Skip to content

Respect group id in options for ranking task #2742

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 26, 2019
Merged

Respect group id in options for ranking task #2742

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions src/Microsoft.ML.FastTree/FastTree.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,8 @@ private protected FastTreeTrainerBase(IHostEnvironment env,
/// Constructor that is used when invoking the classes deriving from this, through maml.
/// </summary>
private protected FastTreeTrainerBase(IHostEnvironment env, TOptions options, SchemaShape.Column label)
: base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), TrainerUtils.MakeR4VecFeature(options.FeatureColumn), label, TrainerUtils.MakeR4ScalarWeightColumn(options.WeightColumn))
: base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), TrainerUtils.MakeR4VecFeature(options.FeatureColumn), label, TrainerUtils.MakeR4ScalarWeightColumn(options.WeightColumn),
TrainerUtils.MakeU4ScalarColumn(options.GroupIdColumn))
{
Host.CheckValue(options, nameof(options));
FastTreeTrainerOptions = options;
Expand Down Expand Up @@ -1842,7 +1843,7 @@ private void MakeBoundariesAndCheckLabels(out long missingInstances, out long to
{
hasGroup = _data.Schema.Group != null;

if(hasGroup)
if (hasGroup)
curOptions |= CursOpt.Group;
}
else
Expand Down
7 changes: 4 additions & 3 deletions src/Microsoft.ML.LightGBM/LightGbmTrainerBase.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,8 @@ private protected LightGbmTrainerBase(IHostEnvironment env,
}

private protected LightGbmTrainerBase(IHostEnvironment env, string name, Options options, SchemaShape.Column label)
: base(Contracts.CheckRef(env, nameof(env)).Register(name), TrainerUtils.MakeR4VecFeature(options.FeatureColumn), label, TrainerUtils.MakeR4ScalarWeightColumn(options.WeightColumn))
: base(Contracts.CheckRef(env, nameof(env)).Register(name), TrainerUtils.MakeR4VecFeature(options.FeatureColumn), label,
TrainerUtils.MakeR4ScalarWeightColumn(options.WeightColumn), TrainerUtils.MakeU4ScalarColumn(options.GroupIdColumn))
{
Host.CheckValue(options, nameof(options));

Expand Down Expand Up @@ -163,7 +164,7 @@ private protected virtual void CheckDataValid(IChannel ch, RoleMappedData data)
ch.CheckParam(data.Schema.Label.HasValue, nameof(data), "Need a label column");
}

protected virtual void GetDefaultParameters(IChannel ch, int numRow, bool hasCategarical, int totalCats, bool hiddenMsg=false)
protected virtual void GetDefaultParameters(IChannel ch, int numRow, bool hasCategarical, int totalCats, bool hiddenMsg = false)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hasCategarical [](start = 82, length = 14)

misspelling -- should be hasCategorical.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hiddenMsg [](start = 118, length = 9)

for the sake of not having short names -hiddenMessage?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'll leave that stuff to whoever would scrub lightgbm learners.

{
double learningRate = LightGbmTrainerOptions.LearningRate ?? DefaultLearningRate(numRow, hasCategarical, totalCats);
int numLeaves = LightGbmTrainerOptions.NumLeaves ?? DefaultNumLeaves(numRow, hasCategarical, totalCats);
Expand Down Expand Up @@ -584,7 +585,7 @@ private void CreateDatasetFromSamplingData(IChannel ch, FloatLabelCursor.Factory
int[] nonZeroCntPerColumn = new int[catMetaData.NumCol];
int estimateNonZeroCnt = (int)(numSampleRow * density);
estimateNonZeroCnt = Math.Max(1, estimateNonZeroCnt);
for(int i = 0; i < catMetaData.NumCol; i++)
for (int i = 0; i < catMetaData.NumCol; i++)
{
nonZeroCntPerColumn[i] = 0;
sampleValuePerColumn[i] = new double[estimateNonZeroCnt];
Expand Down
5 changes: 3 additions & 2 deletions test/Microsoft.ML.Tests/TrainerEstimators/TreeEstimators.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,8 @@ public void FastTreeRankerEstimator()
new FastTreeRankingTrainer.Options
{
FeatureColumn = "NumericFeatures",
NumTrees = 10
NumTrees = 10,
GroupIdColumn = "Group"
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

GroupIdColumn [](start = 20, length = 13)

I feel like this should be "GroupColumn" to fall more inline with FeatureColumn and LabelColumn.

});

var pipeWithTrainer = pipe.Append(trainer);
Expand All @@ -134,7 +135,7 @@ public void LightGBMRankerEstimator()
{
var (pipe, dataView) = GetRankingPipeline();

var trainer = ML.Ranking.Trainers.LightGbm(labelColumnName: "Label0", featureColumnName: "NumericFeatures", rowGroupColumnName: "Group", learningRate: 0.4);
var trainer = ML.Ranking.Trainers.LightGbm(new Options() { LabelColumn = "Label0", FeatureColumn = "NumericFeatures", GroupIdColumn = "Group", LearningRate = 0.4 });

var pipeWithTrainer = pipe.Append(trainer);
TestEstimatorCore(pipeWithTrainer, dataView);
Expand Down