static void TrainAndSave()
{
MLContext mlContext = new MLContext();
mlContext.Log += MlContext_Log;
//准备数据
var fulldata = mlContext.Data.LoadFromTextFile <FigureData>(path: DataPath, hasHeader: true, separatorChar: ',');
var trainTestData = mlContext.Data.TrainTestSplit(fulldata, testFraction: 0.2);
var trainData = trainTestData.TrainSet;
var testData = trainTestData.TestSet;
//训练
IEstimator <ITransformer> dataProcessPipeline = mlContext.Transforms.Concatenate("Features", new[] { "Height", "Weight" })
.Append(mlContext.Transforms.NormalizeMeanVariance(inputColumnName: "Features", outputColumnName: "FeaturesNormalizedByMeanVar"));
IEstimator <ITransformer> trainer = mlContext.BinaryClassification.Trainers.FastTree(labelColumnName: "Result", featureColumnName: "FeaturesNormalizedByMeanVar");
IEstimator <ITransformer> trainingPipeline = dataProcessPipeline.Append(trainer);
ITransformer model = trainingPipeline.Fit(trainData);
//评估
var predictions = model.Transform(testData);
var metrics = mlContext.BinaryClassification.Evaluate(data: predictions, labelColumnName: "Result");
PrintBinaryClassificationMetrics(trainer.ToString(), metrics);
//保存模型
mlContext.Model.Save(model, trainData.Schema, ModelPath);
Console.WriteLine($"Model file saved to :{ModelPath}");
}
static void Main()
{
MLContext mLContext = new MLContext(1);
var traningDataPath = Utility.GetAbsolutePath(typeof(Program).Assembly.Location, "../../../SysptomTraining.txt");
var trainingDataView = mLContext.Data.LoadFromTextFile <DiseasesSymptomTraining>(traningDataPath, hasHeader: false, separatorChar: '|');
var dataProcessPipeline = mLContext.Transforms.Conversion.MapValueToKey(outputColumnName: "Label", inputColumnName: nameof(DiseasesSymptomTraining.Name))
.Append(mLContext.Transforms.Text.FeaturizeText(outputColumnName: "Syptom", inputColumnName: nameof(DiseasesSymptomTraining.Syptom)))
.Append(mLContext.Transforms.Concatenate(outputColumnName: "Features", "Syptom"))
.AppendCacheCheckpoint(mLContext);
IEstimator <ITransformer> trainer = mLContext.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features");
var trainingPipeline = dataProcessPipeline.Append(trainer).Append(mLContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
Console.WriteLine("=============== Cross-validating to get model's accuracy metrics ===============");
var crossValidationResults = mLContext.MulticlassClassification.CrossValidate(data: trainingDataView, estimator: trainingPipeline, numberOfFolds: 6, labelColumnName: "Label");
ConsoleHelper.PrintMulticlassClassificationFoldsAverageMetrics(trainer.ToString(), crossValidationResults);
Console.WriteLine("=============== Training the model ===============");
var trainedModel = trainingPipeline.Fit(trainingDataView);
Console.WriteLine("=============== Saving the model to a file ===============");
mLContext.Model.Save(trainedModel, trainingDataView.Schema, "../../../DiseasesSysptomModel.zip");
ConsoleHelper.ConsoleWriteHeader("Training process finalized");
ConsoleHelper.ConsolePressAnyKey();
}
public static void DisplayPipeline(IEstimator <ITransformer> pipeline)
{
if (pipeline == null)
{
Console.WriteLine("Task 2 \"Create pipeline\" not completed.\n");
}
else
{
Console.WriteLine("Pipeline: " + pipeline.ToString() + "\n");
}
}
public static void BuildAndTrainModel()
{
// Create MLContext to be shared across the model creation workflow objects
// Set a random seed for repeatable/deterministic results across multiple trainings.
