private static IDataView GetRegressionMetrics(
IHostEnvironment env,
IPredictor predictor,
RoleMappedData roleMappedData,
PermutationFeatureImportanceArguments input)
{
var roles = roleMappedData.Schema.GetColumnRoleNames();
var featureColumnName = roles.Where(x => x.Key.Value == RoleMappedSchema.ColumnRole.Feature.Value).First().Value;
var labelColumnName = roles.Where(x => x.Key.Value == RoleMappedSchema.ColumnRole.Label.Value).First().Value;
var pred = new RegressionPredictionTransformer <IPredictorProducing <float> >(
env, predictor as IPredictorProducing <float>, roleMappedData.Data.Schema, featureColumnName);
var regressionCatalog = new RegressionCatalog(env);
var permutationMetrics = regressionCatalog
.PermutationFeatureImportance(pred,
roleMappedData.Data,
labelColumnName: labelColumnName,
useFeatureWeightFilter: input.UseFeatureWeightFilter,
numberOfExamplesToUse: input.NumberOfExamplesToUse,
permutationCount: input.PermutationCount);
var slotNames = GetSlotNames(roleMappedData.Schema);
Contracts.Assert(slotNames.Length == permutationMetrics.Length,
"Mismatch between number of feature slots and number of features permuted.");
List <RegressionMetrics> metrics = new List <RegressionMetrics>();
for (int i = 0; i < permutationMetrics.Length; i++)
{
if (string.IsNullOrWhiteSpace(slotNames[i]))
{
continue;
}
var pMetric = permutationMetrics[i];
metrics.Add(new RegressionMetrics
{
FeatureName = slotNames[i],
MeanAbsoluteError = pMetric.MeanAbsoluteError.Mean,
MeanAbsoluteErrorStdErr = pMetric.MeanAbsoluteError.StandardError,
MeanSquaredError = pMetric.MeanSquaredError.Mean,
MeanSquaredErrorStdErr = pMetric.MeanSquaredError.StandardError,
RootMeanSquaredError = pMetric.RootMeanSquaredError.Mean,
RootMeanSquaredErrorStdErr = pMetric.RootMeanSquaredError.StandardError,
LossFunction = pMetric.LossFunction.Mean,
LossFunctionStdErr = pMetric.LossFunction.StandardError,
RSquared = pMetric.RSquared.Mean,
RSquaredStdErr = pMetric.RSquared.StandardError
});
}
var dataOps = new DataOperationsCatalog(env);
var result = dataOps.LoadFromEnumerable(metrics);
return(result);
}
public void FastForestRegressionIntrospectiveTraining()
{
var ml = new MLContext(seed: 1, conc: 1);
var data = SamplesUtils.DatasetUtils.GenerateFloatLabelFloatFeatureVectorSamples(1000);
var dataView = ml.Data.ReadFromEnumerable(data);
RegressionPredictionTransformer <FastForestRegressionModelParameters> pred = null;
var trainer = ml.Regression.Trainers.FastForest(numLeaves: 5, numTrees: 3).WithOnFitDelegate(p => pred = p);
// Train.
var model = trainer.Fit(dataView);
// Extract the learned RF model.
var treeCollection = pred.Model.TrainedTreeEnsemble;
// Inspect properties in the extracted model.
Assert.Equal(3, treeCollection.Trees.Count);
Assert.Equal(3, treeCollection.TreeWeights.Count);
Assert.Equal(0, treeCollection.Bias);
Assert.All(treeCollection.TreeWeights, weight => Assert.Equal(1.0, weight));
// Inspect the last tree.
