Pass hashBits, invertHash to OneHotHashEncodingEstimator (#1564)

Author: feiyun0112

src/Microsoft.ML.Transforms/CategoricalCatalog.cs

@@ -43,13 +43,17 @@ public static OneHotEncodingEstimator OneHotEncoding(this TransformsCatalog.Cate
         /// <param name="catalog">The transform catalog</param>
         /// <param name="inputColumn">The input column</param>
         /// <param name="outputColumn">The output column. If <c>null</c>, <paramref name="inputColumn"/> is used.</param>
+        /// <param name="hashBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
+        /// <param name="invertHash">Limit the number of keys used to generate the slot name to this many. 0 means no invert hashing, -1 means no limit.</param>
         /// <param name="outputKind">The conversion mode.</param>
         /// <returns></returns>
         public static OneHotHashEncodingEstimator OneHotHashEncoding(this TransformsCatalog.CategoricalTransforms catalog,
                 string inputColumn,
                 string outputColumn = null,
+                int hashBits = OneHotHashEncodingEstimator.Defaults.HashBits,
+                int invertHash = OneHotHashEncodingEstimator.Defaults.InvertHash,
                 OneHotEncodingTransformer.OutputKind outputKind = OneHotEncodingTransformer.OutputKind.Ind)
-            => new OneHotHashEncodingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, outputKind);
+            => new OneHotHashEncodingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, hashBits, invertHash, outputKind);
 
         /// <summary>
         /// Convert several text column into hash-based one-hot encoded vectors.

src/Microsoft.ML.Transforms/OneHotHashEncodingTransformer.cs

@@ -145,7 +145,7 @@ public static IDataView Create(IHostEnvironment env,
             int invertHash = OneHotHashEncodingEstimator.Defaults.InvertHash,
             OneHotEncodingTransformer.OutputKind outputKind = OneHotHashEncodingEstimator.Defaults.OutputKind)
         {
-            return new OneHotHashEncodingEstimator(env, name, source, outputKind).Fit(input).Transform(input) as IDataView;
+            return new OneHotHashEncodingEstimator(env, name, source, hashBits, invertHash, outputKind).Fit(input).Transform(input) as IDataView;
         }
 
         internal static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input)
@@ -240,10 +240,16 @@ public ColumnInfo(string input, string output,
         /// <param name="env">Host Environment.</param>
         /// <param name="inputColumn">Name of the input column.</param>
         /// <param name="outputColumn">Name of the output column. If this is null '<paramref name="inputColumn"/>' will be used.</param>
+        /// <param name="hashBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
+        /// <param name="invertHash">Limit the number of keys used to generate the slot name to this many. 0 means no invert hashing, -1 means no limit.</param>
         /// <param name="outputKind">The type of output expected.</param>
-        public OneHotHashEncodingEstimator(IHostEnvironment env, string inputColumn,
-            string outputColumn = null, OneHotEncodingTransformer.OutputKind outputKind = Defaults.OutputKind)
-            : this(env, new ColumnInfo(inputColumn, outputColumn ?? inputColumn, outputKind))
+        public OneHotHashEncodingEstimator(IHostEnvironment env,
+            string inputColumn,
+            string outputColumn,
+            int hashBits = OneHotHashEncodingEstimator.Defaults.HashBits,
+            int invertHash = OneHotHashEncodingEstimator.Defaults.InvertHash,
+            OneHotEncodingTransformer.OutputKind outputKind = Defaults.OutputKind)
+            : this(env, new ColumnInfo(inputColumn, outputColumn ?? inputColumn, outputKind, hashBits, invertHash: invertHash))
         {
         }
 

test/Microsoft.ML.Tests/Transformers/CategoricalTests.cs

@@ -64,6 +64,20 @@ public void CategoricalWorkout()
             Done();
         }
 
+        [Fact]
+        public void CategoricalOneHotHashEncoding()
+        {
+            var data = new[] { new TestClass() { A = 1, B = 2, C = 3, }, new TestClass() { A = 4, B = 5, C = 6 } };
+
+            var mlContext = new MLContext();
+            var dataView = ComponentCreation.CreateDataView(mlContext, data);
+
+            var pipe = mlContext.Transforms.Categorical.OneHotHashEncoding("A", "CatA", 16, 0, OneHotEncodingTransformer.OutputKind.Bag);
+
+            TestEstimatorCore(pipe, dataView);
+            Done();
+        }
+
         [Fact]
         public void CategoricalStatic()
         {