var mlContext = new MLContext(seed: 1);
var dataView = mlContext.Data.LoadFromEnumerable(LoadCorpus());
TrainTestData trainTestSplit = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.2);
IDataView trainingData = trainTestSplit.TrainSet;
IDataView testData = trainTestSplit.TestSet;
var dataProcessPipeline = mlContext.Transforms.CopyColumns(outputColumnName: "Label", inputColumnName: nameof(CorrectionData.GlueWithPrevious))
.Append(mlContext.Transforms.Categorical.OneHotEncoding(nameof(PdfFeatures.FirstChars)))
.Append(mlContext.Transforms.Conversion.ConvertType(new[]
{
new InputOutputColumnPair(nameof(PdfFeatures.PrevLastIsAlpha)),
new InputOutputColumnPair(nameof(PdfFeatures.PrevLastIsDigit)),
new InputOutputColumnPair(nameof(PdfFeatures.PrevLastIsLower)),
new InputOutputColumnPair(nameof(PdfFeatures.PrevLastIsPunct)),
}, DataKind.Single))
.Append(mlContext.Transforms.Concatenate("Features", nameof(PdfFeatures.ThisLen), nameof(PdfFeatures.MeanLen), nameof(PdfFeatures.PrevLen),
nameof(PdfFeatures.FirstChars), nameof(PdfFeatures.PrevLastIsAlpha), nameof(PdfFeatures.PrevLastIsDigit),
nameof(PdfFeatures.PrevLastIsLower), nameof(PdfFeatures.PrevLastIsPunct)))
.AppendCacheCheckpoint(mlContext);
ConsoleHelper.PeekDataViewInConsole(mlContext, trainingData, dataProcessPipeline, 2);
IEstimator <ITransformer> trainer = mlContext.BinaryClassification.Trainers.LbfgsLogisticRegression();
var trainingPipeline = dataProcessPipeline.Append(trainer);
// Train the model fitting to the DataSet
ITransformer trainedModel = trainingPipeline.Fit(trainingData);
// Evaluate the model and show accuracy stats
var predictions = trainedModel.Transform(testData);
var metrics = mlContext.BinaryClassification.Evaluate(data: predictions, labelColumnName: "Label", scoreColumnName: "Score");
ConsoleHelper.PrintBinaryClassificationMetrics(trainer.ToString(), metrics);
// Save/persist the trained model to a .ZIP file
Directory.CreateDirectory(ModelDir);
mlContext.Model.Save(trainedModel, trainingData.Schema, ModelFileName);
Console.WriteLine($"Model has been written into '{ModelFileName}'");
}
public static ITransformer TrainModel(MLContext mlContext, IDataView trainingDataView)
{
// Data process configuration with pipeline data transformations
IEstimator <ITransformer> dataProcessPipeline = mlContext.Transforms.Categorical.OneHotEncoding(new[] { new OneHotEncodingEstimator.ColumnOptions("vendor_id", "vendor_id"), new OneHotEncodingEstimator.ColumnOptions("payment_type", "payment_type") })
.Append(mlContext.Transforms.Concatenate(DefaultColumnNames.Features, new[] { "vendor_id", "payment_type", "rate_code", "passenger_count", "trip_time_in_secs", "trip_distance" }));
// Set the training algorithm
IEstimator <ITransformer> trainer = mlContext.Regression.Trainers.LightGbm(new Options()
{
NumBoostRound = 200, LearningRate = 0.02864992f, NumLeaves = 57, MinDataPerLeaf = 1, UseSoftmax = false, UseCat = false, UseMissing = true, MinDataPerGroup = 100, MaxCatThreshold = 16, CatSmooth = 20, CatL2 = 10, LabelColumn = "fare_amount", FeatureColumn = "Features"
});
IEstimator <ITransformer> trainingPipeline = dataProcessPipeline.Append(trainer);
Console.WriteLine("=============== Training " + trainer.ToString() + " model ===============");
ITransformer model = trainingPipeline.Fit(trainingDataView);
Console.WriteLine("=============== End of training process ===============");
return(model);
}
public static void BuildAndTrainModel(string DataSetLocation, string ModelPath, MyTrainerStrategy selectedStrategy)
{
// Create MLContext to be shared across the model creation workflow objects
// Set a random seed for repeatable/deterministic results across multiple trainings.
