TreeExtensions.FastForest Method
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Overloads
| FastForest(BinaryClassificationCatalog+BinaryClassificationTrainers, FastForestBinaryTrainer+Options) |
Create FastForestBinaryTrainer with advanced options, which predicts a target using a decision tree regression model. |
| FastForest(RegressionCatalog+RegressionTrainers, FastForestRegressionTrainer+Options) |
Create FastForestRegressionTrainer with advanced options, which predicts a target using a decision tree regression model. |
| FastForest(BinaryClassificationCatalog+BinaryClassificationTrainers, String, String, String, Int32, Int32, Int32) |
Create FastForestBinaryTrainer, which predicts a target using a decision tree regression model. |
| FastForest(RegressionCatalog+RegressionTrainers, String, String, String, Int32, Int32, Int32) |
Create FastForestRegressionTrainer, which predicts a target using a decision tree regression model. |
FastForest(BinaryClassificationCatalog+BinaryClassificationTrainers, FastForestBinaryTrainer+Options)
Create FastForestBinaryTrainer with advanced options, which predicts a target using a decision tree regression model.
public static Microsoft.ML.Trainers.FastTree.FastForestBinaryTrainer FastForest (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, Microsoft.ML.Trainers.FastTree.FastForestBinaryTrainer.Options options);static member FastForest : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * Microsoft.ML.Trainers.FastTree.FastForestBinaryTrainer.Options -> Microsoft.ML.Trainers.FastTree.FastForestBinaryTrainer<Extension()>
Public Function FastForest (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, options As FastForestBinaryTrainer.Options) As FastForestBinaryTrainerParameters
- options
- FastForestBinaryTrainer.Options
Trainer options.
Returns
Examples
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers.FastTree;
namespace Samples.Dynamic.Trainers.BinaryClassification
{
public static class FastForestWithOptions
{
// This example requires installation of additional NuGet package for
// Microsoft.ML.FastTree at
// https://www.nuget.org/packages/Microsoft.ML.FastTree/
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();
// Print 5 predictions.
foreach (var p in predictions.Take(5))
Console.WriteLine($"Label: {p.Label}, "
+ $"Prediction: {p.PredictedLabel}");
// Expected output:
// Label: True, Prediction: True
// Label: False, Prediction: False
// Label: True, Prediction: True
// Label: True, Prediction: True
// Label: False, Prediction: True
// Evaluate the overall metrics.
var metrics = mlContext.BinaryClassification
.EvaluateNonCalibrated(transformedTestData);
PrintMetrics(metrics);
// Expected output:
// Accuracy: 0.73
// AUC: 0.81
// F1 Score: 0.73
// Negative Precision: 0.77
// Negative Recall: 0.68
// Positive Precision: 0.69
// Positive Recall: 0.78
//
// TEST POSITIVE RATIO: 0.4760 (238.0/(238.0+262.0))
// Confusion table
// ||======================
// PREDICTED || positive | negative | Recall
// TRUTH ||======================
// positive || 186 | 52 | 0.7815
// negative || 77 | 185 | 0.7061
// ||======================
// Precision || 0.7072 | 0.7806 |
}
private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
int seed = 0)
{
var random = new Random(seed);
float randomFloat() => (float)random.NextDouble();
for (int i = 0; i < count; i++)
{
var label = randomFloat() > 0.5f;
yield return new DataPoint
{
Label = label,
// Create random features that are correlated with the label.
// For data points with false label, the feature values are
// slightly increased by adding a constant.
Features = Enumerable.Repeat(label, 50)
.Select(x => x ? randomFloat() : randomFloat() +
0.03f).ToArray()
};
}
}
// Example with label and 50 feature values. A data set is a collection of
// such examples.
private class DataPoint
{
public bool Label { get; set; }
[VectorType(50)]
public float[] Features { get; set; }
}
// Class used to capture predictions.
private class Prediction
{
// Original label.
public bool Label { get; set; }
// Predicted label from the trainer.
public bool PredictedLabel { get; set; }
}
// Pretty-print BinaryClassificationMetrics objects.
