From c9339144161b3fdffc8734a41a798e0a28f788f2 Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Thu, 3 Sep 2020 21:34:49 +0100
Subject: [PATCH 01/17] FeatureHasher

---
 .../IpcTests/ML/Feature/FeatureHasherTests.cs |  50 ++++++
 .../ML/Feature/FeatureHasher.cs               | 145 ++++++++++++++++++
 2 files changed, 195 insertions(+)
 create mode 100644 src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
 create mode 100644 src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
new file mode 100644
index 000000000..42c224877
--- /dev/null
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
@@ -0,0 +1,50 @@
+using System;
+using System.Collections.Generic;
+using Microsoft.Spark.ML.Feature;
+using Microsoft.Spark.Sql;
+using Microsoft.Spark.Sql.Types;
+using Xunit;
+
+namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
+{
+    [Collection("Spark E2E Tests")]
+    public class FeatureHasherTests
+    {
+        private readonly SparkSession _spark;
+        
+        public FeatureHasherTests(SparkFixture fixture)
+        {
+            _spark = fixture.Spark;
+        }
+
+        [Fact]
+        public void TestFeatureHasher()
+        {
+            DataFrame dataFrame = _spark.CreateDataFrame(
+                new List<GenericRow>()
+                {
+                    new GenericRow(new object[] {2.0D, true, "1", "foo"}),
+                    new GenericRow(new object[] {3.0D, false, "2", "bar"})
+                },
+                new StructType(new List<StructField>()
+                {
+                    new StructField("real", new DoubleType()),
+                    new StructField("bool", new BooleanType()),
+                    new StructField("stringNum", new StringType()),
+                    new StructField("string", new StringType())
+                }));
+
+            FeatureHasher hasher = new FeatureHasher()
+                .SetInputCols(new List<string>() {"real", "bool", "stringNum", "string"})
+                .SetOutputCol("features")
+                .SetCategoricalCols(new List<string>() {"real", "string"})
+                .SetNumFeatures(10);
+
+            Assert.IsType<List<string>>(hasher.GetCategoricalCols());
+            Assert.IsType<int>(hasher.GetNumFeatures());
+
+            Assert.IsType<StructType>(hasher.TransformSchema(dataFrame.Schema()));
+            Assert.IsType<DataFrame>(hasher.Transform(dataFrame));
+        }
+    }
+}
diff --git a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
new file mode 100644
index 000000000..f836fd860
--- /dev/null
+++ b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
@@ -0,0 +1,145 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+// See the LICENSE file in the project root for more information.
+
+using System.Collections.Generic;
+using System.Linq;
+using Microsoft.Spark.Interop;
+using Microsoft.Spark.Interop.Ipc;
+using Microsoft.Spark.Sql;
+using Microsoft.Spark.Sql.Types;
+
+namespace Microsoft.Spark.ML.Feature
+{
+    public class FeatureHasher: FeatureBase<FeatureHasher>, IJvmObjectReferenceProvider
+    {
+        private static readonly string s_featureHasherClassName = 
+            "org.apache.spark.ml.feature.FeatureHasher";
+        
+        internal FeatureHasher() : base(s_featureHasherClassName)
+        {
+        }
+
+        internal FeatureHasher(string uid) : base(s_featureHasherClassName, uid)
+        {
+        }
+
+        internal FeatureHasher(JvmObjectReference jvmObject) : base(jvmObject)
+        {
+        }
+
+        JvmObjectReference IJvmObjectReferenceProvider.Reference => _jvmObject;
+        
+        /// <summary>
+        /// Loads the <see cref="FeatureHasher"/> that was previously saved using Save.
+        /// </summary>
+        /// <param name="path">
+        /// The path the previous <see cref="FeatureHasher"/> was saved to.
+        /// </param>
+        /// <returns>New <see cref="FeatureHasher"/> object</returns>
+        public static FeatureHasher Load(string path) =>
+            WrapAsFeatureHasher(
+                SparkEnvironment.JvmBridge.CallStaticJavaMethod(
+                    s_featureHasherClassName,"load", path));
+        
+        /// <summary>
+        /// Gets a list of the columns which have been specified as categorical columns.
+        /// </summary>
+        /// <returns>List of categorical columns, set by `SetCategoricalCols`</returns>
+        public IEnumerable<string> GetCategoricalCols() => 
+            ((string[])_jvmObject.Invoke("getCategoricalCols")).ToList();
+        
+        /// <summary>
+        /// Marks columns as categorical columns.
+        /// </summary>
+        /// <param name="value">List of column names to mark as a categorical column</param>
+        /// <returns>New <see cref="FeatureHasher"/> object</returns>
+        public FeatureHasher SetCategoricalCols(IEnumerable<string> value) => 
+            WrapAsFeatureHasher(_jvmObject.Invoke("setCategoricalCols", value));
+        
+        /// <summary>
+        /// Gets the columns that the <see cref="FeatureHasher"/> should read from and convert into
+        /// hashes. This would have been set by SetInputCol.
+        /// </summary>
+        /// <returns>string, the input column</returns>
+        public string GetInputCols() => (string)_jvmObject.Invoke("getInputCols");
+
+        /// <summary>
+        /// Sets the column that the <see cref="FeatureHasher"/> should read from and convert into
+        /// hashes.
+        /// </summary>
+        /// <param name="value">The name of the column to as the source of the buckets</param>
+        /// <returns>New <see cref="FeatureHasher"/> object</returns>
+        public FeatureHasher SetInputCols(IEnumerable<string> value) => 
+            WrapAsFeatureHasher(_jvmObject.Invoke("setInputCols", value));
+        
+        /// <summary>
+        /// Gets the number of features that should be used. Since a simple modulo is used to
+        /// transform the hash function to a column index, it is advisable to use a power of two
+        /// as the numFeatures parameter; otherwise the features will not be mapped evenly to the
+        /// columns.
+        /// </summary>
+        /// <returns>The number of features to be used</returns>
+        public int GetNumFeatures() => (int)_jvmObject.Invoke("getNumFeatures");
+
+        /// <summary>
+        /// Sets the number of features that should be used. Since a simple modulo is used to
+        /// transform the hash function to a column index, it is advisable to use a power of two as
+        /// the numFeatures parameter; otherwise the features will not be mapped evenly to the
+        /// columns.
+        /// </summary>
+        /// <param name="value">int</param>
+        /// <returns>New <see cref="FeatureHasher"/> object</returns>
+        public FeatureHasher SetNumFeatures(int value) => 
+            WrapAsFeatureHasher(_jvmObject.Invoke("setNumFeatures", value));
+        
+        /// <summary>
+        /// Gets the name of the column the output data will be written to. This is set by
+        /// SetInputCol
+        /// </summary>
+        /// <returns>string, the output column</returns>
+        public string GetOutputCol() => (string)_jvmObject.Invoke("getOutputCol");
+
+        /// <summary>
+        /// The <see cref="FeatureHasher"/> will create a new column in the DataFrame, this is the
+        /// name of the new column.
+        /// </summary>
+        /// <param name="value">The name of the new column which contains the hash</param>
+        /// <returns>New <see cref="FeatureHasher"/> object</returns>
+        public FeatureHasher SetOutputCol(string value) => 
+            WrapAsFeatureHasher(_jvmObject.Invoke("setOutputCol", value));
+        
+        /// <summary>
+        /// Transforms the input <see cref="DataFrame"/>. It is recommended that you validate that
+        /// the transform will succeed by calling `TransformSchema`.
+        /// </summary>
+        /// <param name="value">Input <see cref="DataFrame"/> to transform</param>
+        /// <returns>Transformed <see cref="DataFrame"/></returns>
+        public DataFrame Transform(DataFrame value) => 
+            new DataFrame((JvmObjectReference)_jvmObject.Invoke("transform", value));
+        
+        /// <summary>
+        /// Check transform validity and derive the output schema from the input schema.
+        /// We check validity for interactions between parameters during transformSchema and
+        /// raise an exception if any parameter value is invalid. Parameter value checks which do
+        /// not depend on other parameters are handled by Param.validate().    
+        ///
+        /// Typical implementation should first conduct verification on schema change and parameter
+        /// validity, including complex parameter interaction checks.
+        /// </summary>
+        /// <param name="value">
+        /// The <see cref="StructType"/> of the <see cref="DataFrame"/> which will be transformed
+        /// </param>
+        /// <returns>
+        /// The <see cref="StructType"/> of the output schema that would have been derived form the
+        /// input schema, if Transform had been called
+        /// </returns>
+        public StructType TransformSchema(StructType value) => 
+            new StructType(
+                (JvmObjectReference)_jvmObject.Invoke("transformSchema", 
+                    DataType.FromJson(_jvmObject.Jvm, value.Json)));
+
+        private static FeatureHasher WrapAsFeatureHasher(object obj) => 
+            new FeatureHasher((JvmObjectReference)obj);
+    }
+}

