Source code for updated clustering tutorial (dotnet#521)

ik-dotnet · Dec 17, 2018 · b4adcf7 · b4adcf7
1 parent b48e921
commit b4adcf7
Show file tree

Hide file tree

Showing 5 changed files with 170 additions and 0 deletions.
diff --git a/machine-learning/tutorials/IrisFlowerClustering.sln b/machine-learning/tutorials/IrisFlowerClustering.sln
@@ -0,0 +1,25 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio 15
+VisualStudioVersion = 15.0.28307.168
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "IrisFlowerClustering", "IrisFlowerClustering\IrisFlowerClustering.csproj", "{B1297D9B-46A6-4A03-A04E-65B2FAC0B687}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{B1297D9B-46A6-4A03-A04E-65B2FAC0B687}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{B1297D9B-46A6-4A03-A04E-65B2FAC0B687}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{B1297D9B-46A6-4A03-A04E-65B2FAC0B687}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{B1297D9B-46A6-4A03-A04E-65B2FAC0B687}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {30D318E3-A018-46F2-8D53-F72211D6BA70}
+	EndGlobalSection
+EndGlobal
diff --git a/machine-learning/tutorials/IrisFlowerClustering/IrisData.cs b/machine-learning/tutorials/IrisFlowerClustering/IrisData.cs
@@ -0,0 +1,32 @@
+// <SnippetUsings>
+using Microsoft.ML.Runtime.Api;
+// </SnippetUsings>
+
+namespace IrisFlowerClustering
+{
+    // <SnippetClassDefinitions>
+    public class IrisData
+    {
+        [Column("0")]
+        public float SepalLength;
+
+        [Column("1")]
+        public float SepalWidth;
+
+        [Column("2")]
+        public float PetalLength;
+
+        [Column("3")]
+        public float PetalWidth;
+    }
+
+    public class ClusterPrediction
+    {
+        [ColumnName("PredictedLabel")]
+        public uint PredictedClusterId;
+
+        [ColumnName("Score")]
+        public float[] Distances;
+    }
+    // </SnippetClassDefinitions>
+}
diff --git a/machine-learning/tutorials/IrisFlowerClustering/IrisFlowerClustering.csproj b/machine-learning/tutorials/IrisFlowerClustering/IrisFlowerClustering.csproj
@@ -0,0 +1,22 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>netcoreapp2.2</TargetFramework>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <Folder Include="Data\" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.ML" Version="0.8.0" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="Data\iris.data">
+      <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+</Project>
diff --git a/machine-learning/tutorials/IrisFlowerClustering/Program.cs b/machine-learning/tutorials/IrisFlowerClustering/Program.cs
@@ -0,0 +1,74 @@
+// <SnippetUsingsForPaths>
+using System;
+using System.IO;
+// </SnippetUsingsForPaths>
+
+// <SnippetMLUsings>
+using Microsoft.ML;
+using Microsoft.ML.Runtime.Data;
+// </SnippetMLUsings>
+
+namespace IrisFlowerClustering
+{
+    class Program
+    {
+        // <SnippetPaths>
+        static readonly string _dataPath = Path.Combine(Environment.CurrentDirectory, "Data", "iris.data");
+        static readonly string _modelPath = Path.Combine(Environment.CurrentDirectory, "Data", "IrisClusteringModel.zip");
+        // </SnippetPaths>
+
+        static void Main(string[] args)
+        {
+            // <SnippetCreateContext>
+            var mlContext = new MLContext(seed: 0);
+            // </SnippetCreateContext>
+
+            // <SnippetSetupTextLoader>
+            TextLoader textLoader = mlContext.Data.TextReader(new TextLoader.Arguments()
+            {
+                Separator = ",",
+                HasHeader = false,
+                Column = new[]
+                            {
+                                new TextLoader.Column("SepalLength", DataKind.R4, 0),
+                                new TextLoader.Column("SepalWidth", DataKind.R4, 1),
+                                new TextLoader.Column("PetalLength", DataKind.R4, 2),
+                                new TextLoader.Column("PetalWidth", DataKind.R4, 3)
+                            }
+            });
+            // </SnippetSetupTextLoader>
+
+            // <SnippetCreateDataView>
+            IDataView dataView = textLoader.Read(_dataPath);
+            // </SnippetCreateDataView>
+
+            // <SnippetCreatePipeline>
+            string featuresColumnName = "Features";
+            var pipeline = mlContext.Transforms
+                .Concatenate(featuresColumnName, "SepalLength", "SepalWidth", "PetalLength", "PetalWidth")
+                .Append(mlContext.Clustering.Trainers.KMeans(featuresColumnName, clustersCount: 3));
+            // </SnippetCreatePipeline>
+
+            // <SnippetTrainModel>
+            var model = pipeline.Fit(dataView);
+            // </SnippetTrainModel>
+
+            // <SnippetSaveModel>
+            using (var fileStream = new FileStream(_modelPath, FileMode.Create, FileAccess.Write, FileShare.Write))
+            {
+                mlContext.Model.Save(model, fileStream);
+            }
+            // </SnippetSaveModel>
+
+            // <SnippetPredictor>
+            var predictor = model.MakePredictionFunction<IrisData, ClusterPrediction>(mlContext);
+            // </SnippetPredictor>
+
+            // <SnippetPredictionExample>
+            var prediction = predictor.Predict(TestIrisData.Setosa);
+            Console.WriteLine($"Cluster: {prediction.PredictedClusterId}");
+            Console.WriteLine($"Distances: {string.Join(" ", prediction.Distances)}");
+            // </SnippetPredictionExample>
+        }
+    }
+}
diff --git a/machine-learning/tutorials/IrisFlowerClustering/TestIrisData.cs b/machine-learning/tutorials/IrisFlowerClustering/TestIrisData.cs
@@ -0,0 +1,17 @@
+namespace IrisFlowerClustering
+{
+    // <SnippetStatic>
+    static class TestIrisData
+    // </SnippetStatic>
+    {
+        // <SnippetTestData>
+        internal static readonly IrisData Setosa = new IrisData
+        {
+            SepalLength = 5.1f,
+            SepalWidth = 3.5f,
+            PetalLength = 1.4f,
+            PetalWidth = 0.2f
+        };
+        // </SnippetTestData>
+    }
+}