private static void PrintMetrics(BinaryClassificationMetrics metrics)
{
Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
Console.WriteLine($"Negative Precision: " +
$"{metrics.NegativePrecision:F2}");
Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
Console.WriteLine($"Positive Precision: " +
$"{metrics.PositivePrecision:F2}");
Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}\n");
Console.WriteLine(metrics.ConfusionMatrix.GetFormattedConfusionTable());
}
}
}
Applies to
FastForest(RegressionCatalog+RegressionTrainers, FastForestRegressionTrainer+Options)
Create FastForestRegressionTrainer with advanced options, which predicts a target using a decision tree regression model.
public static Microsoft.ML.Trainers.FastTree.FastForestRegressionTrainer FastForest (this Microsoft.ML.RegressionCatalog.RegressionTrainers catalog, Microsoft.ML.Trainers.FastTree.FastForestRegressionTrainer.Options options);static member FastForest : Microsoft.ML.RegressionCatalog.RegressionTrainers * Microsoft.ML.Trainers.FastTree.FastForestRegressionTrainer.Options -> Microsoft.ML.Trainers.FastTree.FastForestRegressionTrainer<Extension()>
Public Function FastForest (catalog As RegressionCatalog.RegressionTrainers, options As FastForestRegressionTrainer.Options) As FastForestRegressionTrainerParameters
The RegressionCatalog.
Trainer options.
Returns
Examples
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers.FastTree;
namespace Samples.Dynamic.Trainers.Regression
{
public static class FastForestWithOptionsRegression
{
// This example requires installation of additional NuGet
// package for Microsoft.ML.FastTree found at
// https://www.nuget.org/packages/Microsoft.ML.FastTree/
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 FastForestRegressionTrainer.Options
{
LabelColumnName = nameof(DataPoint.Label),
FeatureColumnName = nameof(DataPoint.Features),
// 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.Regression.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(5, 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 for the Label, side by side with the actual
// Label for comparison.
foreach (var p in predictions)
Console.WriteLine($"Label: {p.Label:F3}, Prediction: {p.Score:F3}");
// Expected output:
// Label: 0.985, Prediction: 0.866
// Label: 0.155, Prediction: 0.171
// Label: 0.515, Prediction: 0.470
// Label: 0.566, Prediction: 0.476
// Label: 0.096, Prediction: 0.140
// Evaluate the overall metrics
var metrics = mlContext.Regression.Evaluate(transformedTestData);
PrintMetrics(metrics);
// Expected output:
// Mean Absolute Error: 0.06
// Mean Squared Error: 0.01
// Root Mean Squared Error: 0.07
// RSquared: 0.95 (closer to 1 is better. The worst case is 0)
}
private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
int seed = 0)
{
var random = new Random(seed);
for (int i = 0; i < count; i++)
{
float label = (float)random.NextDouble();
yield return new DataPoint
{
Label = label,
// Create random features that are correlated with the label.
Features = Enumerable.Repeat(label, 50).Select(
x => x + (float)random.NextDouble()).ToArray()
};
}
}
// Example with label and 50 feature values. A data set is a collection of
// such examples.
private class DataPoint
{
public float Label { get; set; }
[VectorType(50)]
public float[] Features { get; set; }
}
// Class used to capture predictions.
private class Prediction
{
// Original label.
public float Label { get; set; }
// Predicted score from the trainer.
public float Score { get; set; }
}
// Print some evaluation metrics to regression problems.
private static void PrintMetrics(RegressionMetrics metrics)
{
Console.WriteLine("Mean Absolute Error: " + metrics.MeanAbsoluteError);
Console.WriteLine("Mean Squared Error: " + metrics.MeanSquaredError);
Console.WriteLine(
"Root Mean Squared Error: " + metrics.RootMeanSquaredError);
Console.WriteLine("RSquared: " + metrics.RSquared);
}
}
}
Applies to
FastForest(BinaryClassificationCatalog+BinaryClassificationTrainers, String, String, String, Int32, Int32, Int32)
Create FastForestBinaryTrainer, which predicts a target using a decision tree regression model.