var mlContext = new MLContext(seed: 0);
// STEP 1: Common data loading configuration
var trainingDataView = mlContext.Data.ReadFromTextFile <GitHubIssue>(DataSetLocation, hasHeader: true, separatorChar: '\t');
// STEP 2: Common data process configuration with pipeline data transformations
var dataProcessPipeline = mlContext.Transforms.Conversion.MapValueToKey(outputColumnName: DefaultColumnNames.Label, inputColumnName: nameof(GitHubIssue.Area))
.Append(mlContext.Transforms.Text.FeaturizeText(outputColumnName: "TitleFeaturized", inputColumnName: nameof(GitHubIssue.Title)))
.Append(mlContext.Transforms.Text.FeaturizeText(outputColumnName: "DescriptionFeaturized", inputColumnName: nameof(GitHubIssue.Description)))
.Append(mlContext.Transforms.Concatenate(outputColumnName: DefaultColumnNames.Features, "TitleFeaturized", "DescriptionFeaturized"))
//Sample Caching the DataView so estimators iterating over the data multiple times, instead of always reading from file, using the cache might get better performance
.AppendCacheCheckpoint(mlContext); //In this sample, only when using OVA (Not SDCA) the cache improves the training time, since OVA works multiple times/iterations over the same data
// (OPTIONAL) Peek data (such as 2 records) in training DataView after applying the ProcessPipeline's transformations into "Features"
Common.ConsoleHelper.PeekDataViewInConsole <GitHubIssue>(mlContext, trainingDataView, dataProcessPipeline, 2);
//Common.ConsoleHelper.PeekVectorColumnDataInConsole(mlContext, "Features", trainingDataView, dataProcessPipeline, 2);
// STEP 3: Create the selected training algorithm/trainer
IEstimator <ITransformer> trainer = null;
switch (selectedStrategy)
{
case MyTrainerStrategy.SdcaMultiClassTrainer:
trainer = mlContext.MulticlassClassification.Trainers.StochasticDualCoordinateAscent(DefaultColumnNames.Label,
DefaultColumnNames.Features);
break;
case MyTrainerStrategy.OVAAveragedPerceptronTrainer:
{
// Create a binary classification trainer.
var averagedPerceptronBinaryTrainer = mlContext.BinaryClassification.Trainers.AveragedPerceptron(DefaultColumnNames.Label,
DefaultColumnNames.Features,
numIterations: 10);
// Compose an OVA (One-Versus-All) trainer with the BinaryTrainer.
// In this strategy, a binary classification algorithm is used to train one classifier for each class, "
// which distinguishes that class from all other classes. Prediction is then performed by running these binary classifiers, "
// and choosing the prediction with the highest confidence score.
trainer = mlContext.MulticlassClassification.Trainers.OneVersusAll(averagedPerceptronBinaryTrainer);
break;
}
default:
break;
}
//Set the trainer/algorithm and map label to value (original readable state)
var trainingPipeline = dataProcessPipeline.Append(trainer)
.Append(mlContext.Transforms.Conversion.MapKeyToValue(DefaultColumnNames.PredictedLabel));
// STEP 4: Cross-Validate with single dataset (since we don't have two datasets, one for training and for evaluate)
// in order to evaluate and get the model's accuracy metrics
Console.WriteLine("=============== Cross-validating to get model's accuracy metrics ===============");
//Measure cross-validation time
var watchCrossValTime = System.Diagnostics.Stopwatch.StartNew();
var crossValidationResults = mlContext.MulticlassClassification.CrossValidate(data: trainingDataView, estimator: trainingPipeline, numFolds: 6, labelColumn: DefaultColumnNames.Label);
//Stop measuring time
watchCrossValTime.Stop();
long elapsedMs = watchCrossValTime.ElapsedMilliseconds;
Console.WriteLine($"Time Cross-Validating: {elapsedMs} miliSecs");
//(CDLTLL-Pending-TODO)
//
ConsoleHelper.PrintMulticlassClassificationFoldsAverageMetrics(trainer.ToString(), crossValidationResults);
// STEP 5: Train the model fitting to the DataSet
Console.WriteLine("=============== Training the model ===============");
//Measure training time
var watch = System.Diagnostics.Stopwatch.StartNew();
var trainedModel = trainingPipeline.Fit(trainingDataView);
//Stop measuring time
watch.Stop();
long elapsedCrossValMs = watch.ElapsedMilliseconds;
Console.WriteLine($"Time Training the model: {elapsedCrossValMs} miliSecs");
// (OPTIONAL) Try/test a single prediction with the "just-trained model" (Before saving the model)
GitHubIssue issue = new GitHubIssue()
{
ID = "Any-ID", Title = "WebSockets communication is slow in my machine", Description = "The WebSockets communication used under the covers by SignalR looks like is going slow in my development machine.."
