Skip to content

Commit

Permalink
Scrub changes for LightGBM (#2808)
Browse files Browse the repository at this point in the history 
Api clean up for LightGBM. The cleanup includes:
- Changing all abbreviated parameters to full names (i.e. numThreads->NumberOfThreads)
- Moving protected to private protected
- Updated baseline files to reflect these changes which are semantical
and should not have any computational difference.

Part of the fix for #2618
  • Loading branch information
@singlis
singlis committed Mar 5, 2019
1 parent a4bfd93 commit d28886f
Show file tree
Hide file tree
Showing 39 changed files with 458 additions and 492 deletions.
2 changes: 1 addition & 1 deletion ...les/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/LightGbmWithOptions.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ public static void Example()
FeatureColumnName = "Features",
Booster = new DartBooster.Options
{
DropRate = 0.15,
TreeDropFraction = 0.15,
XgboostDartMode = false
}
}))
Expand Down
6 changes: 3 additions & 3 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbm.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -20,10 +20,10 @@ public static void Example()

// Create the Estimator pipeline. For simplicity, we will train a small tree with 4 leaves and 2 boosting iterations.
var pipeline = mlContext.Ranking.Trainers.LightGbm(
numLeaves: 4,
minDataPerLeaf: 10,
numberOfLeaves: 4,
minimumExampleCountPerLeaf: 10,
learningRate: 0.1,
numBoostRound: 2);
numberOfIterations: 2);

// Fit this Pipeline to the Training Data.
var model = pipeline.Fit(split.TrainSet);
Expand Down
6 changes: 3 additions & 3 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbmWithOptions.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -23,10 +23,10 @@ public static void Example()
var pipeline = mlContext.Ranking.Trainers.LightGbm(
new Options
{
NumLeaves = 4,
MinDataPerLeaf = 10,
NumberOfLeaves = 4,
MinimumExampleCountPerGroup = 10,
LearningRate = 0.1,
NumBoostRound = 2,
NumberOfIterations = 2,
Booster = new TreeBooster.Options
{
FeatureFraction = 0.9
Expand Down
4 changes: 2 additions & 2 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbm.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -35,8 +35,8 @@ public static void Example()
var pipeline = mlContext.Transforms.Concatenate("Features", featureNames)
.Append(mlContext.Regression.Trainers.LightGbm(
labelColumnName: labelName,
numLeaves: 4,
minDataPerLeaf: 6,
numberOfLeaves: 4,
minimumExampleCountPerLeaf: 6,
learningRate: 0.001));

