public void OvaFastTree()
{
string dataPath = GetDataPath("iris.txt");
// 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.
var mlContext = new MLContext(seed: 1);
var reader = new TextLoader(mlContext, new TextLoader.Arguments()
{
Columns = new[]
{
new TextLoader.Column("Label", DataKind.R4, 0),
new TextLoader.Column("Features", DataKind.R4, new [] { new TextLoader.Range(1, 4) }),
}
});
// Data
var data = reader.Read(GetDataPath(dataPath));
// Pipeline
var pipeline = new Ova(
mlContext,
mlContext.BinaryClassification.Trainers.FastTree(new FastTreeBinaryClassificationTrainer.Options {
NumThreads = 1
}),
useProbabilities: false);
var model = pipeline.Fit(data);
var predictions = model.Transform(data);
// Metrics
var metrics = mlContext.MulticlassClassification.Evaluate(predictions);
Assert.True(metrics.AccuracyMicro > 0.99);
}
public async Task <IActionResult> Edit(int id, [Bind("Id,CodigoOva,Año,Nombre,Capitulos,Duracion")] Ova ova)
{
if (id != ova.Id)
{
return(NotFound());
}
if (ModelState.IsValid)
{
try
{
_context.Update(ova);
await _context.SaveChangesAsync();
}
catch (DbUpdateConcurrencyException)
{
if (!OvaExists(ova.Id))
{
return(NotFound());
}
else
{
throw;
}
}
return(RedirectToAction(nameof(Index)));
}
return(View(ova));
}
public void OvaAveragedPerceptron()
{
string dataPath = GetDataPath("iris.txt");
// 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.
var mlContext = new MLContext(seed: 1);
var reader = new TextLoader(mlContext, new TextLoader.Arguments()
{
Column = new[]
{
new TextLoader.Column("Label", DataKind.R4, 0),
new TextLoader.Column("Features", DataKind.R4, new [] { new TextLoader.Range(1, 4) }),
}
});
// Data
var data = reader.Read(GetDataPath(dataPath));
// Pipeline
var pipeline = new Ova(
mlContext,
new AveragedPerceptronTrainer(mlContext, "Label", "Features", advancedSettings: s => { s.Shuffle = true; s.Calibrator = null; }),
useProbabilities: false);
var model = pipeline.Fit(data);
var predictions = model.Transform(data);
// Metrics
var metrics = mlContext.MulticlassClassification.Evaluate(predictions);
Assert.True(metrics.AccuracyMicro > 0.71);
}
public async Task <IActionResult> Create([Bind("Id,CodigoOva,Año,Nombre,Capitulos,Duracion")] Ova ova)
{
if (ModelState.IsValid)
{
_context.Add(ova);
await _context.SaveChangesAsync();
return(RedirectToAction(nameof(Index)));
}
return(View(ova));
}
public void Metacomponents()
{
using (var env = new LocalEnvironment())
{
var loader = TextLoader.ReadFile(env, MakeIrisTextLoaderArgs(), new MultiFileSource(GetDataPath(TestDatasets.irisData.trainFilename)));
var term = TermTransform.Create(env, loader, "Label");
var concat = new ConcatTransform(env, "Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth").Transform(term);
var trainer = new Ova(env, new Ova.Arguments
{
PredictorType = ComponentFactoryUtils.CreateFromFunction(
e => new AveragedPerceptronTrainer(env, new AveragedPerceptronTrainer.Arguments()))
});
IDataView trainData = trainer.Info.WantCaching ? (IDataView) new CacheDataView(env, concat, prefetch: null) : concat;
var trainRoles = new RoleMappedData(trainData, label: "Label", feature: "Features");
// Auto-normalization.