};
// Create prediction engine related to the loaded trained model
var predEngine = trainedModel.CreatePredictionEngine <GitHubIssue, GitHubIssuePrediction>(mlContext);
//Score
var prediction = predEngine.Predict(issue);
Console.WriteLine($"=============== Single Prediction just-trained-model - Result: {prediction.Area} ===============");
//
// STEP 6: Save/persist the trained model to a .ZIP file
Console.WriteLine("=============== Saving the model to a file ===============");
using (var fs = new FileStream(ModelPath, FileMode.Create, FileAccess.Write, FileShare.Write))
mlContext.Model.Save(trainedModel, fs);
Common.ConsoleHelper.ConsoleWriteHeader("Training process finalized");
}
public static void BuildAndTrainModel(string DataSetLocation, string ModelPath, MyTrainerStrategy selectedStrategy)
{
// Create MLContext to be shared across the model creation workflow objects
// Set a random seed for repeatable/deterministic results across multiple trainings.
var mlContext = new MLContext(seed: 1);
// STEP 1: Common data loading configuration
var trainingDataView = mlContext.Data.LoadFromTextFile<GitHubIssue>(DataSetLocation, hasHeader: true, separatorChar:'\t', allowSparse: false);
// STEP 2: Common data process configuration with pipeline data transformations
var dataProcessPipeline = mlContext.Transforms.Conversion.MapValueToKey(outputColumnName: "Label",inputColumnName:nameof(GitHubIssue.Area))
.Append(mlContext.Transforms.Text.FeaturizeText(outputColumnName: "TitleFeaturized",inputColumnName:nameof(GitHubIssue.Title)))
.Append(mlContext.Transforms.Text.FeaturizeText(outputColumnName: "DescriptionFeaturized", inputColumnName: nameof(GitHubIssue.Description)))
.Append(mlContext.Transforms.Concatenate(outputColumnName:"Features", "TitleFeaturized", "DescriptionFeaturized"))
.AppendCacheCheckpoint(mlContext);
// Use in-memory cache for small/medium datasets to lower training time.
// Do NOT use it (remove .AppendCacheCheckpoint()) when handling very large datasets.
// (OPTIONAL) Peek data (such as 2 records) in training DataView after applying the ProcessPipeline's transformations into "Features"
Common.ConsoleHelper.PeekDataViewInConsole(mlContext, trainingDataView, dataProcessPipeline, 2);
// STEP 3: Create the selected training algorithm/trainer
IEstimator<ITransformer> trainer = null;
switch(selectedStrategy)
{
case MyTrainerStrategy.SdcaMultiClassTrainer:
trainer = mlContext.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features");
break;
case MyTrainerStrategy.OVAAveragedPerceptronTrainer:
{
// Create a binary classification trainer.
var averagedPerceptronBinaryTrainer = mlContext.BinaryClassification.Trainers.AveragedPerceptron("Label", "Features",numberOfIterations: 10);
// Compose an OVA (One-Versus-All) trainer with the BinaryTrainer.
// In this strategy, a binary classification algorithm is used to train one classifier for each class, "
// which distinguishes that class from all other classes. Prediction is then performed by running these binary classifiers, "
// and choosing the prediction with the highest confidence score.
trainer = mlContext.MulticlassClassification.Trainers.OneVersusAll(averagedPerceptronBinaryTrainer);
break;
}
default:
break;
}
//Set the trainer/algorithm and map label to value (original readable state)
var trainingPipeline = dataProcessPipeline.Append(trainer)
.Append(mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
// STEP 4: Cross-Validate with single dataset (since we don't have two datasets, one for training and for evaluate)
// in order to evaluate and get the model's accuracy metrics
Console.WriteLine("=============== Cross-validating to get model's accuracy metrics ===============");
var crossValidationResults= mlContext.MulticlassClassification.CrossValidate(data:trainingDataView, estimator:trainingPipeline, numberOfFolds: 6, labelColumnName:"Label");
ConsoleHelper.PrintMulticlassClassificationFoldsAverageMetrics(trainer.ToString(), crossValidationResults);
// STEP 5: Train the model fitting to the DataSet
Console.WriteLine("=============== Training the model ===============");
var trainedModel = trainingPipeline.Fit(trainingDataView);
// (OPTIONAL) Try/test a single prediction with the "just-trained model" (Before saving the model)
GitHubIssue issue = new GitHubIssue() { ID = "Any-ID", Title = "WebSockets communication is slow in my machine", Description = "The WebSockets communication used under the covers by SignalR looks like is going slow in my development machine.." };
// Create prediction engine related to the loaded trained model
var predEngine = mlContext.Model.CreatePredictionEngine<GitHubIssue, GitHubIssuePrediction>(trainedModel);
//Score
var prediction = predEngine.Predict(issue);
Console.WriteLine($"=============== Single Prediction just-trained-model - Result: {prediction.Area} ===============");
//
// STEP 6: Save/persist the trained model to a .ZIP file
Console.WriteLine("=============== Saving the model to a file ===============");
mlContext.Model.Save(trainedModel, trainingDataView.Schema, ModelPath);
Common.ConsoleHelper.ConsoleWriteHeader("Training process finalized");
}
public static void BuildAndTrainModel(string DataSetLocation, string ModelPath, MyTrainerStrategy selectedStrategy)
{
// Create MLContext to be shared across the model creation workflow objects
// Set a random seed for repeatable/deterministic results across multiple trainings.
