review comments

dotnet · Apr 17, 2019 · 1877e7d · 1877e7d
1 parent 09fbb77
commit 1877e7d
Show file tree

Hide file tree

Showing 8 changed files with 76 additions and 48 deletions.
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTree.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTree.cs
@@ -35,11 +35,14 @@ public static void Example()
             // Run the model on test data set.
             var transformedTestData = model.Transform(testData);
 
+            // Take the top 5 rows.
+            var topTransformedTestData = mlContext.Data.TakeRows(transformedTestData, 5);
+
             // Convert IDataView object to a list.
-            var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();
+            var predictions = mlContext.Data.CreateEnumerable<Prediction>(topTransformedTestData, reuseRowObject: false).ToList();
 
-            // Look at 5 predictions
-            foreach (var p in predictions.Take(5))
+            // Print 5 predictions.
+            foreach (var p in predictions)
                 Console.WriteLine($"Label: {p.Label}, Score: {p.Score}");
 
             // Expected output:
@@ -49,7 +52,7 @@ public static void Example()
             //   Label: 3, Score: -8.178633
             //   Label: 1, Score: -17.09313
 
-            // Evaluate the overall metrics
+            // Evaluate the overall metrics.
             var metrics = mlContext.Ranking.Evaluate(transformedTestData);
             PrintMetrics(metrics);
 
@@ -81,8 +84,8 @@ private class DataPoint
         {
             [KeyType(5)]
             public uint Label { get; set; }
-            [KeyType(100)]            
-            public uint GroupId { get; set; }            
+            [KeyType(100)]
+            public uint GroupId { get; set; }
             [VectorType(50)]
             public float[] Features { get; set; }
         }

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTreeWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTreeWithOptions.cs
@@ -32,7 +32,9 @@ public static void Example()
                 // Create a simpler model by penalizing usage of new features.
                 FeatureFirstUsePenalty = 0.1,
                 // Reduce the number of trees to 50.
-                NumberOfTrees = 50
+                NumberOfTrees = 50,
+                // Specify the row group column name.
+                RowGroupColumnName = "GroupId"
             };
 
             // Define the trainer.
@@ -47,27 +49,30 @@ public static void Example()
             // Run the model on test data set.
             var transformedTestData = model.Transform(testData);
 
+            // Take the top 5 rows.
+            var topTransformedTestData = mlContext.Data.TakeRows(transformedTestData, 5);
+
             // Convert IDataView object to a list.
-            var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();
+            var predictions = mlContext.Data.CreateEnumerable<Prediction>(topTransformedTestData, reuseRowObject: false).ToList();
 
-            // Look at 5 predictions
-            foreach (var p in predictions.Take(5))
+            // Print 5 predictions.
+            foreach (var p in predictions)
                 Console.WriteLine($"Label: {p.Label}, Score: {p.Score}");
 
             // Expected output:
-            //   Label: 5, Score: 8.098782
-            //   Label: 1, Score: -11.2527
-            //   Label: 3, Score: -10.89519
-            //   Label: 3, Score: -5.050685
-            //   Label: 1, Score: -10.44891
+            //   Label: 5, Score: 8.807633
+            //   Label: 1, Score: -10.71331
+            //   Label: 3, Score: -8.134147
+            //   Label: 3, Score: -6.545538
+            //   Label: 1, Score: -10.27982
 
-            // Evaluate the overall metrics
+            // Evaluate the overall metrics.
             var metrics = mlContext.Ranking.Evaluate(transformedTestData);
             PrintMetrics(metrics);
 
             // Expected output:
-            //   DCG: @1:41.03, @2:60.07, @3:74.30
-            //   NDCG: @1:0.97, @2:0.93, @3:0.97
+            //   DCG: @1:40.57, @2:61.21, @3:74.11
+            //   NDCG: @1:0.96, @2:0.95, @3:0.97
         }
 
         private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed = 0, int groupSize = 10)
@@ -93,8 +98,8 @@ private class DataPoint
         {
             [KeyType(5)]
             public uint Label { get; set; }
-            [KeyType(100)]            
-            public uint GroupId { get; set; }            
+            [KeyType(100)]
+            public uint GroupId { get; set; }
             [VectorType(50)]
             public float[] Features { get; set; }
         }