public static Microsoft.ML.Trainers.FastTree.FastForestBinaryTrainer FastForest (this Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers catalog, string labelColumnName = "Label", string featureColumnName = "Features", string exampleWeightColumnName = default, int numberOfLeaves = 20, int numberOfTrees = 100, int minimumExampleCountPerLeaf = 10);static member FastForest : Microsoft.ML.BinaryClassificationCatalog.BinaryClassificationTrainers * string * string * string * int * int * int -> Microsoft.ML.Trainers.FastTree.FastForestBinaryTrainer<Extension()>
Public Function FastForest (catalog As BinaryClassificationCatalog.BinaryClassificationTrainers, Optional labelColumnName As String = "Label", Optional featureColumnName As String = "Features", Optional exampleWeightColumnName As String = Nothing, Optional numberOfLeaves As Integer = 20, Optional numberOfTrees As Integer = 100, Optional minimumExampleCountPerLeaf As Integer = 10) As FastForestBinaryTrainerParameters
- featureColumnName
- String
The name of the feature column. The column data must be a known-sized vector of Single.
- exampleWeightColumnName
- String
The name of the example weight column (optional).
- numberOfLeaves
- Int32
The maximum number of leaves per decision tree.
- numberOfTrees
- Int32
Total number of decision trees to create in the ensemble.
- minimumExampleCountPerLeaf
- Int32
The minimal number of data points required to form a new tree leaf.
Returns
Examples
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
namespace Samples.Dynamic.Trainers.BinaryClassification
{
public static class FastForest
{
// This example requires installation of additional NuGet package for
// Microsoft.ML.FastTree at
// https://www.nuget.org/packages/Microsoft.ML.FastTree/
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
.FastForest();
// 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();
// Print 5 predictions.
foreach (var p in predictions.Take(5))
Console.WriteLine($"Label: {p.Label}, "
+ $"Prediction: {p.PredictedLabel}");
// Expected output:
// Label: True, Prediction: True
// Label: False, Prediction: False
// Label: True, Prediction: True
// Label: True, Prediction: True
// Label: False, Prediction: False
// Evaluate the overall metrics.
var metrics = mlContext.BinaryClassification
.EvaluateNonCalibrated(transformedTestData);
PrintMetrics(metrics);
// Expected output:
// Accuracy: 0.74
// AUC: 0.83
// F1 Score: 0.74
// Negative Precision: 0.78
// Negative Recall: 0.71
// Positive Precision: 0.71
// Positive Recall: 0.78
//
// TEST POSITIVE RATIO: 0.4760 (238.0/(238.0+262.0))
// Confusion table
// ||======================
// PREDICTED || positive | negative | Recall
// TRUTH ||======================
// positive || 34 | 204 | 0.1429
// negative || 21 | 241 | 0.9198
// ||======================
// Precision || 0.6182 | 0.5416 |
}
private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
int seed = 0)
{
var random = new Random(seed);
float randomFloat() => (float)random.NextDouble();
for (int i = 0; i < count; i++)
{
var label = randomFloat() > 0.5f;
yield return new DataPoint
{
Label = label,
// Create random features that are correlated with the label.
// For data points with false label, the feature values are
// slightly increased by adding a constant.
Features = Enumerable.Repeat(label, 50)
.Select(x => x ? randomFloat() : randomFloat() +
0.03f).ToArray()
};
}
}
// Example with label and 50 feature values. A data set is a collection of
// such examples.
private class DataPoint
{
public bool Label { get; set; }
[VectorType(50)]
public float[] Features { get; set; }
}
// Class used to capture predictions.
private class Prediction
{
// Original label.
public bool Label { get; set; }
// Predicted label from the trainer.
public bool PredictedLabel { get; set; }
}
// Pretty-print BinaryClassificationMetrics objects.
private static void PrintMetrics(BinaryClassificationMetrics metrics)
{
Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
Console.WriteLine($"Negative Precision: " +
$"{metrics.NegativePrecision:F2}");
Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
Console.WriteLine($"Positive Precision: " +
$"{metrics.PositivePrecision:F2}");
Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}\n");
Console.WriteLine(metrics.ConfusionMatrix.GetFormattedConfusionTable());
}
}
}
Applies to
FastForest(RegressionCatalog+RegressionTrainers, String, String, String, Int32, Int32, Int32)
Create FastForestRegressionTrainer, which predicts a target using a decision tree regression model.
