void IAiTest.Train()
{
Console.WriteLine("=============== Regression task - Price Prediction ===============");
IDataView dataView = _context.Data.LoadFromTextFile <TaxiTrip>($"{RootFolder}/{TrainDataFile}", hasHeader: true, separatorChar: ',');
//Sample code of removing extreme data like "outliers" for FareAmounts higher than $150 and lower than $1 which can be error-data
//IDataView dataView = _context.Data.FilterRowsByColumn(baseTrainingDataView, nameof(TaxiTrip.FareAmount), lowerBound: 1, upperBound: 150);
var dataProcessPipeline = _context.Transforms.CopyColumns(outputColumnName: "Label", inputColumnName: nameof(TaxiTrip.FareAmount))
.Append(_context.Transforms.Categorical.OneHotEncoding(outputColumnName: "VendorIdEncoded", inputColumnName: nameof(TaxiTrip.VendorId)))
.Append(_context.Transforms.Categorical.OneHotEncoding(outputColumnName: "RateCodeEncoded", inputColumnName: nameof(TaxiTrip.RateCode)))
.Append(_context.Transforms.Categorical.OneHotEncoding(outputColumnName: "PaymentTypeEncoded", inputColumnName: nameof(TaxiTrip.PaymentType)))
.Append(_context.Transforms.NormalizeMeanVariance(outputColumnName: nameof(TaxiTrip.PassengerCount)))
.Append(_context.Transforms.NormalizeMeanVariance(outputColumnName: nameof(TaxiTrip.TripTime)))
.Append(_context.Transforms.NormalizeMeanVariance(outputColumnName: nameof(TaxiTrip.TripDistance)))
.Append(_context.Transforms.Concatenate("Features", "VendorIdEncoded", "RateCodeEncoded", "PaymentTypeEncoded", nameof(TaxiTrip.PassengerCount)
, nameof(TaxiTrip.TripTime), nameof(TaxiTrip.TripDistance)));
_trainer = _context.Regression.Trainers.Sdca(labelColumnName: "Label", featureColumnName: "Features");
var trainingPipeline = dataProcessPipeline.Append(_trainer);
Stopwatch stop = new Stopwatch();
Console.WriteLine("=============== Create and Train the Model ===============");
stop.Start();
_model = trainingPipeline.Fit(dataView);
stop.Stop();
Console.WriteLine($" Total {stop.ElapsedMilliseconds} ms");
Console.WriteLine("=============== End of training ===============");
Console.WriteLine();
}
/// <summary>
/// Predict a target using a linear regression model trained with the SDCA trainer.
/// </summary>
/// <param name="ctx">The regression context trainer object.</param>
/// <param name="label">The label, or dependent variable.</param>
/// <param name="features">The features, or independent variables.</param>
/// <param name="weights">The optional example weights.</param>
/// <param name="l2Const">The L2 regularization hyperparameter.</param>
/// <param name="l1Threshold">The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.</param>
/// <param name="maxIterations">The maximum number of passes to perform over the data.</param>
/// <param name="loss">The custom loss, if unspecified will be <see cref="SquaredLoss"/>.</param>
/// <param name="advancedSettings">A delegate to set more settings.
/// The settings here will override the ones provided in the direct method signature,
/// if both are present and have different values.
