ch07 / ch08

.gitignore

@@ -30,3 +30,17 @@
 /ch06/CarApi/obj
 /ch06/CarApi/.vs/CarApi/FileContentIndex
 /ch06/CarApi/.vs
+/ch07/MachineLearning/.vs
+/ch07/MachineLearning/MachineLearning/bin/Debug/net8.0
+/ch07/MachineLearning/MachineLearning/obj
+/ch07/MachineLearning/SampleML_WebApi/bin/Debug/net6.0
+/ch07/MachineLearning/SampleML_WebApi/obj
+/ch08/SampleAspireApp/.vs/SampleAspireApp
+/ch08/SampleAspireApp/SampleAspireApp.ApiService/bin/Debug/net8.0
+/ch08/SampleAspireApp/SampleAspireApp.ApiService/obj
+/ch08/SampleAspireApp/SampleAspireApp.AppHost/bin/Debug/net8.0
+/ch08/SampleAspireApp/SampleAspireApp.AppHost/obj
+/ch08/SampleAspireApp/SampleAspireApp.ServiceDefaults/bin/Debug/net8.0
+/ch08/SampleAspireApp/SampleAspireApp.ServiceDefaults/obj
+/ch08/SampleAspireApp/SampleAspireApp.Web/bin/Debug/net8.0
+/ch08/SampleAspireApp/SampleAspireApp.Web/obj

ch07/MachineLearning/MachineLearning.sln

@@ -0,0 +1,37 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 17
+VisualStudioVersion = 17.10.34607.79
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "MachineLearning", "MachineLearning\MachineLearning.csproj", "{5D303F78-8327-46C0-8ECF-1E5B0CEA5A51}"
+EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "SampleML_WebApi", "SampleML_WebApi\SampleML_WebApi.csproj", "{0781E771-DF9B-4285-B542-5389BC7423E4}"
+EndProject
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "SampleML_AzureFunction", "SampleML_AzureFunction\SampleML_AzureFunction.csproj", "{99FA86FA-1751-47BE-95DC-771F32744A5B}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{5D303F78-8327-46C0-8ECF-1E5B0CEA5A51}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{5D303F78-8327-46C0-8ECF-1E5B0CEA5A51}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{5D303F78-8327-46C0-8ECF-1E5B0CEA5A51}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{5D303F78-8327-46C0-8ECF-1E5B0CEA5A51}.Release|Any CPU.Build.0 = Release|Any CPU
+		{0781E771-DF9B-4285-B542-5389BC7423E4}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{0781E771-DF9B-4285-B542-5389BC7423E4}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{0781E771-DF9B-4285-B542-5389BC7423E4}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{0781E771-DF9B-4285-B542-5389BC7423E4}.Release|Any CPU.Build.0 = Release|Any CPU
+		{99FA86FA-1751-47BE-95DC-771F32744A5B}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{99FA86FA-1751-47BE-95DC-771F32744A5B}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{99FA86FA-1751-47BE-95DC-771F32744A5B}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{99FA86FA-1751-47BE-95DC-771F32744A5B}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {AA8D540E-39C4-4B14-919E-3FE70BD177FA}
+	EndGlobalSection
+EndGlobal

ch07/MachineLearning/MachineLearning/MachineLearning.csproj

@@ -0,0 +1,17 @@
+<Project Sdk="Microsoft.NET.Sdk">
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net8.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+  <ItemGroup>
+    <PackageReference Include="Microsoft.ML" Version="3.0.1" />
+    <PackageReference Include="Microsoft.ML.FastTree" Version="3.0.1" />
+  </ItemGroup>
+  <ItemGroup Label="SampleML">
+    <None Include="SampleML.mlnet">
+      <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+</Project>

ch07/MachineLearning/MachineLearning/Program.cs

@@ -0,0 +1,11 @@
+//Load sample data
+using MachineLearning;
+
+var sampleData = new SampleML.ModelInput()
+{
+    Month = @"2-Jan",
+};
+
+//Load model and predict output
+var result = SampleML.Predict(sampleData);
+Console.WriteLine(result.ProductSales);