var tree = treeCollection.Trees[2];
Assert.Equal(5, tree.NumLeaves);
Assert.Equal(4, tree.NumNodes);
Assert.Equal(tree.LteChild, new int[] { -1, -2, -3, -4 });
Assert.Equal(tree.GtChild, new int[] { 1, 2, 3, -5 });
Assert.Equal(tree.NumericalSplitFeatureIndexes, new int[] { 9, 0, 1, 8 });
var expectedThresholds = new float[] { 0.208134219f, 0.198336035f, 0.202952743f, 0.205061346f };
for (int i = 0; i < tree.NumNodes; ++i)
{
Assert.Equal(expectedThresholds[i], tree.NumericalSplitThresholds[i], 6);
}
Assert.All(tree.CategoricalSplitFlags, flag => Assert.False(flag));
Assert.Equal(0, tree.GetCategoricalSplitFeaturesAt(0).Count);
Assert.Equal(0, tree.GetCategoricalCategoricalSplitFeatureRangeAt(0).Count);
var samples = new double[] { 0.97468354430379744, 1.0, 0.97727272727272729, 0.972972972972973, 0.26124197002141325 };
for (int i = 0; i < tree.NumLeaves; ++i)
{
var sample = tree.GetLeafSamplesAt(i);
Assert.Single(sample);
Assert.Equal(samples[i], sample[0], 6);
var weight = tree.GetLeafSampleWeightsAt(i);
Assert.Single(weight);
Assert.Equal(1, weight[0]);
}
}
static void Main(string[] args)
{
Helper.PrintLine("使用的单独的数据准备和模型管道");
MLContext mlContext = new MLContext();
Helper.PrintLine("准备训练数据集...");
HousingData[] housingData = new HousingData[]
{
new HousingData
{
Size = 600f,
HistoricalPrices = new float[] { 100000f, 125000f, 122000f },
CurrentPrice = 170000f
},
new HousingData
{
Size = 1000f,
HistoricalPrices = new float[] { 200000f, 250000f, 230000f },
CurrentPrice = 225000f
},
new HousingData
{
Size = 1000f,
HistoricalPrices = new float[] { 126000f, 130000f, 200000f },
CurrentPrice = 195000f
}
};
IDataView data = mlContext.Data.LoadFromEnumerable(housingData);
Helper.PrintLine("准备数据处理管道...");
IEstimator <ITransformer> dataPrepEstimator =
mlContext.Transforms.Concatenate("Features", new string[] { "Size", "HistoricalPrices" })
.Append(mlContext.Transforms.NormalizeMinMax("Features"));
Helper.PrintLine("训练数据处理管道...");
ITransformer dataPrepTransformer = dataPrepEstimator.Fit(data);
Helper.PrintLine("准备神经网络模型...");
var sdcaEstimator = mlContext.Regression.Trainers.Sdca();
Helper.PrintLine("训练神经网络模型...");
IDataView transformedData = dataPrepTransformer.Transform(data);
RegressionPredictionTransformer <LinearRegressionModelParameters> trainedModel = sdcaEstimator.Fit(transformedData);
Helper.PrintLine("训练神经网络完成");
Helper.PrintLine("保存数据处理管道和神经网络模型...");
mlContext.Model.Save(dataPrepTransformer, data.Schema, DataPipelinePath);
mlContext.Model.Save(trainedModel, transformedData.Schema, ModelPath);
Helper.Exit(0);
}
public RegressionPoiOnDisplayEstimator(RegressionPoiOnDisplayEstimatorConfiguration data)
{
mlContext = new MLContext(seed: 0);
using (var s = new MemoryStream()) {
s.Write(data.PredictorX, 0, data.PredictorX.Length);
estimatorX = (RegressionPredictionTransformer <FastTreeRegressionModelParameters>)mlContext.Model.Load(s, out _);
}
using (var s = new MemoryStream()) {
s.Write(data.PredictorY, 0, data.PredictorY.Length);
estimatorY = (RegressionPredictionTransformer <FastTreeRegressionModelParameters>)mlContext.Model.Load(s, out _);
}
GenPredictors();
}
public void Load(GazeToDisplayConverterParameters param)
{
var data = (EndToEndConverterParameters)param;
mlContext = new MLContext(seed: 0);
using (var s = new MemoryStream()) {
