60 lines
2.4 KiB
C#
60 lines
2.4 KiB
C#
using Microsoft.ML;
|
|
using Microsoft.ML.Data;
|
|
|
|
namespace RhSolutions.ML.Lib;
|
|
|
|
public class RhSolutionsMLBuilder
|
|
{
|
|
private static string _appPath = Path.GetDirectoryName(Environment.GetCommandLineArgs()[0]) ?? ".";
|
|
private static string _testDataPath = Path.Combine(_appPath, "..", "..", "..", "..", "TestData", "*");
|
|
|
|
private static MLContext _mlContext = new MLContext(seed: 0);
|
|
|
|
public static void RebuildModel()
|
|
{
|
|
var _trainDataView = _mlContext.Data.LoadFromTextFile<Product>(
|
|
Path.Combine(_appPath, "..", "..", "..", "..", "TrainData", "*"), hasHeader: false);
|
|
var pipeline = ProcessData();
|
|
BuildAndTrainModel(_trainDataView, pipeline, out ITransformer _trainedModel);
|
|
SaveModelAsFile(_mlContext, _trainDataView.Schema, _trainedModel);
|
|
}
|
|
|
|
public static MulticlassClassificationMetrics EvaluateModel()
|
|
{
|
|
var testDataView = _mlContext.Data.LoadFromTextFile<Product>(_testDataPath, hasHeader: false, separatorChar: ';');
|
|
MLContext mlContext = new(seed: 0);
|
|
string modelPath = Path.Combine(_appPath, "..", "..", "..", "..", "Models", "model.zip");
|
|
var trainedModel = mlContext.Model.Load(modelPath, out _);
|
|
return _mlContext.MulticlassClassification.Evaluate(trainedModel.Transform(testDataView));
|
|
}
|
|
|
|
private static IEstimator<ITransformer> ProcessData()
|
|
{
|
|
var pipeline = _mlContext.Transforms.Conversion.MapValueToKey(inputColumnName: "Type", outputColumnName: "Label")
|
|
.Append(_mlContext.Transforms.Text.FeaturizeText(inputColumnName: "Name", outputColumnName: "NameFeaturized"))
|
|
.Append(_mlContext.Transforms.Concatenate("Features", "NameFeaturized"))
|
|
.AppendCacheCheckpoint(_mlContext);
|
|
return pipeline;
|
|
}
|
|
|
|
private static IEstimator<ITransformer> BuildAndTrainModel(IDataView trainingDataView, IEstimator<ITransformer> pipeline, out ITransformer trainedModel)
|
|
{
|
|
var trainingPipeline = pipeline.Append(_mlContext.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features"))
|
|
.Append(_mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
|
|
|
|
trainedModel = trainingPipeline.Fit(trainingDataView);
|
|
return trainingPipeline;
|
|
}
|
|
|
|
private static void SaveModelAsFile(MLContext mlContext, DataViewSchema trainingDataViewSchema, ITransformer model)
|
|
{
|
|
string path = Path.Combine(_appPath, "..", "..", "..", "..", "Models");
|
|
if (!Directory.Exists(path))
|
|
{
|
|
Directory.CreateDirectory(path);
|
|
}
|
|
mlContext.Model.Save(model, trainingDataViewSchema,
|
|
Path.Combine(path, "model.zip"));
|
|
}
|
|
}
|