Tree-based featurization #3812
Add a sample
- Loading branch information
commit 49fe1d713ebbf0d5f55eeab2c696daee1a665c89
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,131 @@ | ||
| using System; | ||
| using System.Collections.Generic; | ||
| using System.Linq; | ||
| using Microsoft.ML; | ||
| using Microsoft.ML.Data; | ||
| using Microsoft.ML.Trainers.FastTree; | ||
|
|
||
| namespace Samples.Dynamic.Transforms.TreeFeaturization | ||
| { | ||
| public static class PretrainedTreeEnsembleFeaturizationWithOptions | ||
| { | ||
| public static void Example() | ||
| { | ||
| // Create data set | ||
| int dataPointCount = 200; | ||
| // 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(dataPointCount).ToList(); | ||
|
|
||
| // Convert the list of data points to an IDataView object, which is consumable by ML.NET API. | ||
| var dataView = mlContext.Data.LoadFromEnumerable(dataPoints); | ||
|
|
||
| // Define input and output columns of tree-based featurizer. | ||
| string labelColumnName = nameof(DataPoint.Label); | ||
| string featureColumnName = nameof(DataPoint.Features); | ||
| string treesColumnName = nameof(TransformedDataPoint.Trees); | ||
| string leavesColumnName = nameof(TransformedDataPoint.Leaves); | ||
| string pathsColumnName = nameof(TransformedDataPoint.Paths); | ||
|
|
||
| // Define a tree model whose trees will be extracted to construct a tree featurizer. | ||
| var trainer = mlContext.BinaryClassification.Trainers.FastTree( | ||
| new FastTreeBinaryTrainer.Options | ||
| { | ||
| NumberOfThreads = 1, | ||
| NumberOfTrees = 1, | ||
| NumberOfLeaves = 4, | ||
| MinimumExampleCountPerLeaf = 1, | ||
| FeatureColumnName = featureColumnName, | ||
| LabelColumnName = labelColumnName | ||
| }); | ||
|
|
||
| // Train the defined tree model. | ||
| var model = trainer.Fit(dataView); | ||
| var predicted = model.Transform(dataView); | ||
|
|
||
| // Define the configuration of tree-based featurizer. | ||
| var options = new PretrainedTreeFeaturizationEstimator.Options() | ||
| { | ||
| InputColumnName = featureColumnName, | ||
| ModelParameters = model.Model.SubModel, // Pretrained tree model. | ||
| TreesColumnName = treesColumnName, | ||
| LeavesColumnName = leavesColumnName, | ||
| PathsColumnName = pathsColumnName | ||
| }; | ||
|
|
||
| // Fit the created featurizer. It doesn't perform actual training because a pretrained model is provided. | ||
| var treeFeaturizer = mlContext.Transforms.FeaturizeByPretrainTreeEnsemble(options).Fit(dataView); | ||
|
|
||
| // Apply TreeEnsembleFeaturizer to the input data. | ||
| var transformed = treeFeaturizer.Transform(dataView); | ||
|
|
||
| // Convert IDataView object to a list. Each element in the resulted list corresponds to a row in the IDataView. | ||
| var transformedDataPoints = mlContext.Data.CreateEnumerable<TransformedDataPoint>(transformed, false).ToList(); | ||
|
|
||
| // Print out the transformation of the first 3 data points. | ||
| for (int i = 0; i < 3; ++i) | ||
| { | ||
| var dataPoint = dataPoints[i]; | ||
| var transformedDataPoint = transformedDataPoints[i]; | ||
| Console.WriteLine($"The original feature vector [{String.Join(",", dataPoint.Features)}] is transformed to three different tree-based feature vectors:"); | ||
| Console.WriteLine($" Trees' output values: [{String.Join(",", transformedDataPoint.Trees)}]."); | ||
| Console.WriteLine($" Leave IDs' 0-1 representation: [{String.Join(",", transformedDataPoint.Leaves)}]."); | ||
| Console.WriteLine($" Paths IDs' 0-1 representation: [{String.Join(",", transformedDataPoint.Paths)}]."); | ||
| } | ||
|
|
||
| // Expected output: | ||
| // The original feature vector[0.8173254, 0.7680227, 0.5581612] is transformed to three different tree - based feature vectors: | ||
| // Trees' output values: [0.4172185]. | ||
| // Leave IDs' 0-1 representation: [1,0,0,0]. | ||
| // Paths IDs' 0-1 representation: [1,1,1]. | ||
| // The original feature vector[0.7588848, 1.106027, 0.6421779] is transformed to three different tree - based feature vectors: | ||
| // Trees' output values: [-1]. | ||
| // Leave IDs' 0-1 representation: [0,0,1,0]. | ||
| // Paths IDs' 0-1 representation: [1,1,0]. | ||
| // The original feature vector[0.2737045, 0.2919063, 0.4673147] is transformed to three different tree - based feature vectors: | ||
| // Trees' output values: [0.4172185]. | ||
| // Leave IDs' 0-1 representation: [1,0,0,0]. | ||
| // Paths IDs' 0-1 representation: [1,1,1]. | ||
| } | ||
|
|
||
| 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() > 0.5; | ||
| 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, 3).Select(x => x ? randomFloat() : randomFloat() + 0.2f).ToArray() | ||
| }; | ||
| } | ||
| } | ||
|
|
||
| // Example with label and 3 feature values. A data set is a collection of such examples. | ||
| private class DataPoint | ||
| { | ||
| public bool Label { get; set; } | ||
| [VectorType(3)] | ||
| public float[] Features { get; set; } | ||
| } | ||
|
|
||
| // Class used to capture the output of tree-base featurization. | ||
| private class TransformedDataPoint : DataPoint | ||
| { | ||
| // The i-th value is the output value of the i-th decision tree. | ||
| public float[] Trees { get; set; } | ||
| // The 0-1 encoding of leaves the input feature vector falls into. | ||
| public float[] Leaves { get; set; } | ||
| // The 0-1 encoding of paths the input feature vector reaches the leaves. | ||
| public float[] Paths { get; set; } | ||
| } | ||
| } | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
May want to note in its name that FastTreeTweedie is regression: (the naming of the others list their task types)
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes if the model name doesn't tell the task. Given that
Tweediesomehow implies a regression case, we don't haveRegressionappended to any of publicTweediemodules. This pattern can be seen inFastTreeTweedieTrainerandFastTreeTweedieModelParameters. #Resolved