Add NaiveBayes sample & docs

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/MulticlassClassification.ttinclude

@@ -3,7 +3,6 @@ using System.Collections.Generic;
 using System.Linq;
 using Microsoft.ML;
 using Microsoft.ML.Data;
-using Microsoft.ML.SamplesUtils;
 <# if (TrainerOptions != null) { #>
 <#=OptionsInclude#>
 <# } #>
@@ -67,15 +66,20 @@ namespace Samples.Dynamic.Trainers.MulticlassClassification
 
             // Evaluate the overall metrics
             var metrics = mlContext.MulticlassClassification.Evaluate(transformedTestData);
-            ConsoleUtils.PrintMetrics(metrics);
+            Console.WriteLine($"Micro Accuracy: {metrics.MicroAccuracy:F2}");
+            Console.WriteLine($"Macro Accuracy: {metrics.MacroAccuracy:F2}");
+            Console.WriteLine($"Log Loss: {metrics.LogLoss:F2}");
+            Console.WriteLine($"Log Loss Reduction: {metrics.LogLossReduction:F2}");
+
 
             <#=ExpectedOutput#>
         }
 
+        <#=DataGenerationComments#>
         private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
         {
             var random = new Random(seed);
-            float randomFloat() => (float)random.NextDouble();
+            float randomFloat() => (float)(random.NextDouble() - 0.5);
             for (int i = 0; i < count; i++)
             {
                 // Generate Labels that are integers 1, 2 or 3

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/NaiveBayes.cs

@@ -0,0 +1,111 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using Microsoft.ML;
+using Microsoft.ML.Data;
+
+namespace Samples.Dynamic.Trainers.MulticlassClassification
+{
+    public static class NaiveBayes
+    {
+        // Naive Bayes classifier is based on Bayes' theorem. 
+        // It assumes independence among the presence of features in a class even though they may be dependent on each other.
+        // It is  a multi-class trainer that accepts binary feature values of type float, i.e., feature values are either true or false.
+        // Specifically a feature value greater than zero is treated as true, zero or less is treated as false.
+        public static void Example()
+        {
+            // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+            // as a catalog of available operations and as the source of randomness.
+            // Setting the seed to a fixed number in this example to make outputs deterministic.
+            var mlContext = new MLContext(seed: 0);
+
+            // Create a list of training data points.
+            var dataPoints = GenerateRandomDataPoints(1000);
+
+            // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
+            var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);
+
+            // Define the trainer.
+            var pipeline =
+                    // Convert the string labels into key types.
+                    mlContext.Transforms.Conversion.MapValueToKey("Label")
+                    // Apply NaiveBayes multiclass trainer.
+                    .Append(mlContext.MulticlassClassification.Trainers.NaiveBayes());
+
+            // Train the model.
+            var model = pipeline.Fit(trainingData);
+
+            // Create testing data. Use different random seed to make it different from training data.
+            var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));
+
+            // Run the model on test data set.
+            var transformedTestData = model.Transform(testData);
+
+            // Convert IDataView object to a list.
+            var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();
+
+            // Look at 5 predictions
+            foreach (var p in predictions.Take(5))
+                Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");
+
+            // Expected output:
+            //   Label: 1, Prediction: 1
+            //   Label: 2, Prediction: 2
+            //   Label: 3, Prediction: 3
+            //   Label: 2, Prediction: 2
+            //   Label: 3, Prediction: 3
+
+            // Evaluate the overall metrics
+            var metrics = mlContext.MulticlassClassification.Evaluate(transformedTestData);
+            Console.WriteLine($"Micro Accuracy: {metrics.MicroAccuracy:F2}");
+            Console.WriteLine($"Macro Accuracy: {metrics.MacroAccuracy:F2}");
+            Console.WriteLine($"Log Loss: {metrics.LogLoss:F2}");
+            Console.WriteLine($"Log Loss Reduction: {metrics.LogLossReduction:F2}");
+
+
+            // Expected output:
+            //  Micro Accuracy: 0.88
+            //  Macro Accuracy: 0.88
+            //  Log Loss: 34.54
+            //  Log Loss Reduction: -30.47
+        }
+
+
+        // Generates random uniform doubles in [-0.5, 0.5) range with labels 1, 2 or 3.
+        // For NaiveBayes values greater than zero are treated as true, zero or less are treated as false.
+        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
+        {
+            var random = new Random(seed);
+            float randomFloat() => (float)(random.NextDouble() - 0.5);
+            for (int i = 0; i < count; i++)
+            {
+                // Generate Labels that are integers 1, 2 or 3
+                var label = random.Next(1, 4);
+                yield return new DataPoint
+                {
+                    Label = (uint)label,
+                    // Create random features that are correlated with the label.
+                    // The feature values are slightly increased by adding a constant multiple of label.
+                    Features = Enumerable.Repeat(label, 20).Select(x => randomFloat() + label * 0.2f).ToArray()
+                };
+            }
+        }
+
+        // Example with label and 20 feature values. A data set is a collection of such examples.
+        private class DataPoint
+        {
+            public uint Label { get; set; }
+            [VectorType(20)]
+            public float[] Features { get; set; }
+        }
+
+        // Class used to capture predictions.
+        private class Prediction
+        {
+            // Original label.
+            public uint Label { get; set; }
+            // Predicted label from the trainer.
+            public uint PredictedLabel { get; set; }
+        }
+    }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/NaiveBayes.tt

