Adding a sample for LightGbm ranking

docs/code/MlNetCookBook.md

@@ -959,7 +959,7 @@ public static ITransformer TrainModel(MLContext mlContext, IDataView trainData)
     // Construct the learning pipeline.
     var estimator = mlContext.Transforms.CustomMapping(mapping, null)
         .AppendCacheCheckpoint(mlContext)
-        .Append(mlContext.BinaryClassification.Trainers.FastTree(label: "Label"));
+        .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumnName: "Label"));
 
     return estimator.Fit(trainData);
 }
@@ -998,7 +998,7 @@ public class CustomMappings : CustomMappingFactory<InputRow, OutputRow>
 // Construct the learning pipeline. Note that we are now providing a contract name for the custom mapping:
 // otherwise we will not be able to save the model.
 var estimator = mlContext.Transforms.CustomMapping<InputRow, OutputRow>(CustomMappings.IncomeMapping, nameof(CustomMappings.IncomeMapping))
-    .Append(mlContext.BinaryClassification.Trainers.FastTree(label: "Label"));
+    .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumnName: "Label"));
 
 // If memory is enough, we can cache the data in-memory to avoid reading them from file
 // when it will be accessed multiple times. 

docs/samples/Microsoft.ML.Samples/Dynamic/Calibrator.cs

@@ -34,8 +34,8 @@ public static void Example()
                 HasHeader = true,
                 Columns = new[]
                     {
-                        new TextLoader.Column("Sentiment", DataKind.BL, 0),
-                        new TextLoader.Column("SentimentText", DataKind.Text, 1)
+                        new TextLoader.Column("Sentiment", DataKind.Boolean, 0),
+                        new TextLoader.Column("SentimentText", DataKind.String, 1)
                     }
             });
 
@@ -50,8 +50,8 @@ public static void Example()
             // the "Features" column produced by FeaturizeText as the features column. 
             var pipeline = mlContext.Transforms.Text.FeaturizeText("SentimentText", "Features")
                     .Append(mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscentNonCalibrated(
-                        labelColumn: "Sentiment", 
-                        featureColumn: "Features", 
+                        labelColumnName: "Sentiment", 
+                        featureColumnName: "Features", 
                         l2Const: 0.001f, 
                         loss: new HingeLoss())); // By specifying loss: new HingeLoss(), StochasticDualCoordinateAscent will train a support vector machine (SVM).
 

docs/samples/Microsoft.ML.Samples/Dynamic/FastTreeRegression.cs

@@ -29,7 +29,7 @@ public static void Example()
             // We will train a FastTreeRegression model with 1 tree on these two columns to predict Age.
             string outputColumnName = "Features";
             var pipeline = ml.Transforms.Concatenate(outputColumnName, new[] { "Parity", "Induced" })
-                .Append(ml.Regression.Trainers.FastTree(labelColumn: "Age", featureColumn: outputColumnName, numTrees: 1, numLeaves: 2, minDatapointsInLeaves: 1));
+                .Append(ml.Regression.Trainers.FastTree(labelColumnName: "Age", featureColumnName: outputColumnName, numTrees: 1, numLeaves: 2, minDatapointsInLeaves: 1));
 
             var model = pipeline.Fit(trainData);
 

docs/samples/Microsoft.ML.Samples/Dynamic/FeatureSelectionTransform.cs

@@ -33,8 +33,8 @@ public static void Example()
             var reader = ml.Data.CreateTextLoader(
                 columns: new[]
                     {
-                        new TextLoader.Column("Label", DataKind.BL, 0),
-                        new TextLoader.Column("Features", DataKind.Num, new [] { new TextLoader.Range(1, 9) })
+                        new TextLoader.Column("Label", DataKind.Boolean, 0),
+                        new TextLoader.Column("Features", DataKind.Single, new [] { new TextLoader.Range(1, 9) })
                     },
                 hasHeader: true
             );

docs/samples/Microsoft.ML.Samples/Dynamic/FieldAwareFactorizationMachine.cs

@@ -25,8 +25,8 @@ public static void Example()
             var reader = mlContext.Data.CreateTextLoader(
                 columns: new[]
                     {
-                        new TextLoader.Column("Sentiment", DataKind.BL, 0),
-                        new TextLoader.Column("SentimentText", DataKind.Text, 1)
+                        new TextLoader.Column("Sentiment", DataKind.Boolean, 0),
+                        new TextLoader.Column("SentimentText", DataKind.String, 1)
                     },
                 hasHeader: true
             );
@@ -46,7 +46,7 @@ public static void Example()
             // the "Features" column produced by FeaturizeText as the features column.
             var pipeline = mlContext.Transforms.Text.FeaturizeText("SentimentText", "Features")
                     .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
-                    .Append(mlContext.BinaryClassification.Trainers.FieldAwareFactorizationMachine(labelColumn: "Sentiment", featureColumns: new[] { "Features" }));
+                    .Append(mlContext.BinaryClassification.Trainers.FieldAwareFactorizationMachine(labelColumnName: "Sentiment", featureColumnNames: new[] { "Features" }));
 
