Pass group id via options (#2742)

Author: Ivanidzo4ka

src/Microsoft.ML.FastTree/FastTree.cs

@@ -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;
@@ -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

src/Microsoft.ML.LightGBM/LightGbmTrainerBase.cs

@@ -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));
 
@@ -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)
         {
             double learningRate = LightGbmTrainerOptions.LearningRate ?? DefaultLearningRate(numRow, hasCategarical, totalCats);
             int numLeaves = LightGbmTrainerOptions.NumLeaves ?? DefaultNumLeaves(numRow, hasCategarical, totalCats);
@@ -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];

test/Microsoft.ML.Tests/TrainerEstimators/TreeEstimators.cs

@@ -115,7 +115,8 @@ public void FastTreeRankerEstimator()
                 new FastTreeRankingTrainer.Options
                 {
                     FeatureColumn = "NumericFeatures",
-                    NumTrees = 10
+                    NumTrees = 10,
+                    GroupIdColumn = "Group"
                 });
 
             var pipeWithTrainer = pipe.Append(trainer);
@@ -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);