// Fit this pipeline to the training data.
Expand Down
4 changes: 2 additions & 2 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbmWithOptions.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -39,8 +39,8 @@ public static void Example()
.Append(mlContext.Regression.Trainers.LightGbm(new Options
{
LabelColumnName = labelName,
NumLeaves = 4,
MinDataPerLeaf = 6,
NumberOfLeaves = 4,
MinimumExampleCountPerLeaf = 6,
LearningRate = 0.001,
Booster = new GossBooster.Options
{
Expand Down
4 changes: 2 additions & 2 deletions docs/samples/Microsoft.ML.Samples/Static/LightGBMBinaryClassification.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -78,8 +78,8 @@ public static void LightGbmBinaryClassification()
Score: mlContext.BinaryClassification.Trainers.LightGbm(
row.Label,
row.Features,
numLeaves: 4,
minDataPerLeaf: 6,
numberOfLeaves: 4,
minimumExampleCountPerLeaf: 6,
learningRate: 0.001)))
.Append(row => (
Label: row.Label,
Expand Down
4 changes: 2 additions & 2 deletions docs/samples/Microsoft.ML.Samples/Static/LightGBMRegression.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -38,8 +38,8 @@ public static void LightGbmRegression()
.Append(r => (r.label, score: mlContext.Regression.Trainers.LightGbm(
r.label,
r.features,
numLeaves: 4,
minDataPerLeaf: 6,
numberOfLeaves: 4,
minimumExampleCountPerLeaf: 6,
learningRate: 0.001,
onFit: p => pred = p)
)
Expand Down
89 changes: 47 additions & 42 deletions src/Microsoft.ML.LightGBM.StaticPipe/LightGbmStaticExtensions.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,10 +21,10 @@ public static class LightGbmStaticExtensions
/// <param name="label">The label column.</param>
/// <param name="features">The features column.</param>
/// <param name="weights">The weights column.</param>
/// <param name="numLeaves">The number of leaves to use.</param>
/// <param name="numBoostRound">Number of iterations.</param>
/// <param name="minDataPerLeaf">The minimal number of documents allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="numberOfLeaves">The number of leaves to use.</param>
/// <param name="minimumExampleCountPerLeaf">The minimal number of data points allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="learningRate">The learning rate.</param>
/// <param name="numberOfIterations">Number of iterations.</param>
/// <param name="onFit">A delegate that is called every time the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}.Fit(DataView{TInShape})"/> method is called on the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}"/> instance created out of this. This delegate will receive
Expand All @@ -39,19 +39,19 @@ public static class LightGbmStaticExtensions
/// </example>
public static Scalar<float> LightGbm(this RegressionCatalog.RegressionTrainers catalog,
Scalar<float> label, Vector<float> features, Scalar<float> weights = null,
int? numLeaves = null,
int? minDataPerLeaf = null,
int? numberOfLeaves = null,
int? minimumExampleCountPerLeaf = null,
double? learningRate = null,
int numBoostRound = Options.Defaults.NumBoostRound,
int numberOfIterations = Options.Defaults.NumberOfIterations,
Action<LightGbmRegressionModelParameters> onFit = null)
{
CheckUserValues(label, features, weights, numLeaves, minDataPerLeaf, learningRate, numBoostRound, onFit);
CheckUserValues(label, features, weights, numberOfLeaves, minimumExampleCountPerLeaf, learningRate, numberOfIterations, onFit);

var rec = new TrainerEstimatorReconciler.Regression(
(env, labelName, featuresName, weightsName) =>
{
var trainer = new LightGbmRegressorTrainer(env, labelName, featuresName, weightsName, numLeaves,
minDataPerLeaf, learningRate, numBoostRound);
var trainer = new LightGbmRegressorTrainer(env, labelName, featuresName, weightsName, numberOfLeaves,
minimumExampleCountPerLeaf, learningRate, numberOfIterations);
if (onFit != null)
return trainer.WithOnFitDelegate(trans => onFit(trans.Model));
return trainer;
Expand Down Expand Up @@ -104,10 +104,10 @@ public static Scalar<float> LightGbm(this RegressionCatalog.RegressionTrainers c
/// <param name="label">The label column.</param>
/// <param name="features">The features column.</param>
/// <param name="weights">The weights column.</param>
/// <param name="numLeaves">The number of leaves to use.</param>
/// <param name="numBoostRound">Number of iterations.</param>
/// <param name="minDataPerLeaf">The minimal number of documents allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="numberOfLeaves">The number of leaves to use.</param>
/// <param name="minimumExampleCountPerLeaf">The minimal number of data points allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="learningRate">The learning rate.</param>
/// <param name="numberOfIterations">Number of iterations.</param>
/// <param name="onFit">A delegate that is called every time the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}.Fit(DataView{TInShape})"/> method is called on the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}"/> instance created out of this. This delegate will receive
Expand All @@ -122,20 +122,22 @@ public static Scalar<float> LightGbm(this RegressionCatalog.RegressionTrainers c
/// ]]></format>
/// </example>
public static (Scalar<float> score, Scalar<float> probability, Scalar<bool> predictedLabel) LightGbm(this BinaryClassificationCatalog.BinaryClassificationTrainers catalog,
Scalar<bool> label, Vector<float> features, Scalar<float> weights = null,
int? numLeaves = null,
int? minDataPerLeaf = null,
Scalar<bool> label,
Vector<float> features,
Scalar<float> weights = null,
int? numberOfLeaves = null,
int? minimumExampleCountPerLeaf = null,
double? learningRate = null,
int numBoostRound = Options.Defaults.NumBoostRound,
int numberOfIterations = Options.Defaults.NumberOfIterations,
Action<CalibratedModelParametersBase<LightGbmBinaryModelParameters, PlattCalibrator>> onFit = null)
{
CheckUserValues(label, features, weights, numLeaves, minDataPerLeaf, learningRate, numBoostRound, onFit);
CheckUserValues(label, features, weights, numberOfLeaves, minimumExampleCountPerLeaf, learningRate, numberOfIterations, onFit);