var mlContext = new MLContext(seed: 0);
// STEP 1: Common data loading configuration
TextLoader textLoader = mlContext.Data.TextReader(new TextLoader.Arguments()
{
Separator = "tab",
HasHeader = true,
Column = new[]
{
new TextLoader.Column("ID", DataKind.Text, 0),
new TextLoader.Column("Area", DataKind.Text, 1),
new TextLoader.Column("Title", DataKind.Text, 2),
new TextLoader.Column("Description", DataKind.Text, 3),
}
});
var trainingDataView = textLoader.Read(DataSetLocation);
// STEP 2: Common data process configuration with pipeline data transformations
var dataProcessPipeline = mlContext.Transforms.Conversion.MapValueToKey("Area", "Label")
.Append(mlContext.Transforms.Text.FeaturizeText("Title", "TitleFeaturized"))
.Append(mlContext.Transforms.Text.FeaturizeText("Description", "DescriptionFeaturized"))
.Append(mlContext.Transforms.Concatenate("Features", "TitleFeaturized", "DescriptionFeaturized"));
// (OPTIONAL) Peek data (such as 2 records) in training DataView after applying the ProcessPipeline's transformations into "Features"
Common.ConsoleHelper.PeekDataViewInConsole <GitHubIssue>(mlContext, trainingDataView, dataProcessPipeline, 2);
//Common.ConsoleHelper.PeekVectorColumnDataInConsole(mlContext, "Features", trainingDataView, dataProcessPipeline, 2);
// STEP 3: Create the selected training algorithm/trainer
IEstimator <ITransformer> trainer = null;
switch (selectedStrategy)
{
case MyTrainerStrategy.SdcaMultiClassTrainer:
trainer = mlContext.MulticlassClassification.Trainers.StochasticDualCoordinateAscent(DefaultColumnNames.Label,
DefaultColumnNames.Features);
break;
case MyTrainerStrategy.OVAAveragedPerceptronTrainer:
{
// Create a binary classification trainer.
var averagedPerceptronBinaryTrainer = mlContext.BinaryClassification.Trainers.AveragedPerceptron(DefaultColumnNames.Label,
DefaultColumnNames.Features,
numIterations: 10);
// Compose an OVA (One-Versus-All) trainer with the BinaryTrainer.
// In this strategy, a binary classification algorithm is used to train one classifier for each class, "
// which distinguishes that class from all other classes. Prediction is then performed by running these binary classifiers, "
// and choosing the prediction with the highest confidence score.
trainer = mlContext.MulticlassClassification.Trainers.OneVersusAll(averagedPerceptronBinaryTrainer);
break;
}
default:
break;
}
//Set the trainer/algorithm and map label to value (original readable state)
var trainingPipeline = dataProcessPipeline.Append(trainer)
.Append(mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
// STEP 4: Cross-Validate with single dataset (since we don't have two datasets, one for training and for evaluate)
// in order to evaluate and get the model's accuracy metrics
Console.WriteLine("=============== Cross-validating to get model's accuracy metrics ===============");
var crossValidationResults = mlContext.MulticlassClassification.CrossValidate(trainingDataView, trainingPipeline, numFolds: 6, labelColumn: "Label");
ConsoleHelper.PrintMulticlassClassificationFoldsAverageMetrics(trainer.ToString(), crossValidationResults);
// STEP 5: Train the model fitting to the DataSet
Console.WriteLine("=============== Training the model ===============");
var trainedModel = trainingPipeline.Fit(trainingDataView);
// (OPTIONAL) Try/test a single prediction with the "just-trained model" (Before saving the model)
GitHubIssue issue = new GitHubIssue()
{
ID = "Any-ID", Title = "WebSockets communication is slow in my machine", Description = "The WebSockets communication used under the covers by SignalR looks like is going slow in my development machine.."