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTreeWithOptions.tt b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTreeWithOptions.tt
@@ -9,7 +9,9 @@ string TrainerOptions = @"FastTreeRankingTrainer.Options
                 // Create a simpler model by penalizing usage of new features.
                 FeatureFirstUsePenalty = 0.1,
                 // Reduce the number of trees to 50.
-                NumberOfTrees = 50
+                NumberOfTrees = 50,
+                // Specify the row group column name.
+                RowGroupColumnName = ""GroupId""
             }";
 
 string OptionsInclude = "using Microsoft.ML.Trainers.FastTree;";
@@ -18,13 +20,13 @@ string Comments= @"
         // <a href=""https://www.nuget.org/packages/Microsoft.ML.FastTree/"">Microsoft.ML.FastTree</a>.";
 
 string ExpectedOutputPerInstance = @"// Expected output:
-            //   Label: 5, Score: 8.098782
-            //   Label: 1, Score: -11.2527
-            //   Label: 3, Score: -10.89519
-            //   Label: 3, Score: -5.050685
-            //   Label: 1, Score: -10.44891";
+            //   Label: 5, Score: 8.807633
+            //   Label: 1, Score: -10.71331
+            //   Label: 3, Score: -8.134147
+            //   Label: 3, Score: -6.545538
+            //   Label: 1, Score: -10.27982";
 
 string ExpectedOutput = @"// Expected output:
-            //   DCG: @1:41.03, @2:60.07, @3:74.30
-            //   NDCG: @1:0.97, @2:0.93, @3:0.97";
+            //   DCG: @1:40.57, @2:61.21, @3:74.11
+            //   NDCG: @1:0.96, @2:0.95, @3:0.97";
 #>
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbm.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbm.cs
@@ -35,11 +35,14 @@ public static void Example()
             // Run the model on test data set.
             var transformedTestData = model.Transform(testData);
 
+            // Take the top 5 rows.
+            var topTransformedTestData = mlContext.Data.TakeRows(transformedTestData, 5);
+
             // Convert IDataView object to a list.
-            var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();
+            var predictions = mlContext.Data.CreateEnumerable<Prediction>(topTransformedTestData, reuseRowObject: false).ToList();
 
-            // Look at 5 predictions
-            foreach (var p in predictions.Take(5))
+            // Print 5 predictions.
+            foreach (var p in predictions)
                 Console.WriteLine($"Label: {p.Label}, Score: {p.Score}");
 
             // Expected output:
@@ -49,7 +52,7 @@ public static void Example()
             //   Label: 3, Score: -2.151812
             //   Label: 1, Score: -4.089102
 
-            // Evaluate the overall metrics
+            // Evaluate the overall metrics.
             var metrics = mlContext.Ranking.Evaluate(transformedTestData);
             PrintMetrics(metrics);
 
@@ -81,8 +84,8 @@ private class DataPoint
         {
             [KeyType(5)]
             public uint Label { get; set; }
-            [KeyType(100)]            
-            public uint GroupId { get; set; }            
+            [KeyType(100)]
+            public uint GroupId { get; set; }
             [VectorType(50)]
             public float[] Features { get; set; }
         }

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbmWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbmWithOptions.cs
@@ -50,11 +50,14 @@ public static void Example()
             // Run the model on test data set.
             var transformedTestData = model.Transform(testData);
 
+            // Take the top 5 rows.
+            var topTransformedTestData = mlContext.Data.TakeRows(transformedTestData, 5);
+
             // Convert IDataView object to a list.
-            var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();
+            var predictions = mlContext.Data.CreateEnumerable<Prediction>(topTransformedTestData, reuseRowObject: false).ToList();
 