var rec = new TrainerEstimatorReconciler.BinaryClassifier(
(env, labelName, featuresName, weightsName) =>
{
var trainer = new LightGbmBinaryTrainer(env, labelName, featuresName, weightsName, numLeaves,
minDataPerLeaf, learningRate, numBoostRound);
var trainer = new LightGbmBinaryTrainer(env, labelName, featuresName, weightsName, numberOfLeaves,
minimumExampleCountPerLeaf, learningRate, numberOfIterations);
if (onFit != null)
return trainer.WithOnFitDelegate(trans => onFit(trans.Model));
Expand Down Expand Up @@ -194,10 +196,10 @@ public static (Scalar<float> score, Scalar<float> probability, Scalar<bool> pred
/// <param name="features">The features column.</param>
/// <param name="groupId">The groupId column.</param>
/// <param name="weights">The weights column.</param>
/// <param name="numLeaves">The number of leaves to use.</param>
/// <param name="numBoostRound">Number of iterations.</param>
/// <param name="minDataPerLeaf">The minimal number of documents allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="numberOfLeaves">The number of leaves to use.</param>
/// <param name="minimumExampleCountPerLeaf">The minimal number of data points allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="learningRate">The learning rate.</param>
/// <param name="numberOfIterations">Number of iterations.</param>
/// <param name="onFit">A delegate that is called every time the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}.Fit(DataView{TInShape})"/> method is called on the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}"/> instance created out of this. This delegate will receive
Expand All @@ -206,21 +208,24 @@ public static (Scalar<float> score, Scalar<float> probability, Scalar<bool> pred
/// <returns>The set of output columns including in order the predicted binary classification score (which will range
/// from negative to positive infinity), the calibrated prediction (from 0 to 1), and the predicted label.</returns>
public static Scalar<float> LightGbm<TVal>(this RankingCatalog.RankingTrainers catalog,
Scalar<float> label, Vector<float> features, Key<uint, TVal> groupId, Scalar<float> weights = null,
int? numLeaves = null,
int? minDataPerLeaf = null,
Scalar<float> label,
Vector<float> features,
Key<uint, TVal> groupId,
Scalar<float> weights = null,
int? numberOfLeaves = null,
int? minimumExampleCountPerLeaf = null,
double? learningRate = null,
int numBoostRound = Options.Defaults.NumBoostRound,
int numberOfIterations = Options.Defaults.NumberOfIterations,
Action<LightGbmRankingModelParameters> onFit = null)
{
CheckUserValues(label, features, weights, numLeaves, minDataPerLeaf, learningRate, numBoostRound, onFit);
CheckUserValues(label, features, weights, numberOfLeaves, minimumExampleCountPerLeaf, learningRate, numberOfIterations, onFit);
Contracts.CheckValue(groupId, nameof(groupId));