             // Fit the model.
             var model = pipeline.Fit(data);

docs/samples/Microsoft.ML.Samples/Dynamic/GeneralizedAdditiveModels.cs

@@ -28,7 +28,7 @@ public static void Example()
                 .ToArray();
             var pipeline = mlContext.Transforms.Concatenate("Features", featureNames)
                     .Append(mlContext.Regression.Trainers.GeneralizedAdditiveModels(
-                        labelColumn: labelName, featureColumn: "Features", maxBins: 16));
+                        labelColumnName: labelName, featureColumnName: "Features", maxBins: 16));
             var fitPipeline = pipeline.Fit(data);
 
             // Extract the model from the pipeline

docs/samples/Microsoft.ML.Samples/Dynamic/ImageAnalytics/ConvertToGrayScale.cs

@@ -27,8 +27,8 @@ public static void Example()
             {
                 Columns = new[]
                 {
-                        new TextLoader.Column("ImagePath", DataKind.TX, 0),
-                        new TextLoader.Column("Name", DataKind.TX, 1),
+                        new TextLoader.Column("ImagePath", DataKind.String, 0),
+                        new TextLoader.Column("Name", DataKind.String, 1),
                  }
             }).Read(imagesDataFile);
 

docs/samples/Microsoft.ML.Samples/Dynamic/ImageAnalytics/ExtractPixels.cs

@@ -28,8 +28,8 @@ public static void Example()
             {
                 Columns = new[]
                 {
-                        new TextLoader.Column("ImagePath", DataKind.TX, 0),
-                        new TextLoader.Column("Name", DataKind.TX, 1),
+                        new TextLoader.Column("ImagePath", DataKind.String, 0),
+                        new TextLoader.Column("Name", DataKind.String, 1),
                 }
             }).Read(imagesDataFile);
 

docs/samples/Microsoft.ML.Samples/Dynamic/ImageAnalytics/LoadImages.cs

@@ -27,8 +27,8 @@ public static void Example()
             {
                 Columns = new[]
                 {
-                        new TextLoader.Column("ImagePath", DataKind.TX, 0),
-                        new TextLoader.Column("Name", DataKind.TX, 1),
+                        new TextLoader.Column("ImagePath", DataKind.String, 0),
+                        new TextLoader.Column("Name", DataKind.String, 1),
                     }
             }).Read(imagesDataFile);
 

docs/samples/Microsoft.ML.Samples/Dynamic/ImageAnalytics/ResizeImages.cs

@@ -27,8 +27,8 @@ public static void Example()
             {
                 Columns = new[]
                 {
-                        new TextLoader.Column("ImagePath", DataKind.TX, 0),
-                        new TextLoader.Column("Name", DataKind.TX, 1),
+                        new TextLoader.Column("ImagePath", DataKind.String, 0),
+                        new TextLoader.Column("Name", DataKind.String, 1),
                 }
             }).Read(imagesDataFile);
 

docs/samples/Microsoft.ML.Samples/Dynamic/LogisticRegression.cs

@@ -37,21 +37,21 @@ public static void Example()
                 HasHeader = true,
                 Columns = new[]
                 {
-                    new TextLoader.Column("age", DataKind.R4, 0),
-                    new TextLoader.Column("workclass", DataKind.Text, 1),
-                    new TextLoader.Column("fnlwgt", DataKind.R4, 2),
-                    new TextLoader.Column("education", DataKind.Text, 3),
-                    new TextLoader.Column("education-num", DataKind.R4, 4),
-                    new TextLoader.Column("marital-status", DataKind.Text, 5),
-                    new TextLoader.Column("occupation", DataKind.Text, 6),
-                    new TextLoader.Column("relationship", DataKind.Text, 7),
-                    new TextLoader.Column("ethnicity", DataKind.Text, 8),
-                    new TextLoader.Column("sex", DataKind.Text, 9),
-                    new TextLoader.Column("capital-gain", DataKind.R4, 10),
-                    new TextLoader.Column("capital-loss", DataKind.R4, 11),
-                    new TextLoader.Column("hours-per-week", DataKind.R4, 12),
-                    new TextLoader.Column("native-country", DataKind.Text, 13),
-                    new TextLoader.Column("Label", DataKind.Bool, 14)
+                    new TextLoader.Column("age", DataKind.Single, 0),
+                    new TextLoader.Column("workclass", DataKind.String, 1),
+                    new TextLoader.Column("fnlwgt", DataKind.Single, 2),
+                    new TextLoader.Column("education", DataKind.String, 3),
+                    new TextLoader.Column("education-num", DataKind.Single, 4),
+                    new TextLoader.Column("marital-status", DataKind.String, 5),
+                    new TextLoader.Column("occupation", DataKind.String, 6),
+                    new TextLoader.Column("relationship", DataKind.String, 7),
+                    new TextLoader.Column("ethnicity", DataKind.String, 8),
+                    new TextLoader.Column("sex", DataKind.String, 9),
+                    new TextLoader.Column("capital-gain", DataKind.Single, 10),
+                    new TextLoader.Column("capital-loss", DataKind.Single, 11),
+                    new TextLoader.Column("hours-per-week", DataKind.Single, 12),
+                    new TextLoader.Column("native-country", DataKind.String, 13),
+                    new TextLoader.Column("Label", DataKind.Boolean, 14)
                 }
             });
 