NormalizeTransform.CreateIfNeeded(env, ref trainRoles, trainer);
var predictor = trainer.Train(new TrainContext(trainRoles));
}
}
void Metacomponents()
{
var dataPath = GetDataPath(IrisDataPath);
using (var env = new TlcEnvironment())
{
var loader = new TextLoader(env, MakeIrisTextLoaderArgs(), new MultiFileSource(dataPath));
var term = new TermTransform(env, loader, "Label");
var concat = new ConcatTransform(env, term, "Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");
var trainer = new Ova(env, new Ova.Arguments
{
PredictorType = new SimpleComponentFactory <ITrainer <IPredictorProducing <float> > >
(
(e) => new FastTreeBinaryClassificationTrainer(e, new FastTreeBinaryClassificationTrainer.Arguments())
)
});
IDataView trainData = trainer.Info.WantCaching ? (IDataView) new CacheDataView(env, concat, prefetch: null) : concat;
var trainRoles = new RoleMappedData(trainData, label: "Label", feature: "Features");
// Auto-normalization.
NormalizeTransform.CreateIfNeeded(env, ref trainRoles, trainer);
var predictor = trainer.Train(new Runtime.TrainContext(trainRoles));
var scoreRoles = new RoleMappedData(concat, label: "Label", feature: "Features");
IDataScorerTransform scorer = ScoreUtils.GetScorer(predictor, scoreRoles, env, trainRoles.Schema);
var keyToValue = new KeyToValueTransform(env, scorer, "PredictedLabel");
var model = env.CreatePredictionEngine <IrisData, IrisPrediction>(keyToValue);
var testLoader = new TextLoader(env, MakeIrisTextLoaderArgs(), new MultiFileSource(dataPath));
var testData = testLoader.AsEnumerable <IrisData>(env, false);
foreach (var input in testData.Take(20))
{
var prediction = model.Predict(input);
Assert.True(prediction.PredictedLabel == input.Label);
}
}
}
public void Metacomponents()
{
var dataPath = GetDataPath(IrisDataPath);
using (var env = new TlcEnvironment())
{
var loader = new TextLoader(env, MakeIrisTextLoaderArgs(), new MultiFileSource(dataPath));
var term = new TermTransform(env, loader, "Label");
var concat = new ConcatTransform(env, term, "Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");
var trainer = new Ova(env, new Ova.Arguments
{
PredictorType = ComponentFactoryUtils.CreateFromFunction(
e => new FastTreeBinaryClassificationTrainer(e, new FastTreeBinaryClassificationTrainer.Arguments()))
});
IDataView trainData = trainer.Info.WantCaching ? (IDataView) new CacheDataView(env, concat, prefetch: null) : concat;
var trainRoles = new RoleMappedData(trainData, label: "Label", feature: "Features");
// Auto-normalization.
NormalizeTransform.CreateIfNeeded(env, ref trainRoles, trainer);
var predictor = trainer.Train(new TrainContext(trainRoles));
}
}
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.Categorical.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 = new Ova(mlContext, 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");
}
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 textLoader = GitHubLabelerTextLoaderFactory.CreateTextLoader(mlContext);
var trainingDataView = textLoader.Read(DataSetLocation);
// STEP 2: Common data process configuration with pipeline data transformations
var dataProcessPipeline = GitHubLabelerDataProcessPipelineFactory.CreateDataProcessPipeline(mlContext);
// (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 = new Ova(mlContext, averagedPerceptronBinaryTrainer);
break;
}
default:
break;
}
//Set the trainer/algorithm
var modelBuilder = new Common.ModelBuilder <GitHubIssue, GitHubIssuePrediction>(mlContext, dataProcessPipeline);
modelBuilder.AddTrainer(trainer);
modelBuilder.AddEstimator(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 crossValResults = modelBuilder.CrossValidateAndEvaluateMulticlassClassificationModel(trainingDataView, 6, "Label");
ConsoleHelper.PrintMulticlassClassificationFoldsAverageMetrics(trainer.ToString(), crossValResults);
// STEP 5: Train the model fitting to the DataSet
Console.WriteLine("=============== Training the model ===============");
modelBuilder.Train(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.."
};
var modelScorer = new ModelScorer <GitHubIssue, GitHubIssuePrediction>(mlContext, modelBuilder.TrainedModel);
var prediction = modelScorer.PredictSingle(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 ===============");
modelBuilder.SaveModelAsFile(ModelPath);
Common.ConsoleHelper.ConsoleWriteHeader("Training process finalized");
}