public static Microsoft.ML.Trainers.FastTree.FastForestRegressionTrainer FastForest (this Microsoft.ML.RegressionCatalog.RegressionTrainers catalog, string labelColumnName = "Label", string featureColumnName = "Features", string exampleWeightColumnName = default, int numberOfLeaves = 20, int numberOfTrees = 100, int minimumExampleCountPerLeaf = 10);static member FastForest : Microsoft.ML.RegressionCatalog.RegressionTrainers * string * string * string * int * int * int -> Microsoft.ML.Trainers.FastTree.FastForestRegressionTrainer<Extension()>
Public Function FastForest (catalog As RegressionCatalog.RegressionTrainers, Optional labelColumnName As String = "Label", Optional featureColumnName As String = "Features", Optional exampleWeightColumnName As String = Nothing, Optional numberOfLeaves As Integer = 20, Optional numberOfTrees As Integer = 100, Optional minimumExampleCountPerLeaf As Integer = 10) As FastForestRegressionTrainerParameters
The RegressionCatalog.
- featureColumnName
- String
The name of the feature column. The column data must be a known-sized vector of Single
- exampleWeightColumnName
- String
The name of the example weight column (optional).
- numberOfLeaves
- Int32
The maximum number of leaves per decision tree.
- numberOfTrees
- Int32
Total number of decision trees to create in the ensemble.
- minimumExampleCountPerLeaf
- Int32
The minimal number of data points required to form a new tree leaf.
Returns
Examples
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
namespace Samples.Dynamic.Trainers.Regression
{
public static class FastForestRegression
{
// This example requires installation of additional NuGet
// package for Microsoft.ML.FastTree found at
// https://www.nuget.org/packages/Microsoft.ML.FastTree/
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.Regression.Trainers.FastForest(
labelColumnName: nameof(DataPoint.Label),
featureColumnName: nameof(DataPoint.Features));
// 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(5, 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 for the Label, side by side with the actual
// Label for comparison.
foreach (var p in predictions)
Console.WriteLine($"Label: {p.Label:F3}, Prediction: {p.Score:F3}");
// Expected output:
// Label: 0.985, Prediction: 0.864
// Label: 0.155, Prediction: 0.164
// Label: 0.515, Prediction: 0.470
// Label: 0.566, Prediction: 0.501
// Label: 0.096, Prediction: 0.138
// Evaluate the overall metrics
var metrics = mlContext.Regression.Evaluate(transformedTestData);
PrintMetrics(metrics);
// Expected output:
// Mean Absolute Error: 0.06
// Mean Squared Error: 0.00
// Root Mean Squared Error: 0.07
// RSquared: 0.96 (closer to 1 is better. The worst case is 0)
}
private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count,
int seed = 0)
{
var random = new Random(seed);
for (int i = 0; i < count; i++)
{
float label = (float)random.NextDouble();
yield return new DataPoint
{
Label = label,
// Create random features that are correlated with the label.
Features = Enumerable.Repeat(label, 50).Select(
x => x + (float)random.NextDouble()).ToArray()
};
}
}
// Example with label and 50 feature values. A data set is a collection of
// such examples.
private class DataPoint
{
public float Label { get; set; }
[VectorType(50)]
public float[] Features { get; set; }
}
// Class used to capture predictions.
private class Prediction
{
// Original label.
public float Label { get; set; }
// Predicted score from the trainer.
public float Score { get; set; }
}
// Print some evaluation metrics to regression problems.
private static void PrintMetrics(RegressionMetrics metrics)
{
Console.WriteLine("Mean Absolute Error: " + metrics.MeanAbsoluteError);
Console.WriteLine("Mean Squared Error: " + metrics.MeanSquaredError);
Console.WriteLine(
"Root Mean Squared Error: " + metrics.RootMeanSquaredError);
Console.WriteLine("RSquared: " + metrics.RSquared);
}
}
}