-            // Look at 5 predictions
-            foreach (var p in predictions.Take(5))
+            // Print 5 predictions.
+            foreach (var p in predictions)
                 Console.WriteLine($"Label: {p.Label}, Score: {p.Score}");
 
             // Expected output:
@@ -64,7 +67,7 @@ public static void Example()
             //   Label: 3, Score: -0.009396422
             //   Label: 1, Score: -0.05871891
 
-            // Evaluate the overall metrics
+            // Evaluate the overall metrics.
             var metrics = mlContext.Ranking.Evaluate(transformedTestData);
             PrintMetrics(metrics);
 
@@ -96,8 +99,8 @@ private class DataPoint
         {
             [KeyType(5)]
             public uint Label { get; set; }
-            [KeyType(100)]            
-            public uint GroupId { get; set; }            
+            [KeyType(100)]
+            public uint GroupId { get; set; }
             [VectorType(50)]
             public float[] Features { get; set; }
         }

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/Ranking.ttinclude b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/Ranking.ttinclude
@@ -44,16 +44,19 @@ namespace Samples.Dynamic.Trainers.Ranking
             // Run the model on test data set.
             var transformedTestData = model.Transform(testData);
 
+            // Take the top 5 rows.
+            var topTransformedTestData = mlContext.Data.TakeRows(transformedTestData, 5);
+
             // Convert IDataView object to a list.
-            var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();
+            var predictions = mlContext.Data.CreateEnumerable<Prediction>(topTransformedTestData, reuseRowObject: false).ToList();
 
-            // Look at 5 predictions
-            foreach (var p in predictions.Take(5))
+            // Print 5 predictions.
+            foreach (var p in predictions)
                 Console.WriteLine($"Label: {p.Label}, Score: {p.Score}");
 
             <#=ExpectedOutputPerInstance#>
 
-            // Evaluate the overall metrics
+            // Evaluate the overall metrics.
             var metrics = mlContext.Ranking.Evaluate(transformedTestData);
             PrintMetrics(metrics);
 
@@ -83,8 +86,8 @@ namespace Samples.Dynamic.Trainers.Ranking
         {
             [KeyType(5)]
             public uint Label { get; set; }
-            [KeyType(100)]            
-            public uint GroupId { get; set; }            
+            [KeyType(100)]
+            public uint GroupId { get; set; }
             [VectorType(50)]
             public float[] Features { get; set; }
         }

diff --git a/docs/samples/Microsoft.ML.Samples/Microsoft.ML.Samples.csproj b/docs/samples/Microsoft.ML.Samples/Microsoft.ML.Samples.csproj
@@ -284,6 +284,10 @@
       <Generator>TextTemplatingFileGenerator</Generator>
       <LastGenOutput>LightGbmWithOptions.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>
@@ -679,6 +683,11 @@
       <AutoGen>True</AutoGen>
       <DependentUpon>SdcaNonCalibratedWithOptions.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\Ranking\FastTree.cs">
       <DesignTime>True</DesignTime>
       <AutoGen>True</AutoGen>

diff --git a/src/Microsoft.ML.FastTree/TreeTrainersCatalog.cs b/src/Microsoft.ML.FastTree/TreeTrainersCatalog.cs
@@ -136,7 +136,7 @@ public static class TreeExtensions
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        /// [!code-csharp[FastTreeBinaryClassification](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTree.cs)]
+        /// [!code-csharp[FastTree](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTree.cs)]
         /// ]]>
         /// </format>
         /// </example>
@@ -163,7 +163,7 @@ public static class TreeExtensions
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        /// [!code-csharp[FastTreeBinaryClassification](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTreeWithOptions.cs)]
+        /// [!code-csharp[FastTree](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/FastTreeWithOptions.cs)]
         /// ]]>
         /// </format>
         /// </example>