/// The columns names, however need to be provided directly, not through the <paramref name="advancedSettings"/>.</param>
/// <param name="onFit">A delegate that is called every time the
/// <see cref="Estimator{TInShape, TShape, TTransformer}.Fit(DataView{TInShape})"/> method is called on the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}"/> instance created out of this. This delegate will receive
/// the linear model that was trained. Note that this action cannot change the result in any way; it is only a way for the caller to
/// be informed about what was learnt.</param>
/// <returns>The predicted output.</returns>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]></format>
/// </example>
public static Scalar <float> Sdca(this RegressionContext.RegressionTrainers ctx,
Scalar <float> label, Vector <float> features, Scalar <float> weights = null,
float?l2Const = null,
float?l1Threshold = null,
int?maxIterations = null,
ISupportSdcaRegressionLoss loss = null,
Action <SdcaRegressionTrainer.Arguments> advancedSettings = null,
Action <LinearRegressionModelParameters> onFit = null)
{
Contracts.CheckValue(label, nameof(label));
Contracts.CheckValue(features, nameof(features));
Contracts.CheckValueOrNull(weights);
Contracts.CheckParam(!(l2Const < 0), nameof(l2Const), "Must not be negative, if specified.");
Contracts.CheckParam(!(l1Threshold < 0), nameof(l1Threshold), "Must not be negative, if specified.");
Contracts.CheckParam(!(maxIterations < 1), nameof(maxIterations), "Must be positive if specified");
Contracts.CheckValueOrNull(loss);
Contracts.CheckValueOrNull(advancedSettings);
Contracts.CheckValueOrNull(onFit);
var rec = new TrainerEstimatorReconciler.Regression(
(env, labelName, featuresName, weightsName) =>
{
var trainer = new SdcaRegressionTrainer(env, labelName, featuresName, weightsName, loss, l2Const, l1Threshold, maxIterations, advancedSettings);
if (onFit != null)
{
return(trainer.WithOnFitDelegate(trans => onFit(trans.Model)));
}
return(trainer);
}, label, features, weights);
return(rec.Score);
}
/// <summary>
/// Predict a target using a linear regression model trained with the SDCA trainer.
/// </summary>
/// <param name="catalog">The regression catalog trainer object.</param>
/// <param name="label">The label, or dependent variable.</param>
/// <param name="features">The features, or independent variables.</param>
/// <param name="weights">The optional example weights.</param>
/// <param name="l2Regularization">The L2 regularization hyperparameter.</param>
/// <param name="l1Threshold">The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.</param>
/// <param name="numberOfIterations">The maximum number of passes to perform over the data.</param>
/// <param name="lossFunction">The custom loss, if unspecified will be <see cref="SquaredLoss"/>.</param>
/// <param name="onFit">A delegate that is called every time the
/// <see cref="Estimator{TInShape, TShape, TTransformer}.Fit(DataView{TInShape})"/> method is called on the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}"/> instance created out of this. This delegate will receive
/// the linear model that was trained. Note that this action cannot change the result in any way; it is only a way for the caller to
/// be informed about what was learnt.</param>
/// <returns>The predicted output.</returns>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]></format>
/// </example>
public static Scalar <float> Sdca(this RegressionCatalog.RegressionTrainers catalog,
Scalar <float> label, Vector <float> features, Scalar <float> weights = null,
float?l2Regularization = null,
float?l1Threshold = null,
int?numberOfIterations = null,
ISupportSdcaRegressionLoss lossFunction = null,
Action <LinearRegressionModelParameters> onFit = null)
{
Contracts.CheckValue(label, nameof(label));
Contracts.CheckValue(features, nameof(features));
Contracts.CheckValueOrNull(weights);
Contracts.CheckParam(!(l2Regularization < 0), nameof(l2Regularization), "Must not be negative, if specified.");
Contracts.CheckParam(!(l1Threshold < 0), nameof(l1Threshold), "Must not be negative, if specified.");
Contracts.CheckParam(!(numberOfIterations < 1), nameof(numberOfIterations), "Must be positive if specified");
Contracts.CheckValueOrNull(lossFunction);
Contracts.CheckValueOrNull(onFit);
var rec = new TrainerEstimatorReconciler.Regression(
(env, labelName, featuresName, weightsName) =>
{
var trainer = new SdcaRegressionTrainer(env, labelName, featuresName, weightsName, lossFunction, l2Regularization, l1Threshold, numberOfIterations);
if (onFit != null)
{
return(trainer.WithOnFitDelegate(trans => onFit(trans.Model)));
}
return(trainer);
}, label, features, weights);
return(rec.Score);
}
/// <summary>
/// Predict a target using a linear regression model trained with the SDCA trainer.
