private static void Main(string[] args)
{
// Create ML.NET context/environment
using (var env = new LocalEnvironment())
{
// Create DataReader with data schema mapped to file's columns
var reader = new TextLoader(env,
new TextLoader.Arguments()
{
Separator = "\t",
HasHeader = true,
Column = new[]
{
new TextLoader.Column("Label", DataKind.R4, 0),
new TextLoader.Column("SepalLength", DataKind.R4, 1),
new TextLoader.Column("SepalWidth", DataKind.R4, 2),
new TextLoader.Column("PetalLength", DataKind.R4, 3),
new TextLoader.Column("PetalWidth", DataKind.R4, 4),
}
});
//Load training data
IDataView trainingDataView = reader.Read(new MultiFileSource(DataPath));
// Transform your data and add a learner
// Add a learning algorithm to the pipeline. e.g.(What are characteristics of iris is this?)
// Convert the Label back into original text (after converting to number in step 3)
var pipeline = new ConcatEstimator(env, "Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth")
.Append(new KMeansPlusPlusTrainer(env, "Features", clustersCount: 3));
// Create and train the model
Console.WriteLine("=============== Create and Train the Model ===============");
var model = pipeline.Fit(trainingDataView);
Console.WriteLine("=============== End of training ===============");
Console.WriteLine();
// Test with one sample text
var sampleIrisData = new IrisData()
{
SepalLength = 3.3f,
SepalWidth = 1.6f,
PetalLength = 0.2f,
PetalWidth = 5.1f,
};
var prediction = model.MakePredictionFunction <IrisData, IrisPrediction>(env).Predict(
sampleIrisData);
Console.WriteLine($"Clusters assigned for setosa flowers:" + prediction.SelectedClusterId);
// Save model to .ZIP file
SaveModelAsFile(env, model);
// Predict again but now testing the model loading from the .ZIP file
PredictWithModelLoadedFromFile(sampleIrisData);
Console.WriteLine("=============== End of process, hit any key to finish ===============");
Console.ReadKey();
}
}
private static void PredictWithModelLoadedFromFile(IrisData sampleData)
{
// Test with Loaded Model from .zip file
using (var env = new LocalEnvironment())
{
ITransformer loadedModel;
using (var stream = new FileStream(ModelPath, FileMode.Open, FileAccess.Read, FileShare.Read))
{
loadedModel = TransformerChain.LoadFrom(env, stream);
}
// Create prediction engine and make prediction.
var prediction = loadedModel.MakePredictionFunction <IrisData, IrisPrediction>(env).Predict(
new IrisData()
{
SepalLength = 3.3f,
SepalWidth = 1.6f,
PetalLength = 0.2f,
PetalWidth = 5.1f,
});
Console.WriteLine();
Console.WriteLine($"Clusters assigned for setosa flowers:" + prediction.SelectedClusterId);
}
}
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();
}
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 configuration
IDataView fullData = mlContext.Data.ReadFromTextFile(path: DataPath,
columns: new[]
{
new TextLoader.Column(DefaultColumnNames.Label, DataKind.R4, 0),
new TextLoader.Column(nameof(IrisData.SepalLength), DataKind.R4, 1),
new TextLoader.Column(nameof(IrisData.SepalWidth), DataKind.R4, 2),
new TextLoader.Column(nameof(IrisData.PetalLength), DataKind.R4, 3),
new TextLoader.Column(nameof(IrisData.PetalWidth), DataKind.R4, 4),
},
hasHeader: true,
separatorChar: '\t');
//Split dataset in two parts: TrainingDataset (80%) and TestDataset (20%)
(IDataView trainingDataView, IDataView testingDataView) = mlContext.Clustering.TrainTestSplit(fullData, testFraction: 0.2);
//STEP 2: Process data transformations in pipeline
var dataProcessPipeline = mlContext.Transforms.Concatenate(DefaultColumnNames.Features, nameof(IrisData.SepalLength), nameof(IrisData.SepalWidth), nameof(IrisData.PetalLength), nameof(IrisData.PetalWidth));
// (Optional) Peek data in training DataView after applying the ProcessPipeline's transformations
Common.ConsoleHelper.PeekDataViewInConsole <IrisData>(mlContext, trainingDataView, dataProcessPipeline, 10);
Common.ConsoleHelper.PeekVectorColumnDataInConsole(mlContext, DefaultColumnNames.Features, trainingDataView, dataProcessPipeline, 10);
// STEP 3: Create and train the model
var trainer = mlContext.Clustering.Trainers.KMeans(featureColumn: DefaultColumnNames.Features, clustersCount: 3);
var trainingPipeline = dataProcessPipeline.Append(trainer);
var trainedModel = trainingPipeline.Fit(trainingDataView);
// STEP4: Evaluate accuracy of the model
IDataView predictions = trainedModel.Transform(testingDataView);
var metrics = mlContext.Clustering.Evaluate(predictions, score: DefaultColumnNames.Score, features: DefaultColumnNames.Features);
ConsoleHelper.PrintClusteringMetrics(trainer.ToString(), metrics);
// STEP5: Save/persist the model as a .ZIP file
using (var fs = new FileStream(ModelPath, FileMode.Create, FileAccess.Write, FileShare.Write))
mlContext.Model.Save(trainedModel, fs);
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,
};
using (var stream = new FileStream(ModelPath, FileMode.Open, FileAccess.Read, FileShare.Read))
{
ITransformer model = mlContext.Model.Load(stream);
// Create prediction engine related to the loaded trained model
var predEngine = model.CreatePredictionEngine <IrisData, IrisPrediction>(mlContext);
//Score
var resultprediction = predEngine.Predict(sampleIrisData);
Console.WriteLine($"Cluster assigned for setosa flowers:" + resultprediction.SelectedClusterId);
}
Console.WriteLine("=============== End of process, hit any key to finish ===============");
Console.ReadKey();
}