var rec = new TrainerEstimatorReconciler.Ranker<TVal>(
(env, labelName, featuresName, groupIdName, weightsName) =>
{
var trainer = new LightGbmRankingTrainer(env, labelName, featuresName, groupIdName, weightsName, numLeaves,
minDataPerLeaf, learningRate, numBoostRound);
var trainer = new LightGbmRankingTrainer(env, labelName, featuresName, groupIdName, weightsName, numberOfLeaves,
minimumExampleCountPerLeaf, learningRate, numberOfIterations);
if (onFit != null)
return trainer.WithOnFitDelegate(trans => onFit(trans.Model));
Expand Down Expand Up @@ -279,10 +284,10 @@ public static Scalar<float> LightGbm<TVal>(this RankingCatalog.RankingTrainers c
/// <param name="label">The label, or dependent variable.</param>
/// <param name="features">The features, or independent variables.</param>
/// <param name="weights">The weights column.</param>
/// <param name="numLeaves">The number of leaves to use.</param>
/// <param name="numBoostRound">Number of iterations.</param>
/// <param name="minDataPerLeaf">The minimal number of documents allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="numberOfLeaves">The number of leaves to use.</param>
/// <param name="minimumExampleCountPerLeaf">The minimal number of data points allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="learningRate">The learning rate.</param>
/// <param name="numberOfIterations">Number of iterations.</param>
/// <param name="onFit">A delegate that is called every time the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}.Fit(DataView{TInShape})"/> method is called on the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}"/> instance created out of this. This delegate will receive
Expand All @@ -301,19 +306,19 @@ public static (Vector<float> score, Key<uint, TVal> predictedLabel)
Key<uint, TVal> label,
Vector<float> features,
Scalar<float> weights = null,
int? numLeaves = null,
int? minDataPerLeaf = null,
int? numberOfLeaves = null,
int? minimumExampleCountPerLeaf = null,
double? learningRate = null,
int numBoostRound = Options.Defaults.NumBoostRound,
int numberOfIterations = Options.Defaults.NumberOfIterations,
Action<OneVersusAllModelParameters> onFit = null)
{
CheckUserValues(label, features, weights, numLeaves, minDataPerLeaf, learningRate, numBoostRound, onFit);
CheckUserValues(label, features, weights, numberOfLeaves, minimumExampleCountPerLeaf, learningRate, numberOfIterations, onFit);

var rec = new TrainerEstimatorReconciler.MulticlassClassifier<TVal>(
(env, labelName, featuresName, weightsName) =>
{
var trainer = new LightGbmMulticlassTrainer(env, labelName, featuresName, weightsName, numLeaves,
minDataPerLeaf, learningRate, numBoostRound);
var trainer = new LightGbmMulticlassTrainer(env, labelName, featuresName, weightsName, numberOfLeaves,
minimumExampleCountPerLeaf, learningRate, numberOfIterations);
if (onFit != null)
return trainer.WithOnFitDelegate(trans => onFit(trans.Model));
Expand Down Expand Up @@ -365,17 +370,17 @@ public static (Vector<float> score, Key<uint, TVal> predictedLabel)
}

private static void CheckUserValues(PipelineColumn label, Vector<float> features, Scalar<float> weights,
int? numLeaves,
int? minDataPerLeaf,
int? numberOfLeaves,
int? minimumExampleCountPerLeaf,
double? learningRate,
int numBoostRound,
Delegate onFit)
{
Contracts.CheckValue(label, nameof(label));
Contracts.CheckValue(features, nameof(features));
Contracts.CheckValueOrNull(weights);
Contracts.CheckParam(!(numLeaves < 2), nameof(numLeaves), "Must be at least 2.");
Contracts.CheckParam(!(minDataPerLeaf <= 0), nameof(minDataPerLeaf), "Must be positive");
Contracts.CheckParam(!(numberOfLeaves < 2), nameof(numberOfLeaves), "Must be at least 2.");
Contracts.CheckParam(!(minimumExampleCountPerLeaf <= 0), nameof(minimumExampleCountPerLeaf), "Must be positive");
Contracts.CheckParam(!(learningRate <= 0), nameof(learningRate), "Must be positive");
Contracts.CheckParam(numBoostRound > 0, nameof(numBoostRound), "Must be positive");
Contracts.CheckValueOrNull(onFit);
Expand Down
Loading

0 comments on commit d28886f

Please sign in to comment.