/// </summary>
/// <param name="catalog">The regression catalog trainer object.</param>
/// <param name="label">The label, or dependent variable.</param>
/// <param name="features">The features, or independent variables.</param>
/// <param name="weights">The optional example weights.</param>
/// <param name="options">Advanced arguments to the algorithm.</param>
/// <param name="onFit">A delegate that is called every time the
/// <see cref="Estimator{TInShape, TShape, TTransformer}.Fit(DataView{TInShape})"/> method is called on the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}"/> instance created out of this. This delegate will receive
/// the linear model that was trained. Note that this action cannot change the result in any way; it is only a way for the caller to
/// be informed about what was learnt.</param>
/// <returns>The predicted output.</returns>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]></format>
/// </example>
public static Scalar <float> Sdca(this RegressionCatalog.RegressionTrainers catalog,
Scalar <float> label, Vector <float> features, Scalar <float> weights,
SdcaRegressionTrainer.Options options,
Action <LinearRegressionModelParameters> onFit = null)
{
Contracts.CheckValue(label, nameof(label));
Contracts.CheckValue(features, nameof(features));
Contracts.CheckValueOrNull(weights);
Contracts.CheckValueOrNull(options);
Contracts.CheckValueOrNull(onFit);
var rec = new TrainerEstimatorReconciler.Regression(
(env, labelName, featuresName, weightsName) =>
{
options.LabelColumnName = labelName;
options.FeatureColumnName = featuresName;
var trainer = new SdcaRegressionTrainer(env, options);
if (onFit != null)
{
return(trainer.WithOnFitDelegate(trans => onFit(trans.Model)));
}
return(trainer);
}, label, features, weights);
return(rec.Score);
}
public void SdcaWorkout()
{
var dataPath = GetDataPath("breast-cancer.txt");
var data = TextLoader.CreateReader(Env, ctx => (Label: ctx.LoadFloat(0), Features: ctx.LoadFloat(1, 10)))
.Read(new MultiFileSource(dataPath));
IEstimator <ITransformer> est = new LinearClassificationTrainer(Env, new LinearClassificationTrainer.Arguments {
ConvergenceTolerance = 1e-2f
}, "Features", "Label");
TestEstimatorCore(est, data.AsDynamic);
est = new SdcaRegressionTrainer(Env, new SdcaRegressionTrainer.Arguments {
ConvergenceTolerance = 1e-2f
}, "Features", "Label");
TestEstimatorCore(est, data.AsDynamic);
est = new SdcaMultiClassTrainer(Env, new SdcaMultiClassTrainer.Arguments {
ConvergenceTolerance = 1e-2f
}, "Features", "Label");
TestEstimatorCore(est, data.AsDynamic);
Done();
}
static void Main(string[] args)
{
Helper.PrintLine($"使用 PFI 解释模型...");
MLContext mlContext = new MLContext();
Helper.PrintLine("加载训练数据集...");
IDataView trainDataView = mlContext.Data.LoadFromTextFile <HousingPriceData>(TrainDataPath, separatorChar: ',');
Helper.PrintLine("获取特征成员名称...");
string[] featureColumnNames = trainDataView.Schema
.Select(column => column.Name)
.Where(columnName => columnName != "Label")
.ToArray();
Helper.PrintLine("创建数据初始化对象...");
IEstimator <ITransformer> dataPrepEstimator = mlContext.Transforms.Concatenate("Features", featureColumnNames)
.Append(mlContext.Transforms.NormalizeMinMax("Features"));
Helper.PrintLine("初始化数据...");
ITransformer dataPrepTransformer = dataPrepEstimator.Fit(trainDataView);
IDataView preprocessedTrainData = dataPrepTransformer.Transform(trainDataView);