@@ -0,0 +1,31 @@
+<#@ include file="MulticlassClassification.ttinclude"#>
+<#+
+string ClassName="NaiveBayes";
+string Trainer = "NaiveBayes";
+string MetaTrainer = null;
+string TrainerOptions = null;
+
+string OptionsInclude = "";
+string Comments= @"
+        // Naive Bayes classifier is based on Bayes' theorem. 
+        // It assumes independence among the presence of features in a class even though they may be dependent on each other.
+        // It is  a multi-class trainer that accepts binary feature values of type float, i.e., feature values are either true or false.
+        // Specifically a feature value greater than zero is treated as true, zero or less is treated as false.";
+
+string DataGenerationComments= @"
+        // Generates random uniform doubles in [-0.5, 0.5) range with labels 1, 2 or 3.
+        // For NaiveBayes values greater than zero are treated as true, zero or less are treated as false.";
+
+string ExpectedOutputPerInstance= @"// Expected output:
+            //   Label: 1, Prediction: 1
+            //   Label: 2, Prediction: 2
+            //   Label: 3, Prediction: 3
+            //   Label: 2, Prediction: 2
+            //   Label: 3, Prediction: 3";
+
+string ExpectedOutput = @"// Expected output:
+            //  Micro Accuracy: 0.88
+            //  Macro Accuracy: 0.88
+            //  Log Loss: 34.54
+            //  Log Loss Reduction: -30.47";
+#>

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/OneVersusAll.cs

@@ -3,7 +3,6 @@
 using System.Linq;
 using Microsoft.ML;
 using Microsoft.ML.Data;
-using Microsoft.ML.SamplesUtils;
 
 namespace Samples.Dynamic.Trainers.MulticlassClassification
 {
@@ -54,7 +53,11 @@ public static void Example()
 
             // Evaluate the overall metrics
             var metrics = mlContext.MulticlassClassification.Evaluate(transformedTestData);
-            ConsoleUtils.PrintMetrics(metrics);
+            Console.WriteLine($"Micro Accuracy: {metrics.MicroAccuracy:F2}");
+            Console.WriteLine($"Macro Accuracy: {metrics.MacroAccuracy:F2}");
+            Console.WriteLine($"Log Loss: {metrics.LogLoss:F2}");
+            Console.WriteLine($"Log Loss Reduction: {metrics.LogLossReduction:F2}");
+
 
             // Expected output:
             //  Micro Accuracy: 0.90
@@ -63,10 +66,12 @@ public static void Example()
             //  Log Loss Reduction: 0.67
         }
 
