public override IEstimator <ITransformer> BuildFromOption(MLContext context, SdcaOption param)
{
var option = new SdcaMaximumEntropyMulticlassTrainer.Options()
{
LabelColumnName = param.LabelColumnName,
FeatureColumnName = param.FeatureColumnName,
ExampleWeightColumnName = param.ExampleWeightColumnName,
L1Regularization = param.L1Regularization,
L2Regularization = param.L2Regularization,
NumberOfThreads = AutoMlUtils.GetNumberOfThreadFromEnvrionment(),
};
return(context.MulticlassClassification.Trainers.SdcaMaximumEntropy(option));
}
public static ITransformer BuildAndTrainModel(this MLContext mlContext, IDataView splitTrainSet)
{
var options = new SdcaMaximumEntropyMulticlassTrainer.Options {
// Make the convergence tolerance tighter.
ConvergenceTolerance = 0.05f,
// Increase the maximum number of passes over training data.
MaximumNumberOfIterations = 30,
};
var pipeline =
mlContext.Transforms.Conversion.MapValueToKey("Label")
.Append(mlContext.MulticlassClassification.Trainers
.SdcaMaximumEntropy(options));
var model = pipeline.Fit(splitTrainSet);
return(model);
}
public static CommonOutputs.MulticlassClassificationOutput TrainMulticlass(IHostEnvironment env, SdcaMaximumEntropyMulticlassTrainer.Options input)
{
Contracts.CheckValue(env, nameof(env));
var host = env.Register("TrainSDCA");
host.CheckValue(input, nameof(input));
EntryPointUtils.CheckInputArgs(host, input);
return(TrainerEntryPointsUtils.Train <SdcaMaximumEntropyMulticlassTrainer.Options, CommonOutputs.MulticlassClassificationOutput>(host, input,
() => new SdcaMaximumEntropyMulticlassTrainer(host, input),
() => TrainerEntryPointsUtils.FindColumn(host, input.TrainingData.Schema, input.LabelColumnName)));
}
SdcaMaximumEntropy(this SweepableMultiClassificationTrainers trainer, string labelColumnName = "Label", string featureColumnName = "Features", SweepableOption <SdcaMaximumEntropyMulticlassTrainer.Options> optionBuilder = null, SdcaMaximumEntropyMulticlassTrainer.Options defaultOption = null)
{
var context = trainer.Context;
if (optionBuilder == null)
{
optionBuilder = SdcaMaximumEntropyMulticlassTrainerSweepableOptions.Default;
}
optionBuilder.SetDefaultOption(defaultOption);
return(context.AutoML().CreateSweepableEstimator(
(context, option) =>
{
option.LabelColumnName = labelColumnName;
option.FeatureColumnName = featureColumnName;
return context.MulticlassClassification.Trainers.SdcaMaximumEntropy(option);
},
optionBuilder,
new string[] { featureColumnName },
new string[] { PredictedLabel },
nameof(SdcaMaximumEntropyMulticlassTrainer)));
}
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 trainer options.
var options = new SdcaMaximumEntropyMulticlassTrainer.Options
{
// Make the convergence tolerance tighter.
ConvergenceTolerance = 0.05f,
// Increase the maximum number of passes over training data.
MaximumNumberOfIterations = 30,
};
// Define the trainer.
var pipeline =
// Convert the string labels into key types.
mlContext.Transforms.Conversion.MapValueToKey("Label")
// Apply SdcaMaximumEntropy multiclass trainer.
.Append(mlContext.MulticlassClassification.Trainers.SdcaMaximumEntropy(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: 2
// Label: 2, Prediction: 2
// Label: 3, Prediction: 3
// Evaluate the overall metrics
var metrics = mlContext.MulticlassClassification.Evaluate(transformedTestData);
PrintMetrics(metrics);
// Expected output:
// Micro Accuracy: 0.92
// Macro Accuracy: 0.92
// Log Loss: 0.31
// Log Loss Reduction: 0.72
// Confusion table
// ||========================
// PREDICTED || 0 | 1 | 2 | Recall
// TRUTH ||========================
// 0 || 147 | 0 | 13 | 0.9188
// 1 || 0 | 164 | 13 | 0.9266
// 2 || 10 | 6 | 147 | 0.9018
// ||========================
// Precision ||0.9363 |0.9647 |0.8497 |
}
