ML.Trainers.FieldAwareFactorizationMachineTrainer

<Extension()>
Public Function FieldAwareFactorizationMachine (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, Optional featureColumnName As String = "Features", Optional labelColumnName As String = "Label", Optional exampleWeightColumnName As String = Nothing) As FieldAwareFactorizationMachineTrainer

Параметры

Возвращаемое значение

Примеры

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

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

            // ML.NET doesn't cache data set by default. Therefore, if one reads a
            // data set from a file and accesses it many times, it can be slow due
            // to expensive featurization and disk operations. When the considered
            // data can fit into memory, a solution is to cache the data in memory.
            // Caching is especially helpful when working with iterative algorithms 
            // which needs many data passes.
            trainingData = mlContext.Data.Cache(trainingData);

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

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

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

            PrintMetrics(metrics);

            // Expected output:
            //   Accuracy: 0.55
            //   AUC: 0.54
            //   F1 Score: 0.23
            //   Negative Precision: 0.54
            //   Negative Recall: 0.92
            //   Positive Precision: 0.62
            //   Positive Recall: 0.14
            //
            //   TEST POSITIVE RATIO:    0.4760 (238.0/(238.0+262.0))
            //   Confusion table
            //             ||======================
            //   PREDICTED || positive | negative | Recall
            //   TRUTH     ||======================
            //    positive ||      203 |       35 | 0.8529
            //    negative ||       21 |      241 | 0.9198
            //             ||======================
            //   Precision ||   0.9063 |   0.8732 |
        }

        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());
        }
    }
}

Комментарии

Обратите внимание, что поскольку существует только один столбец признаков, базовая модель эквивалентна стандартному компьютеру факторизации.

public static Microsoft.ML.Trainers.FieldAwareFactorizationMachineTrainer FieldAwareFactorizationMachine (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, string[] featureColumnNames, string labelColumnName = "Label", string exampleWeightColumnName = default);

static member FieldAwareFactorizationMachine : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * string[] * string * string -> Microsoft.ML.Trainers.FieldAwareFactorizationMachineTrainer

<Extension()>
Public Function FieldAwareFactorizationMachine (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, featureColumnNames As String(), Optional labelColumnName As String = "Label", Optional exampleWeightColumnName As String = Nothing) As FieldAwareFactorizationMachineTrainer

Параметры

Возвращаемое значение

Примеры

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

namespace Samples.Dynamic.Trainers.BinaryClassification
{
    public static class FieldAwareFactorizationMachine
    {
        // This example first train a field-aware factorization to binary
        // classification, measure the trained model's quality, and finally
        // use the trained model to make prediction.
        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.
            IEnumerable<DataPoint> data = GenerateRandomDataPoints(500);

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

            // Define the trainer.
            // This trainer trains field-aware factorization (FFM)
            // for binary classification.
            // See https://www.csie.ntu.edu.tw/~cjlin/papers/ffm.pdf for the theory
            // behind and 
            // https://github.com/wschin/fast-ffm/blob/master/fast-ffm.pdf for the
            // training algorithm implemented in ML.NET.
            var pipeline = mlContext.BinaryClassification.Trainers
                .FieldAwareFactorizationMachine(
                // Specify three feature columns!
                new[] {nameof(DataPoint.Field0), nameof(DataPoint.Field1),
                nameof(DataPoint.Field2) },
                // Specify binary label's column name.
                nameof(DataPoint.Label));

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

            // Run the model on training data set.
            var transformedTrainingData = model.Transform(trainingData);

            // Measure the quality of the trained model.
            var metrics = mlContext.BinaryClassification
                .Evaluate(transformedTrainingData);

            // Show the quality metrics.
            PrintMetrics(metrics);

            // Expected output:
            //   Accuracy: 0.99
            //   AUC: 1.00
            //   F1 Score: 0.99
            //   Negative Precision: 1.00
            //   Negative Recall: 0.98
            //   Positive Precision: 0.98
            //   Positive Recall: 1.00
            //   Log Loss: 0.17
            //   Log Loss Reduction: 0.83
            //   Entropy: 1.00
            //
            //   TEST POSITIVE RATIO:    0.4760 (238.0/(238.0+262.0))
            //   Confusion table
            //             ||======================
            //   PREDICTED || positive | negative | Recall
            //   TRUTH     ||======================
            //    positive ||      193 |       45 | 0.8109
            //    negative ||       52 |      210 | 0.8015
            //             ||======================
            //   Precision ||   0.7878 |   0.8235 |