+
+        // Generates random uniform doubles in [-0.5, 0.5) range with labels 1, 2 or 3.
         private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
         {
             var random = new Random(seed);
-            float randomFloat() => (float)random.NextDouble();
+            float randomFloat() => (float)(random.NextDouble() - 0.5);
             for (int i = 0; i < count; i++)
             {
                 // Generate Labels that are integers 1, 2 or 3

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/OneVersusAll.tt

@@ -7,6 +7,8 @@ string TrainerOptions = null;
 
 string OptionsInclude = "";
 string Comments= "";
+string DataGenerationComments= @"
+        // Generates random uniform doubles in [-0.5, 0.5) range with labels 1, 2 or 3.";
 
 string ExpectedOutputPerInstance= @"// Expected output:
             //   Label: 1, Prediction: 1

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/PairwiseCoupling.cs

@@ -3,7 +3,6 @@
 using System.Linq;
 using Microsoft.ML;
 using Microsoft.ML.Data;
-using Microsoft.ML.SamplesUtils;
 
 namespace Samples.Dynamic.Trainers.MulticlassClassification
 {
@@ -54,7 +53,11 @@ public static void Example()
 
             // Evaluate the overall metrics
             var metrics = mlContext.MulticlassClassification.Evaluate(transformedTestData);
-            ConsoleUtils.PrintMetrics(metrics);
+            Console.WriteLine($"Micro Accuracy: {metrics.MicroAccuracy:F2}");
+            Console.WriteLine($"Macro Accuracy: {metrics.MacroAccuracy:F2}");
+            Console.WriteLine($"Log Loss: {metrics.LogLoss:F2}");
+            Console.WriteLine($"Log Loss Reduction: {metrics.LogLossReduction:F2}");
+
 
             // Expected output:
             //  Micro Accuracy: 0.90
@@ -63,10 +66,12 @@ public static void Example()
             //  Log Loss Reduction: 0.67
         }
 
+
+        // Generates random uniform doubles in [-0.5, 0.5) range with labels 1, 2 or 3.
         private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
         {
             var random = new Random(seed);
-            float randomFloat() => (float)random.NextDouble();
+            float randomFloat() => (float)(random.NextDouble() - 0.5);
             for (int i = 0; i < count; i++)
             {
                 // Generate Labels that are integers 1, 2 or 3
@@ -76,7 +81,7 @@ private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int se
                     Label = (uint)label,
                     // Create random features that are correlated with the label.
                     // The feature values are slightly increased by adding a constant multiple of label.
-                    Features = Enumerable.Repeat(label, 20).Select(x => randomFloat() + label * 0.1f).ToArray()
+                    Features = Enumerable.Repeat(label, 20).Select(x => randomFloat() + label * 0.2f).ToArray()
                 };
             }
         }

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/PairwiseCoupling.tt

@@ -7,6 +7,8 @@ string TrainerOptions = null;
 
 string OptionsInclude = "";
 string Comments= "";
+string DataGenerationComments= @"
+        // Generates random uniform doubles in [-0.5, 0.5) range with labels 1, 2 or 3.";
 
 string ExpectedOutputPerInstance= @"// Expected output:
             //   Label: 1, Prediction: 1

docs/samples/Microsoft.ML.Samples/Microsoft.ML.Samples.csproj

@@ -90,6 +90,10 @@
       <Generator>TextTemplatingFileGenerator</Generator>
       <LastGenOutput>LbfgsLogisticRegression.cs</LastGenOutput>
     </None>
+    <None Update="Dynamic\Trainers\MulticlassClassification\NaiveBayes.tt">
+      <LastGenOutput>NaiveBayes.cs</LastGenOutput>
+      <Generator>TextTemplatingFileGenerator</Generator>
+    </None>
     <None Update="Dynamic\Trainers\MulticlassClassification\PairwiseCoupling.tt">
       <LastGenOutput>PairwiseCoupling.cs</LastGenOutput>
       <Generator>TextTemplatingFileGenerator</Generator>
@@ -161,6 +165,11 @@
       <AutoGen>True</AutoGen>
       <DependentUpon>OneVersusAll.tt</DependentUpon>
     </Compile>
+    <Compile Update="Dynamic\Trainers\MulticlassClassification\NaiveBayes.cs">
+      <DesignTime>True</DesignTime>
+      <AutoGen>True</AutoGen>
+      <DependentUpon>NaiveBayes.tt</DependentUpon>
+    </Compile>
     <Compile Update="Dynamic\Trainers\Regression\OnlineGradientDescent.cs">
       <DesignTime>True</DesignTime>
       <AutoGen>True</AutoGen>

src/Microsoft.ML.StandardTrainers/Standard/MulticlassClassification/MulticlassNaiveBayesTrainer.cs

