Binary FastTree/Forest samples using T4 templates.

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

@@ -0,0 +1,99 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic.Trainers.BinaryClassification
+{
+    public static class FastForest
+    {
+        // This example requires installation of additional NuGet package
+        // <a href="https://www.nuget.org/packages/Microsoft.ML.FastTree/">Microsoft.ML.FastTree</a>.
+        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 examples.
+            var examples = GenerateRandomDataPoints(1000);
+
+            // Convert the examples list to an IDataView object, which is consumable by ML.NET API.
+            var trainingData = mlContext.Data.LoadFromEnumerable(examples);
+
+            // Define the trainer.
+            var pipeline = mlContext.BinaryClassification.Trainers.FastForest();
+
+            // Train the model.
+            var model = pipeline.Fit(trainingData);
+
+            // Create testing examples. 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: True, Prediction: True
+            //   Label: False, Prediction: False
+            //   Label: True, Prediction: True
+            //   Label: True, Prediction: True
+            //   Label: False, Prediction: False
+
+            // Evaluate the overall metrics
+            var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
+            SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
+
+            // Expected output:
+            //   Accuracy: 0.74
+            //   AUC: 0.83
+            //   F1 Score: 0.74
+            //   Negative Precision: 0.78
+            //   Negative Recall: 0.71
+            //   Positive Precision: 0.71
+            //   Positive Recall: 0.78
+        }
+
+        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
+        {
+            var random = new Random(seed);
+            float randomFloat() => (float)random.NextDouble();
+            for (int i = 0; i < count; i++)
+            {
+                var label = randomFloat() > 0.5f;
+                yield return new DataPoint
+                {
+                    Label = label,
+                    // Create random features that are correlated with label.
+                    Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.03f).ToArray()
+                };
+            }
+        }
+
+        // Example with label and 50 feature values. A data set is a collection of such examples.
+        private class DataPoint
+        {
+            public bool Label { get; set; }
+            [VectorType(50)]
+            public float[] Features { get; set; }
+        }
+
+        // Class used to capture predictions.
+        private class Prediction
+        {
+            // Original label.
+            public bool Label { get; set; }
+            // Predicted label from the trainer.
+            public bool PredictedLabel { get; set; }
+        }
+    }
+}
+

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/FastForest.tt

@@ -0,0 +1,24 @@
+<#@ include file="TreeSamplesTemplate.ttinclude"#>
+
+<#+
+string ClassName="FastForest";
+string Trainer = "FastForest";
+string TrainerOptions = null;
+bool IsCalibrated = false;
+
+string ExpectedOutputPerInstance= @"// Expected output:
+            //   Label: True, Prediction: True
+            //   Label: False, Prediction: False
+            //   Label: True, Prediction: True
+            //   Label: True, Prediction: True
+            //   Label: False, Prediction: False";
+
+string ExpectedOutput = @"// Expected output:
+            //   Accuracy: 0.74
+            //   AUC: 0.83
+            //   F1 Score: 0.74
+            //   Negative Precision: 0.78
+            //   Negative Recall: 0.71
+            //   Positive Precision: 0.71
+            //   Positive Recall: 0.78";
+#>

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

@@ -0,0 +1,112 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers.FastTree;
+
+namespace Microsoft.ML.Samples.Dynamic.Trainers.BinaryClassification
+{
+    public static class FastForestWithOptions
+    {
+        // This example requires installation of additional NuGet package
+        // <a href="https://www.nuget.org/packages/Microsoft.ML.FastTree/">Microsoft.ML.FastTree</a>.
+        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 trainer options.
+            var options = new FastForestBinaryTrainer.Options
+            {
+                // Only use 80% of features to reduce over-fitting.
+                FeatureFraction = 0.8,
+                // Create a simpler model by penalizing usage of new features.
+                FeatureFirstUsePenalty = 0.1,
+                // Reduce the number of trees to 50.
+                NumberOfTrees = 50
+            };
+
+            // Define the trainer.
+            var pipeline = mlContext.BinaryClassification.Trainers.FastForest(options);
+
+            // 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: True, Prediction: True
+            //   Label: False, Prediction: False
+            //   Label: True, Prediction: True
+            //   Label: True, Prediction: True
+            //   Label: False, Prediction: True
+
+            // Evaluate the overall metrics
+            var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
+            SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
+
+            // Expected output:
+            //   Accuracy: 0.73
+            //   AUC: 0.81
+            //   F1 Score: 0.73
+            //   Negative Precision: 0.77
+            //   Negative Recall: 0.68
+            //   Positive Precision: 0.69
+            //   Positive Recall: 0.78
+        }
+
+        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
+        {
+            var random = new Random(seed);
+            float randomFloat() => (float)random.NextDouble();
+            for (int i = 0; i < count; i++)
+            {
+                var label = randomFloat() > 0.5f;
+                yield return new DataPoint
+                {
+                    Label = label,
+                    // Create random features that are correlated with the label.
+                    // For data points with false label, the feature values are slightly increased by adding a constant.
+                    Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.03f).ToArray()
+                };
+            }
+        }
+
+        // Example with label and 50 feature values. A data set is a collection of such examples.
+        private class DataPoint
+        {
+            public bool Label { get; set; }
+            [VectorType(50)]
+            public float[] Features { get; set; }
+        }
+
+        // Class used to capture predictions.
+        private class Prediction
+        {
+            // Original label.
+            public bool Label { get; set; }
+            // Predicted label from the trainer.
+            public bool PredictedLabel { get; set; }
+        }
+    }
+}
+