s.Write(data.PredictorX, 0, data.PredictorX.Length);
estimatorX = (RegressionPredictionTransformer <FastTreeRegressionModelParameters>)mlContext.Model.Load(s, out _);
}
using (var s = new MemoryStream()) {
s.Write(data.PredictorY, 0, data.PredictorY.Length);
estimatorY = (RegressionPredictionTransformer <FastTreeRegressionModelParameters>)mlContext.Model.Load(s, out _);
}
GenPredictors();
}
static void Main(string[] args)
{
Helper.PrintLine("重新训练模型项目");
MLContext mlContext = new MLContext();
Helper.PrintLine("加载数据处理管道和神经网络模型...");
ITransformer dataPrepPipeline = mlContext.Model.Load(DataPipelinePath, out DataViewSchema dataPrepPipelineSchema);
ITransformer trainedModel = mlContext.Model.Load(ModelPath, out DataViewSchema modelSchema);
LinearRegressionModelParameters originalMP =
((ISingleFeaturePredictionTransformer <object>)trainedModel).Model as LinearRegressionModelParameters;
Helper.PrintLine("重新训练神经网络...");
HousingData[] housingData = new HousingData[]
{
new HousingData
{
Size = 850f,
HistoricalPrices = new float[] { 150000f, 175000f, 210000f },
CurrentPrice = 205000f
},
new HousingData
{
Size = 900f,
HistoricalPrices = new float[] { 155000f, 190000f, 220000f },
CurrentPrice = 210000f
},
new HousingData
{
Size = 550f,
HistoricalPrices = new float[] { 99000f, 98000f, 130000f },
CurrentPrice = 180000f
}
};
IDataView newData = mlContext.Data.LoadFromEnumerable(housingData);
IDataView transformedNewData = dataPrepPipeline.Transform(newData);
RegressionPredictionTransformer <LinearRegressionModelParameters> retrainedModel =
mlContext.Regression.Trainers.OnlineGradientDescent()
.Fit(transformedNewData, originalMP);
LinearRegressionModelParameters retrainedMP = retrainedModel.Model as LinearRegressionModelParameters;
Helper.PrintLine($"比较模型参数变化：\n\t源模型参数\t|更新模型参数\t|变化\n\t{string.Join("\n\t", originalMP.Weights.Append(originalMP.Bias).Zip(retrainedMP.Weights.Append(retrainedMP.Bias)).Select(weights => $"{weights.First:F2}\t|{weights.Second:F2}\t|{weights.Second - weights.First:F2}"))}");
Helper.Exit(0);
}
private static ITransformer TrainModel(MLContext mlContext)
{
// Common data loading configuration
string initialdataKey = ConfigurationManager.AppSettings["InitialDataSet"];
if (String.IsNullOrEmpty(initialdataKey))
{
Console.WriteLine("Initial DataSet key value cannot be null or empty.");
return(null);
}
LoadInitialDataInCache(initialdataKey);
var datasetTraining = Cache.DataTypeManager.GetList <TaxiTrip>(initialdataKey);
var inputDataView = mlContext.Data.LoadFromEnumerable(datasetTraining);
//Sample code of removing extreme data like "outliers" for FareAmounts higher than $150 and lower than $1 which can be error-data
var cnt = inputDataView.GetColumn <float>(nameof(TaxiTrip.FareAmount)).Count();
IDataView trainingDataView = mlContext.Data.FilterRowsByColumn(inputDataView, nameof(TaxiTrip.FareAmount), lowerBound: 1, upperBound: 150);
var cnt2 = trainingDataView.GetColumn <float>(nameof(TaxiTrip.FareAmount)).Count();
// Define data preparation estimator
IEstimator <ITransformer> dataPrepEstimator =
mlContext.Transforms.Concatenate("Features", new string[] { "PassengerCount", "TripTime", "TripDistance", "FareAmount" })
.Append(mlContext.Transforms.NormalizeMinMax("Features"));
// Create data preparation transformer