docs/samples/Microsoft.ML.Samples/Dynamic/PermutationFeatureImportance/PfiBinaryClassificationExample.cs

@@ -23,7 +23,7 @@ public static void Example()
             var pipeline = mlContext.Transforms.Concatenate("Features", featureNames)
                     .Append(mlContext.Transforms.Normalize("Features"))
                     .Append(mlContext.BinaryClassification.Trainers.LogisticRegression(
-                        labelColumn: labelName, featureColumn: "Features"));
+                        labelColumnName: labelName, featureColumnName: "Features"));
             var model = pipeline.Fit(data);
 
             // Extract the model from the pipeline

docs/samples/Microsoft.ML.Samples/Dynamic/TensorFlow/TextClassification.cs

@@ -36,8 +36,8 @@ public static void Example()
             var lookupMap = mlContext.Data.ReadFromTextFile(Path.Combine(modelLocation, "imdb_word_index.csv"),
                 columns: new[]
                    {
-                        new TextLoader.Column("Words", DataKind.TX, 0),
-                        new TextLoader.Column("Ids", DataKind.I4, 1),
+                        new TextLoader.Column("Words", DataKind.String, 0),
+                        new TextLoader.Column("Ids", DataKind.Int32, 1),
                    },
                 separatorChar: ','
                );

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs

@@ -5,7 +5,7 @@ namespace Microsoft.ML.Samples.Dynamic.Trainers.BinaryClassification
     public static class AveragedPerceptron
     {
         // In this examples we will use the adult income dataset. The goal is to predict
-        // if a person's income is above $50K or not, based on different pieces of information about that person.
+        // if a person's income is above $50K or not, based on demographic information about that person.
         // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
         public static void Example()
         {

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs

@@ -6,7 +6,7 @@ namespace Microsoft.ML.Samples.Dynamic.Trainers.BinaryClassification
     public static class AveragedPerceptronWithOptions
     {
         // In this examples we will use the adult income dataset. The goal is to predict
-        // if a person's income is above $50K or not, based on different pieces of information about that person.
+        // if a person's income is above $50K or not, based on demographic information about that person.
         // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
         public static void Example()
         {

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/LightGBMBinaryClassification.cs

@@ -1,8 +1,8 @@
 using Microsoft.ML.Transforms.Categorical;
 
-namespace Microsoft.ML.Samples.Dynamic
+namespace Microsoft.ML.Samples.Dynamic.Trainers.BinaryClassification
 {
-    public class LightGbmBinaryClassification
+    public class LightGbm
     {
         // This example requires installation of additional nuget package <a href="https://www.nuget.org/packages/Microsoft.ML.LightGBM/">Microsoft.ML.LightGBM</a>.
         public static void Example()
@@ -17,25 +17,25 @@ public static void Example()
             var split = mlContext.BinaryClassification.TrainTestSplit(dataview, testFraction: 0.1);
 
             // Create the Estimator.
-            var pipeline = mlContext.BinaryClassification.Trainers.LightGbm("IsOver50K", "Features");
+            var pipeline = mlContext.BinaryClassification.Trainers.LightGbm();
 
             // Fit this Pipeline to the Training Data.
             var model = pipeline.Fit(split.TrainSet);
 
             // Evaluate how the model is doing on the test data.
             var dataWithPredictions = model.Transform(split.TestSet);
 
-            var metrics = mlContext.BinaryClassification.Evaluate(dataWithPredictions, "IsOver50K");
+            var metrics = mlContext.BinaryClassification.Evaluate(dataWithPredictions);
             SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 
-            // Output:
-            // Accuracy: 0.88
-            // AUC: 0.93
-            // F1 Score: 0.71
-            // Negative Precision: 0.90
-            // Negative Recall: 0.94
-            // Positive Precision: 0.76
-            // Positive Recall: 0.66
+            // Expected output:
+            //   Accuracy: 0.88
+            //   AUC: 0.93
+            //   F1 Score: 0.71
+            //   Negative Precision: 0.90
+            //   Negative Recall: 0.94
+            //   Positive Precision: 0.76
+            //   Positive Recall: 0.66
         }
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/LightGBMBinaryClassificationWithOptions.cs