};
// Create prediction engine related to the loaded trained model
var predFunction = trainedModel.MakePredictionFunction <GitHubIssue, GitHubIssuePrediction>(mlContext);
//Score
var prediction = predFunction.Predict(issue);
Console.WriteLine($"=============== Single Prediction just-trained-model - Result: {prediction.Area} ===============");
//
// STEP 6: Save/persist the trained model to a .ZIP file
Console.WriteLine("=============== Saving the model to a file ===============");
using (var fs = new FileStream(ModelPath, FileMode.Create, FileAccess.Write, FileShare.Write))
mlContext.Model.Save(trainedModel, fs);
Common.ConsoleHelper.ConsoleWriteHeader("Training process finalized");
}
private static void TrainModel(string dataFile, string modelFile)
{
// Create MLContext to be shared across the model creation workflow objects
var mlContext = new MLContext(seed: 0);
// STEP 1: Loading the data
Console.WriteLine($"Step 1: Loading the data ({dataFile})");
var textLoader = mlContext.Data.TextReader(
new TextLoader.Arguments
{
Separator = ",",
HasHeader = true,
AllowQuoting = true,
AllowSparse = true,
Column = new[]
{
new TextLoader.Column("Id", DataKind.Text, 0),
new TextLoader.Column("Category", DataKind.Text, 1),
new TextLoader.Column("Content", DataKind.Text, 2),
}
});
var trainingDataView = textLoader.Read(dataFile);
// STEP 2: Common data process configuration with pipeline data transformations
Console.WriteLine("Step 2: Map raw input data columns to ML.NET data");
var dataProcessPipeline = mlContext.Transforms.Categorical.MapValueToKey("Category", DefaultColumnNames.Label)
.Append(mlContext.Transforms.Text.FeaturizeText("Content", DefaultColumnNames.Features));
// (OPTIONAL) Peek data (few records) in training DataView after applying the ProcessPipeline's transformations into "Features"
// DataViewToConsole<JokeModel>(mlContext, trainingDataView, dataProcessPipeline, 2);
// STEP 3: Create the selected training algorithm/trainer
Console.WriteLine("Step 3: Create and configure the selected training algorithm (trainer)");
IEstimator <ITransformer> trainer = mlContext.MulticlassClassification.Trainers.StochasticDualCoordinateAscent();
// Alternative training
//// var averagedPerceptionBinaryTrainer = mlContext.BinaryClassification.Trainers.AveragedPerceptron(
//// DefaultColumnNames.Label,
//// DefaultColumnNames.Features,
//// numIterations: 10);
//// trainer = mlContext.MulticlassClassification.Trainers.OneVersusAll(averagedPerceptronBinaryTrainer);
// Set the trainer/algorithm and map label to value (original readable state)
var trainingPipeline = dataProcessPipeline.Append(trainer).Append(
mlContext.Transforms.Conversion.MapKeyToValue(DefaultColumnNames.PredictedLabel));
// STEP 4: Cross-Validate with single dataset (since we don't have two datasets, one for training and for evaluate)
// in order to evaluate and get the model's accuracy metrics
Console.WriteLine("Step 4: Cross-Validate with single dataset (alternatively we can divide it 80-20)");
var crossValidationResults = mlContext.MulticlassClassification.CrossValidate(
trainingDataView,
trainingPipeline,
numFolds: 10,
labelColumn: "Label");
PrintMulticlassClassificationFoldsAverageMetrics(trainer.ToString(), crossValidationResults);
// STEP 5: Train the model fitting to the DataSet
Console.WriteLine("Step 5: Train the model fitting to the DataSet");
var trainedModel = trainingPipeline.Fit(trainingDataView);
// STEP 6: Save/persist the trained model to a .ZIP file
Console.WriteLine($"Step 6: Save the model to a file ({modelFile})");
using (var fs = new FileStream(modelFile, FileMode.Create, FileAccess.Write, FileShare.Write))
{
mlContext.Model.Save(trainedModel, fs);
}
}