ITransformer dataPrepTransformer = dataPrepEstimator.Fit(trainingDataView);
// Define StochasticDualCoordinateAscent regression algorithm estimator
var sdcaEstimator = mlContext.Regression.Trainers.Sdca();
// Pre-process data using data prep operations
IDataView transformedData = dataPrepTransformer.Transform(trainingDataView);
// Train regression model
RegressionPredictionTransformer <LinearRegressionModelParameters> trainedModel = sdcaEstimator.Fit(transformedData);
Console.WriteLine("Initial model trained.");
// Save Data Prep transformer
mlContext.Model.Save(dataPrepTransformer, trainingDataView.Schema, ModelParamsPath);
// Save Trained Model
mlContext.Model.Save(trainedModel, transformedData.Schema, ModelPath);
Console.WriteLine("The model is saved to {0}", ModelPath);
ModelTrained = true;
Cache.Add(ModelPath, ModelPath);
return(trainedModel);
}
public new ExecuteResult <Agency_Trainer> Update(Agency_Trainer atrain)
{
var res = base.Update(atrain);
// Create MLContext
MLContext mlContext = new MLContext();
// Load Data
IDataView data = mlContext.Data.LoadFromEnumerable(ChatData.Sample);
// Define data preparation estimator
IEstimator <ITransformer> dataPrepEstimator =
mlContext.Transforms.Concatenate("Features", new string[] { "Size", "HistoricalPrices" })
.Append(mlContext.Transforms.NormalizeMinMax("Features"))
;
// Create data preparation transformer
ITransformer dataPrepTransformer = dataPrepEstimator.Fit(data);
//Console.WriteLine("数据准备 填充完成");
// Pre-process data using data prep operations
IDataView transformedData = dataPrepTransformer.Transform(data);
//Console.WriteLine($"数据视图： {Newtonsoft.Json.JsonConvert.SerializeObject(mlContext.Data.CreateEnumerable<TransformedHousingData>(transformedData, true))}");
// Define StochasticDualCoordinateAscent regression algorithm estimator
var sdcaEstimator = mlContext.Regression.Trainers.Sdca();//labelColumnName: "Label", featureColumnName: "Features"
//var sdcaEstimator = mlContext.Regression.Trainers.Sdca(labelColumnName: "Label", featureColumnName: "Features");
//Console.WriteLine("正在训练");
// Train regression model
RegressionPredictionTransformer <LinearRegressionModelParameters> trainedModel = sdcaEstimator.Fit(transformedData);
//Console.WriteLine("训练完成");
// Save Data Prep transformer
mlContext.Model.Save(dataPrepTransformer, data.Schema, "data_preparation_pipeline.zip");
// Save Trained Model
mlContext.Model.Save(trainedModel, transformedData.Schema, "model11.zip");
Console.WriteLine("预训数据 保存完成");
return(res);
}
public (double RSquaredX, double RSquaredY) Train(IList <Record> data)
{
mlContext = new MLContext(seed: 0);
var train = data.Select(r => new RegressionRecord(r));
dataView = mlContext.Data.LoadFromEnumerable(train);
labelX = nameof(RegressionRecord.DisplayX);
var pipelineX = mlContext.Regression.Trainers.FastTree(labelX, FEATURE_COLUMN_NAME);
estimatorX = pipelineX.Fit(dataView);
labelY = nameof(RegressionRecord.DisplayY);
var pipelineY = mlContext.Regression.Trainers.FastTree(labelY, FEATURE_COLUMN_NAME);
estimatorY = pipelineY.Fit(dataView);
GenPredictors();
var transX = estimatorX.Transform(dataView);
var evalX = mlContext.Regression.Evaluate(transX, labelX);
var transY = estimatorY.Transform(dataView);
var evalY = mlContext.Regression.Evaluate(transY, labelY);
return(evalX.RSquared, evalY.RSquared);
}