@@ -17,7 +17,7 @@
     new[] { typeof(SignatureMulticlassClassifierTrainer), typeof(SignatureTrainer) },
     NaiveBayesMulticlassTrainer.UserName,
     NaiveBayesMulticlassTrainer.LoadName,
-    NaiveBayesMulticlassTrainer.ShortName, DocName = "trainer/NaiveBayes.md")]
+    NaiveBayesMulticlassTrainer.ShortName)]
 
 [assembly: LoadableClass(typeof(NaiveBayesMulticlassModelParameters), null, typeof(SignatureLoadModel),
     "Multi Class Naive Bayes predictor", NaiveBayesMulticlassModelParameters.LoaderSignature)]
@@ -26,6 +26,12 @@
 
 namespace Microsoft.ML.Trainers
 {
+    /// <summary>
+    /// Naive Bayes classifier is based on Bayes' theorem. It assumes independence among the presence of features
+    /// in a class even though they may be dependent on each other. It is a multi-class trainer that accepts
+    /// binary feature values of type float, i.e., feature values are either true or false, specifically a
+    /// feature value greater than zero is treated as true.
+    /// </summary>
     public sealed class NaiveBayesMulticlassTrainer : TrainerEstimatorBase<MulticlassPredictionTransformer<NaiveBayesMulticlassModelParameters>, NaiveBayesMulticlassModelParameters>
     {
         internal const string LoadName = "MultiClassNaiveBayes";

src/Microsoft.ML.StandardTrainers/StandardTrainersCatalog.cs

@@ -654,6 +654,12 @@ public static LbfgsMaximumEntropyMulticlassTrainer LbfgsMaximumEntropy(this Mult
         /// <param name="catalog">The <see cref="MulticlassClassificationCatalog.MulticlassClassificationTrainers"/>.</param>
         /// <param name="labelColumnName">The name of the label column.</param>
         /// <param name="featureColumnName">The name of the feature column.</param>
+        /// <example>
+        /// <format type="text/markdown">
+        /// <![CDATA[
+        ///  [!code-csharp[NaiveBayes](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/NaiveBayes.cs)]
+        /// ]]></format>
+        /// </example>
         public static NaiveBayesMulticlassTrainer NaiveBayes(this MulticlassClassificationCatalog.MulticlassClassificationTrainers catalog,
             string labelColumnName = DefaultColumnNames.Label,
             string featureColumnName = DefaultColumnNames.Features)
@@ -703,7 +709,7 @@ private static ICalibratorTrainer GetCalibratorTrainerOrThrow(IExceptionContext
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        ///  [!code-csharp[SDCA](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/OneVersusAll.cs)]
+        ///  [!code-csharp[OneVersusAll](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/OneVersusAll.cs)]
         /// ]]></format>
         /// </example>
         public static OneVersusAllTrainer OneVersusAll<TModel>(this MulticlassClassificationCatalog.MulticlassClassificationTrainers catalog,
@@ -742,7 +748,7 @@ public static OneVersusAllTrainer OneVersusAll<TModel>(this MulticlassClassifica
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        ///  [!code-csharp[SDCA](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/PairwiseCoupling.cs)]
+        ///  [!code-csharp[PairwiseCoupling](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/PairwiseCoupling.cs)]
         /// ]]></format>
         /// </example>
         public static PairwiseCouplingTrainer PairwiseCoupling<TModel>(this MulticlassClassificationCatalog.MulticlassClassificationTrainers catalog,