From cde4fca02029cf3552cb63c050d3002bab68828f Mon Sep 17 00:00:00 2001
From: Serghei Cebotari <serghei@cebotari.ru>
Date: Wed, 20 Sep 2023 13:46:55 +0300
Subject: Solution organize

---
 RhSolutions.ML.Lib/Product.cs                | 16 +++++++++++
 RhSolutions.ML.Lib/RhSolutions.ML.Lib.csproj | 13 +++++++++
 RhSolutions.ML.Lib/RhSolutionsMLBuilder.cs   | 42 ++++++++++++++++++++++++++++
 3 files changed, 71 insertions(+)
 create mode 100644 RhSolutions.ML.Lib/Product.cs
 create mode 100644 RhSolutions.ML.Lib/RhSolutions.ML.Lib.csproj
 create mode 100644 RhSolutions.ML.Lib/RhSolutionsMLBuilder.cs

(limited to 'RhSolutions.ML.Lib')

diff --git a/RhSolutions.ML.Lib/Product.cs b/RhSolutions.ML.Lib/Product.cs
new file mode 100644
index 0000000..99040fc
--- /dev/null
+++ b/RhSolutions.ML.Lib/Product.cs
@@ -0,0 +1,16 @@
+using Microsoft.ML.Data;
+namespace RhSolutions.ML;
+
+public class Product
+{
+	[LoadColumn(0)]
+	public string? Name { get; set; }
+	[LoadColumn(1)]
+	public string? Type { get; set; }
+}
+
+public class TypePrediction
+{
+	[ColumnName("PredictedLabel")]
+	public string? Type { get; set; }
+}
\ No newline at end of file
diff --git a/RhSolutions.ML.Lib/RhSolutions.ML.Lib.csproj b/RhSolutions.ML.Lib/RhSolutions.ML.Lib.csproj
new file mode 100644
index 0000000..928fc99
--- /dev/null
+++ b/RhSolutions.ML.Lib/RhSolutions.ML.Lib.csproj
@@ -0,0 +1,13 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <TargetFramework>net7.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.ML" Version="2.0.1" />
+  </ItemGroup>
+
+</Project>
diff --git a/RhSolutions.ML.Lib/RhSolutionsMLBuilder.cs b/RhSolutions.ML.Lib/RhSolutionsMLBuilder.cs
new file mode 100644
index 0000000..be2e2a6
--- /dev/null
+++ b/RhSolutions.ML.Lib/RhSolutionsMLBuilder.cs
@@ -0,0 +1,42 @@
+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"));
+	}
+}
-- 
cgit v1.2.3