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/FastForestWithOptions.tt

@@ -0,0 +1,33 @@
+<#@ include file="TreeSamplesTemplate.ttinclude"#>
+
+<#+
+string ClassName="FastForestWithOptions";
+string Trainer = "FastForest";
+bool IsCalibrated = false;
+
+string TrainerOptions = @"FastForestBinaryTrainer.Options
+            {
+                // Only use 80% of features to reduce over-fitting.
+                FeatureFraction = 0.8,
+                // Create a simpler model by penalizing usage of new features.
+                FeatureFirstUsePenalty = 0.1,
+                // Reduce the number of trees to 50.
+                NumberOfTrees = 50
+            }";
+
+string ExpectedOutputPerInstance= @"// Expected output:
+            //   Label: True, Prediction: True
+            //   Label: False, Prediction: False
+            //   Label: True, Prediction: True
+            //   Label: True, Prediction: True
+            //   Label: False, Prediction: True";
+
+string ExpectedOutput = @"// Expected output:
+            //   Accuracy: 0.73
+            //   AUC: 0.81
+            //   F1 Score: 0.73
+            //   Negative Precision: 0.77
+            //   Negative Recall: 0.68
+            //   Positive Precision: 0.69
+            //   Positive Recall: 0.78";
+#>

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

@@ -0,0 +1,103 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic.Trainers.BinaryClassification
+{
+    public static class FastTree
+    {
+        // This example requires installation of additional NuGet package
+        // <a href="https://www.nuget.org/packages/Microsoft.ML.FastTree/">Microsoft.ML.FastTree</a>.
+        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 = mlContext.BinaryClassification.Trainers.FastTree();
+
+            // 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: True, Prediction: True
+            //   Label: False, Prediction: False
+            //   Label: True, Prediction: True
+            //   Label: True, Prediction: True
+            //   Label: False, Prediction: False
+
+            // Evaluate the overall metrics
+            var metrics = mlContext.BinaryClassification.Evaluate(transformedTestData);
+            SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
+
+            // Expected output:
+            //   Accuracy: 0.81
+            //   AUC: 0.91
+            //   F1 Score: 0.80
+            //   Negative Precision: 0.82
+            //   Negative Recall: 0.80
+            //   Positive Precision: 0.79
+            //   Positive Recall: 0.81
+            //   Log Loss: 0.59
+            //   Log Loss Reduction: 41.04
+            //   Entropy: 1.00
+        }
+
+        private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
+        {
+            var random = new Random(seed);
+            float randomFloat() => (float)random.NextDouble();
+            for (int i = 0; i < count; i++)
+            {
+                var label = randomFloat() > 0.5f;
+                yield return new DataPoint
+                {
+                    Label = label,
+                    // Create random features that are correlated with the label.
+                    // For data points with false label, the feature values are slightly increased by adding a constant.
+                    Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.03f).ToArray()
+                };
+            }
+        }
+
+        // Example with label and 50 feature values. A data set is a collection of such examples.
+        private class DataPoint
+        {
+            public bool Label { get; set; }
+            [VectorType(50)]
+            public float[] Features { get; set; }
+        }
+
+        // Class used to capture predictions.
+        private class Prediction
+        {
+            // Original label.
+            public bool Label { get; set; }
+            // Predicted label from the trainer.
+            public bool PredictedLabel { get; set; }
+        }
+    }
+}
+