Helper.PrintLine("创建数据估算器对象...");
SdcaRegressionTrainer sdcaEstimator = mlContext.Regression.Trainers.Sdca();
Helper.PrintSplit();
Helper.PrintLine($"开始训练神经网络...");
var sdcaModel = sdcaEstimator.Fit(preprocessedTrainData);
Helper.PrintLine($"训练神经网络完成");
Helper.PrintSplit();
ImmutableArray <RegressionMetricsStatistics> pfi = mlContext.Regression.PermutationFeatureImportance(
sdcaModel,
preprocessedTrainData,
permutationCount: 3);
Helper.PrintLine("按相关性排序特征...");
var featureImportanceMetrics = pfi
.Select((metric, index) => new { index, metric.RSquared })
.OrderByDescending(myFeatures => Math.Abs(myFeatures.RSquared.Mean))
.ToArray();
Helper.PrintSplit();
Helper.PrintLine($"特征 PFI:\n\t{string.Join("\n\t", featureImportanceMetrics.Select(feature => $">>> {featureColumnNames[feature.index]}\n\tMean: {feature.RSquared.Mean:F6}\n\tStandardDeviation: {feature.RSquared.StandardDeviation:F6}\n\tStandardError: {feature.RSquared.StandardError:F6}"))}");
Helper.Exit(0);
}
public void SdcaWorkout()
{
var dataPath = GetDataPath("breast-cancer.txt");
var data = TextLoader.CreateReader(Env, ctx => (Label: ctx.LoadFloat(0), Features: ctx.LoadFloat(1, 10)))
.Read(dataPath);
IEstimator <ITransformer> est = new SdcaBinaryTrainer(Env, "Features", "Label", advancedSettings: (s) => s.ConvergenceTolerance = 1e-2f);
TestEstimatorCore(est, data.AsDynamic);
est = new SdcaRegressionTrainer(Env, "Features", "Label", advancedSettings: (s) => s.ConvergenceTolerance = 1e-2f);
TestEstimatorCore(est, data.AsDynamic);
est = new SdcaMultiClassTrainer(Env, "Features", "Label", advancedSettings: (s) => s.ConvergenceTolerance = 1e-2f);
TestEstimatorCore(est, data.AsDynamic);
Done();
}
void IAiTest.Train()
{
Console.WriteLine("=============== Regression task - Salary Prediction ===============");
IDataView dataView = _context.Data.LoadFromTextFile <SalaryData>($"{RootFolder}/{TrainDataFile}", hasHeader: true, separatorChar: ',');
var dataProcessPipeline = _context.Transforms.CopyColumns(outputColumnName: "Label", inputColumnName: nameof(SalaryData.Salary))
.Append(_context.Transforms.Concatenate("Features", nameof(SalaryData.YearsExperience)));
_trainer = _context.Regression.Trainers.Sdca(labelColumnName: "Label", featureColumnName: "Features");
var trainingPipeline = dataProcessPipeline.Append(_trainer);
Stopwatch stop = new Stopwatch();
Console.WriteLine("=============== Create and Train the Model ===============");
stop.Start();
_model = trainingPipeline.Fit(dataView);
stop.Stop();
Console.WriteLine($" Total {stop.ElapsedMilliseconds} ms");
Console.WriteLine("=============== End of training ===============");
Console.WriteLine();
}
/// <summary>
/// Set the training algorithm, then create and config the modelBuilder - Selected Trainer (SDCA Regression algorithm).
/// </summary>
/// <param name="mlContext"></param>
/// <param name="dataProcessPipeline"></param>
/// <param name="trainer"></param>
/// <param name="trainingPipeline"></param>
private static void SetTrainingAlgorithm(MLContext mlContext, EstimatorChain <ColumnConcatenatingTransformer> dataProcessPipeline, out SdcaRegressionTrainer trainer, out EstimatorChain <RegressionPredictionTransformer <LinearRegressionModelParameters> > trainingPipeline)
{
trainer = mlContext.Regression.Trainers.Sdca(labelColumnName: "Label", featureColumnName: "Features");
trainingPipeline = dataProcessPipeline.Append(trainer);
}