            // Create prediction function from the trained model.
            var engine = mlContext.Model
                .CreatePredictionEngine<DataPoint, Result>(model);

            // Make some predictions.
            foreach (var dataPoint in data.Take(5))
            {
                var result = engine.Predict(dataPoint);
                Console.WriteLine($"Actual label: {dataPoint.Label}, "
                    + $"predicted label: {result.PredictedLabel}, "
                    + $"score of being positive class: {result.Score}, "
                    + $"and probability of beling positive class: "
                    + $"{result.Probability}.");

            }

            // Expected output:
            //   Actual label: True, predicted label: True, score of being positive class: 1.115094, and probability of being positive class: 0.7530775.
            //   Actual label: False, predicted label: False, score of being positive class: -3.478797, and probability of being positive class: 0.02992158.
            //   Actual label: True, predicted label: True, score of being positive class: 3.191896, and probability of being positive class: 0.9605282.
            //   Actual label: False, predicted label: False, score of being positive class: -3.400863, and probability of being positive class: 0.03226851.
            //   Actual label: True, predicted label: True, score of being positive class: 4.06056, and probability of being positive class: 0.9830528.
        }

        // Number of features per field.
        const int featureLength = 5;

        // This class defines objects fed to the trained model.
        private class DataPoint
        {
            // Label.
            public bool Label { get; set; }

            // Features from the first field. Note that different fields can have
            // different numbers of features.
            [VectorType(featureLength)]
            public float[] Field0 { get; set; }

            // Features from the second field. 
            [VectorType(featureLength)]
            public float[] Field1 { get; set; }

            // Features from the thrid field. 
            [VectorType(featureLength)]
            public float[] Field2 { get; set; }
        }

        // This class defines objects produced by trained model. The trained model
        // maps a DataPoint to a Result.
        public class Result
        {
            // Label.
            public bool Label { get; set; }
            // Predicted label.
            public bool PredictedLabel { get; set; }
            // Predicted score.
            public float Score { get; set; }
            // Probability of belonging to positive class.
            public float Probability { get; set; }
        }

        // Function used to create toy data sets.
        private static IEnumerable<DataPoint> GenerateRandomDataPoints(
            int exampleCount, int seed = 0)

        {
            var rnd = new Random(seed);
            var data = new List<DataPoint>();
            for (int i = 0; i < exampleCount; ++i)
            {
                // Initialize an example with a random label and an empty feature
                // vector.
                var sample = new DataPoint()
                {
                    Label = rnd.Next() % 2 == 0,
                    Field0 = new float[featureLength],
                    Field1 = new float[featureLength],
                    Field2 = new float[featureLength]
                };

                // Fill feature vectors according the assigned label.
                // Notice that features from different fields have different biases
                // and therefore different distributions. In practices such as game
                // recommendation, one may use one field to store features from user
                // profile and another field to store features from game profile.
                for (int j = 0; j < featureLength; ++j)
                {
                    var value0 = (float)rnd.NextDouble();
                    // Positive class gets larger feature value.
                    if (sample.Label)
                        value0 += 0.2f;
                    sample.Field0[j] = value0;

                    var value1 = (float)rnd.NextDouble();
                    // Positive class gets smaller feature value.
                    if (sample.Label)
                        value1 -= 0.2f;
                    sample.Field1[j] = value1;

                    var value2 = (float)rnd.NextDouble();
                    // Positive class gets larger feature value.
                    if (sample.Label)
                        value2 += 0.8f;
                    sample.Field2[j] = value2;
                }

                data.Add(sample);
            }
            return data;
        }

        // Function used to show evaluation metrics such as accuracy of predictions.
        private static void PrintMetrics(
            CalibratedBinaryClassificationMetrics 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($"Positive Recall: {metrics.PositiveRecall:F2}");
            Console.WriteLine($"Log Loss: {metrics.LogLoss:F2}");
            Console.WriteLine($"Log Loss Reduction: {metrics.LogLossReduction:F2}");
            Console.WriteLine($"Entropy: {metrics.Entropy:F2}");
        }
    }
}