@@ -1,10 +1,9 @@
 using Microsoft.ML.LightGBM;
-using Microsoft.ML.Transforms.Categorical;
 using static Microsoft.ML.LightGBM.Options;
 
-namespace Microsoft.ML.Samples.Dynamic
+namespace Microsoft.ML.Samples.Dynamic.Trainers.BinaryClassification
 {
-    class LightGbmBinaryClassificationWithOptions
+    class LightGbmWithOptions
     {
         // This example requires installation of additional nuget package <a href="https://www.nuget.org/packages/Microsoft.ML.LightGBM/">Microsoft.ML.LightGBM</a>.
         public static void Example()
@@ -22,8 +21,6 @@ public static void Example()
             var pipeline = mlContext.BinaryClassification.Trainers.LightGbm(
                                 new Options
                                 {
-                                    LabelColumn = "IsOver50K",
-                                    FeatureColumn = "Features",
                                     Booster = new GossBooster.Options
                                     {
                                         TopRate = 0.3,
@@ -37,17 +34,17 @@ public static void Example()
             // Evaluate how the model is doing on the test data.
             var dataWithPredictions = model.Transform(split.TestSet);
 
-            var metrics = mlContext.BinaryClassification.Evaluate(dataWithPredictions, "IsOver50K");
+            var metrics = mlContext.BinaryClassification.Evaluate(dataWithPredictions);
             SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 
-            // Output:
-            // Accuracy: 0.88
-            // AUC: 0.93
-            // F1 Score: 0.71
-            // Negative Precision: 0.90
-            // Negative Recall: 0.94
-            // Positive Precision: 0.76
-            // Positive Recall: 0.67
+            // Expected output:
+            //   Accuracy: 0.88
+            //   AUC: 0.93
+            //   F1 Score: 0.71
+            //   Negative Precision: 0.90
+            //   Negative Recall: 0.94
+            //   Positive Precision: 0.76
+            //   Positive Recall: 0.67
         }
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/SDCALogisticRegression.cs

@@ -3,7 +3,7 @@
 using Microsoft.ML.Data;
 using Microsoft.ML.Trainers;
 
-namespace Microsoft.ML.Samples.Dynamic
+namespace Microsoft.ML.Samples.Dynamic.Trainers.BinaryClassification
 {
     public static class SDCALogisticRegression
     {
@@ -28,8 +28,8 @@ public static void Example()
             var reader = mlContext.Data.CreateTextLoader(
                 columns: new[]
                     {
-                        new TextLoader.Column("Sentiment", DataKind.BL, 0),
-                        new TextLoader.Column("SentimentText", DataKind.Text, 1)
+                        new TextLoader.Column("Sentiment", DataKind.Boolean, 0),
+                        new TextLoader.Column("SentimentText", DataKind.String, 1)
                     },
                 hasHeader: true
             );
@@ -49,7 +49,7 @@ public static void Example()
             // the "Features" column produced by FeaturizeText as the features column.
             var pipeline = mlContext.Transforms.Text.FeaturizeText("SentimentText", "Features")
                     .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
-                    .Append(mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscent(labelColumn: "Sentiment", featureColumn: "Features", l2Const: 0.001f));
+                    .Append(mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscent(labelColumnName: "Sentiment", featureColumnName: "Features", l2Const: 0.001f));
 
             // Step 3: Run Cross-Validation on this pipeline.
             var cvResults = mlContext.BinaryClassification.CrossValidate(data, pipeline, labelColumn: "Sentiment");

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/SDCASupportVectorMachine.cs

@@ -2,7 +2,7 @@
 using System.Linq;
 using Microsoft.ML.Data;
 
-namespace Microsoft.ML.Samples.Dynamic
+namespace Microsoft.ML.Samples.Dynamic.Trainers.BinaryClassification
 {
     public static class SDCASupportVectorMachine
     {
@@ -41,7 +41,7 @@ public static void Example()
             // Step 2: Create a binary classifier. This trainer may produce a logistic regression model.
             // We set the "Label" column as the label of the dataset, and the "Features" column as the features column.
             var pipeline = mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscentNonCalibrated(
-                labelColumn: "Label", featureColumn: "Features", loss: new HingeLoss(), l2Const: 0.001f);
+                labelColumnName: "Label", featureColumnName: "Features", loss: new HingeLoss(), l2Const: 0.001f);
 
             // Step 3: Train the pipeline created.
             var model = pipeline.Fit(data);