43 lines
1.7 KiB
C#
43 lines
1.7 KiB
C#
using Microsoft.ML;
|
|
|
|
namespace RhSolutions.ML.Lib;
|
|
|
|
public class RhSolutionsMLBuilder
|
|
{
|
|
private static string _appPath = Path.GetDirectoryName(Environment.GetCommandLineArgs()[0]) ?? ".";
|
|
|
|
private static MLContext _mlContext = new MLContext(seed: 0);
|
|
|
|
public static void RebuildModel()
|
|
{
|
|
var _trainDataView = _mlContext.Data.LoadFromTextFile<Product>(
|
|
Path.Combine(_appPath, "..", "..", "..", "..", "Data", "*"), hasHeader: false);
|
|
var pipeline = ProcessData();
|
|
BuildAndTrainModel(_trainDataView, pipeline, out ITransformer trainedModel);
|
|
SaveModelAsFile(_mlContext, _trainDataView.Schema, trainedModel);
|
|
}
|
|
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)
|
|
{
|
|
mlContext.Model.Save(model, trainingDataViewSchema,
|
|
Path.Combine(_appPath, "..", "..", "..", "..", "Models", "model.zip"));
|
|
}
|
|
}
|