public void TestPredictionForSingleIssue()
{
GitHubIssue singleIssue = new GitHubIssue()
{
ID = "Any-ID", Title = "Entity Framework crashes", Description = "When connecting to the database, EF is crashing"
};
//Predict label for single hard-coded issue
var prediction = _modelScorer.PredictSingle(singleIssue);
Console.WriteLine($"=============== Single Prediction - Result: {prediction.Area} ===============");
}
private static void Main(string[] args)
{
//Create the MLContext to share across components for deterministic results
MLContext mlContext = new MLContext(seed: 1); //Seed set to any number so you have a deterministic environment
//STEP 1: Common data loading
DataLoader dataLoader = new DataLoader(mlContext);
var fullData = dataLoader.GetDataView(DataPath);
(IDataView trainingDataView, IDataView testingDataView) = mlContext.Clustering.TrainTestSplit(fullData, testFraction: 0.2);
//STEP 2: Process data transformations in pipeline
var dataProcessor = new DataProcessor(mlContext);
var dataProcessPipeline = dataProcessor.DataProcessPipeline;
// (Optional) Peek data in training DataView after applying the ProcessPipeline's transformations
Common.ConsoleHelper.PeekDataViewInConsole <IrisData>(mlContext, trainingDataView, dataProcessPipeline, 10);
Common.ConsoleHelper.PeekVectorColumnDataInConsole(mlContext, "Features", trainingDataView, dataProcessPipeline, 10);
// STEP 3: Create and train the model
var modelBuilder = new ModelBuilder <IrisData, IrisPrediction>(mlContext, dataProcessPipeline);
var trainer = mlContext.Clustering.Trainers.KMeans(features: "Features", clustersCount: 3);
modelBuilder.AddTrainer(trainer);
var trainedModel = modelBuilder.Train(trainingDataView);
// STEP4: Evaluate accuracy of the model
var metrics = modelBuilder.EvaluateClusteringModel(testingDataView);
Common.ConsoleHelper.PrintClusteringMetrics(trainer.ToString(), metrics);
// STEP5: Save/persist the model as a .ZIP file
modelBuilder.SaveModelAsFile(ModelPath);
Console.WriteLine("=============== End of training process ===============");
Console.WriteLine("=============== Predict a cluster for a single case (Single Iris data sample) ===============");
// Test with one sample text
var sampleIrisData = new IrisData()
{
SepalLength = 3.3f,
SepalWidth = 1.6f,
PetalLength = 0.2f,
PetalWidth = 5.1f,
};
//Create the clusters: Create data files and plot a chart
var modelScorer = new ModelScorer <IrisData, IrisPrediction>(mlContext);
modelScorer.LoadModelFromZipFile(ModelPath);
var prediction = modelScorer.PredictSingle(sampleIrisData);
Console.WriteLine($"Cluster assigned for setosa flowers:" + prediction.SelectedClusterId);
Console.WriteLine("=============== End of process, hit any key to finish ===============");
Console.ReadKey();
}
public static void BuildAndTrainModel(string DataSetLocation, string ModelPath)
{
// 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
DataLoader dataLoader = new DataLoader(mlContext);
var trainingDataView = dataLoader.GetDataView(DataSetLocation);
// STEP 2: Common data process configuration with pipeline data transformations
var dataProcessor = new DataProcessor(mlContext);
var dataProcessPipeline = dataProcessor.DataProcessPipeline;
// (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: Set the selected training algorithm into the modelBuilder
var modelBuilder = new Common.ModelBuilder <GitHubIssue, GitHubIssuePrediction>(mlContext, dataProcessPipeline);
var trainer = mlContext.MulticlassClassification.Trainers.StochasticDualCoordinateAscent("Label", "Features");
modelBuilder.AddTrainer(trainer);
modelBuilder.AddEstimator(new KeyToValueEstimator(mlContext, "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("SdcaMultiClassTrainer", crossValResults);
// STEP 5: Train the model fitting to the DataSet
Console.WriteLine("=============== Training the model ===============");
modelBuilder.Train(trainingDataView);
// STEP 6: Save/persist the trained model to a .ZIP file
Console.WriteLine("=============== Saving the model to a file ===============");
modelBuilder.SaveModelAsFile(ModelPath);
// (OPTIONAL) Try/test a single prediction by loding the model from the file, first.
GitHubIssue issue = new GitHubIssue()
{
ID = "Any-ID", Title = "Entity Framework crashes", Description = "When connecting to the database, EF is crashing"
};
var modelScorer = new ModelScorer <GitHubIssue, GitHubIssuePrediction>(mlContext);
modelScorer.LoadModelFromZipFile(ModelPath);
var prediction = modelScorer.PredictSingle(issue);
Console.WriteLine($"=============== Single Prediction - Result: {prediction.Area} ===============");
//
Common.ConsoleHelper.ConsoleWriteHeader("Training process finalized");
}
public static void VisualizeSomePredictions(MLContext mlContext,
string modelName,
string testDataLocation,
ModelScorer <DemandObservation, DemandPrediction> modelScorer,
int numberOfPredictions)
{
//Make a few prediction tests
// Make the provided number of predictions and compare with observed data from the test dataset
var testData = ReadSampleDataFromCsvFile(testDataLocation, numberOfPredictions);
for (int i = 0; i < numberOfPredictions; i++)
{
var prediction = modelScorer.PredictSingle(testData[i]);
Common.ConsoleHelper.PrintRegressionPredictionVersusObserved(prediction.PredictedCount.ToString(),
testData[i].Count.ToString());
}
}
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");
}