ch07/MachineLearning/MachineLearning/SampleML.consumption.cs

@@ -0,0 +1,134 @@
+// This file was auto-generated by ML.NET Model Builder.
+using Microsoft.ML;
+using Microsoft.ML.Data;
+using System;
+using System.Linq;
+using System.IO;
+using System.Collections.Generic;
+namespace MachineLearning
+{
+    public partial class SampleML
+    {
+        /// <summary>
+        /// model input class for SampleML.
+        /// </summary>
+        #region model input class
+        public class ModelInput
+        {
+            [LoadColumn(0)]
+            [ColumnName(@"Month")]
+            public string Month { get; set; }
+
+            [LoadColumn(1)]
+            [ColumnName(@"ProductSales")]
+            public float ProductSales { get; set; }
+
+        }
+
+        #endregion
+
+        /// <summary>
+        /// model output class for SampleML.
+        /// </summary>
+        #region model output class
+        public class ModelOutput
+        {
+            [ColumnName(@"Month")]
+            public float[] Month { get; set; }
+
+            [ColumnName(@"ProductSales")]
+            public uint ProductSales { get; set; }
+
+            [ColumnName(@"Features")]
+            public float[] Features { get; set; }
+
+            [ColumnName(@"PredictedLabel")]
+            public float PredictedLabel { get; set; }
+
+            [ColumnName(@"Score")]
+            public float[] Score { get; set; }
+
+        }
+
+        #endregion
+
+        private static string MLNetModelPath = Path.GetFullPath("SampleML.mlnet");
+
+        public static readonly Lazy<PredictionEngine<ModelInput, ModelOutput>> PredictEngine = new Lazy<PredictionEngine<ModelInput, ModelOutput>>(() => CreatePredictEngine(), true);
+
+
+        private static PredictionEngine<ModelInput, ModelOutput> CreatePredictEngine()
+        {
+            var mlContext = new MLContext();
+            ITransformer mlModel = mlContext.Model.Load(MLNetModelPath, out var _);
+            return mlContext.Model.CreatePredictionEngine<ModelInput, ModelOutput>(mlModel);
+        }
+
+        /// <summary>
+        /// Use this method to predict scores for all possible labels.
+        /// </summary>
+        /// <param name="input">model input.</param>
+        /// <returns><seealso cref=" ModelOutput"/></returns>
+        public static IOrderedEnumerable<KeyValuePair<string, float>> PredictAllLabels(ModelInput input)
+        {
+            var predEngine = PredictEngine.Value;
+            var result = predEngine.Predict(input);
+            return GetSortedScoresWithLabels(result);
+        }
+
+        /// <summary>
+        /// Map the unlabeled result score array to the predicted label names.
+        /// </summary>
+        /// <param name="result">Prediction to get the labeled scores from.</param>
+        /// <returns>Ordered list of label and score.</returns>
+        /// <exception cref="Exception"></exception>
+        public static IOrderedEnumerable<KeyValuePair<string, float>> GetSortedScoresWithLabels(ModelOutput result)
+        {
+            var unlabeledScores = result.Score;
+            var labelNames = GetLabels(result);
+
+            Dictionary<string, float> labledScores = new Dictionary<string, float>();
+            for (int i = 0; i < labelNames.Count(); i++)
+            {
+                // Map the names to the predicted result score array
+                var labelName = labelNames.ElementAt(i);
+                labledScores.Add(labelName.ToString(), unlabeledScores[i]);
+            }
+
+            return labledScores.OrderByDescending(c => c.Value);
+        }
+
+        /// <summary>
+        /// Get the ordered label names.
+        /// </summary>
+        /// <param name="result">Predicted result to get the labels from.</param>
+        /// <returns>List of labels.</returns>
+        /// <exception cref="Exception"></exception>
+        private static IEnumerable<string> GetLabels(ModelOutput result)
+        {
+            var schema = PredictEngine.Value.OutputSchema;
+
+            var labelColumn = schema.GetColumnOrNull("ProductSales");
+            if (labelColumn == null)
+            {
+                throw new Exception("ProductSales column not found. Make sure the name searched for matches the name in the schema.");
+            }
+
+            // Key values contains an ordered array of the possible labels. This allows us to map the results to the correct label value.
+            var keyNames = new VBuffer<float>();
+            labelColumn.Value.GetKeyValues(ref keyNames);
+            return keyNames.DenseValues().Select(x => x.ToString());
+        }
+
+        /// <summary>
+        /// Use this method to predict on <see cref="ModelInput"/>.
+        /// </summary>
+        /// <param name="input">model input.</param>
+        /// <returns><seealso cref=" ModelOutput"/></returns>
+        public static ModelOutput Predict(ModelInput input)
+        {
+            var predEngine = PredictEngine.Value;
+            return predEngine.Predict(input);
+        }
+    }
+}

ch07/MachineLearning/MachineLearning/SampleML.evaluate.cs

@@ -0,0 +1,59 @@
+// This file was auto-generated by ML.NET Model Builder.
+
+using Microsoft.ML.Data;
+using Microsoft.ML;
+using System;
+using System.Collections.Generic;
+using System.Linq;
+
+namespace MachineLearning
+{
+    public partial class SampleML
+    {
+        /// <summary>
+        /// Permutation feature importance (PFI) is a technique to determine the importance 
+        /// of features in a trained machine learning model. PFI works by taking a labeled dataset, 
+        /// choosing a feature, and permuting the values for that feature across all the examples, 
+        /// so that each example now has a random value for the feature and the original values for all other features.
+        /// The evaluation metric (e.g. R-squared) is then calculated for this modified dataset, 
+        /// and the change in the evaluation metric from the original dataset is computed. 
+        /// The larger the change in the evaluation metric, the more important the feature is to the model.
+        /// 
+        /// PFI typically takes a long time to compute, as the evaluation metric is calculated 
+        /// many times to determine the importance of each feature. 
+        /// 
+        /// </summary>
+        /// <param name="mlContext">The common context for all ML.NET operations.</param>
+        /// <param name="trainData">IDataView used to evaluate the model.</param>
+        /// <param name="model">Model to evaluate.</param>
+        /// <param name="labelColumnName">Label column being predicted.</param>
+        /// <returns>A list of each feature and its importance.</returns>
+        public static List<Tuple<string, double>> CalculatePFI(MLContext mlContext, IDataView trainData, ITransformer model, string labelColumnName)
+        {
+            var preprocessedTrainData = model.Transform(trainData);
+
+            var permutationFeatureImportance =
+         mlContext.MulticlassClassification
+         .PermutationFeatureImportance(
+                 model,
+                 preprocessedTrainData,
+                 labelColumnName: labelColumnName);
+
+            var featureImportanceMetrics =
+                 permutationFeatureImportance
+                 .Select((kvp) => new { kvp.Key, kvp.Value.MacroAccuracy })
+                 .OrderByDescending(myFeatures => Math.Abs(myFeatures.MacroAccuracy.Mean));
+
+            var featurePFI = new List<Tuple<string, double>>();
+            foreach (var feature in featureImportanceMetrics)
+            {
+                var pfiValue = Math.Abs(feature.MacroAccuracy.Mean);
+                featurePFI.Add(new Tuple<string, double>(feature.Key, pfiValue));
+            }
+
+            return featurePFI;
+        }
+    }
+}
+
+