From 08011080339fab8aeb1a8d9e189f90e92f15659e Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Fri, 4 Sep 2020 08:32:52 +0100
Subject: [PATCH 02/17] tidy

---
 .../IpcTests/ML/Feature/FeatureHasherTests.cs     | 11 ++++++++---
 .../Microsoft.Spark/ML/Feature/FeatureHasher.cs   | 15 +++++++--------
 2 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
index 42c224877..24b0b22ee 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
@@ -1,3 +1,7 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+// See the LICENSE file in the project root for more information.
+
 using System;
 using System.Collections.Generic;
 using Microsoft.Spark.ML.Feature;
@@ -21,12 +25,12 @@ public FeatureHasherTests(SparkFixture fixture)
         public void TestFeatureHasher()
         {
             DataFrame dataFrame = _spark.CreateDataFrame(
-                new List<GenericRow>()
+                new List<GenericRow>
                 {
                     new GenericRow(new object[] {2.0D, true, "1", "foo"}),
                     new GenericRow(new object[] {3.0D, false, "2", "bar"})
                 },
-                new StructType(new List<StructField>()
+                new StructType(new List<StructField>
                 {
                     new StructField("real", new DoubleType()),
                     new StructField("bool", new BooleanType()),
@@ -40,9 +44,10 @@ public void TestFeatureHasher()
                 .SetCategoricalCols(new List<string>() {"real", "string"})
                 .SetNumFeatures(10);
 
+            Assert.IsType<string>(hasher.GetOutputCol());
+            Assert.IsType <string[]>(hasher.GetInputCols());
             Assert.IsType<List<string>>(hasher.GetCategoricalCols());
             Assert.IsType<int>(hasher.GetNumFeatures());
-
             Assert.IsType<StructType>(hasher.TransformSchema(dataFrame.Schema()));
             Assert.IsType<DataFrame>(hasher.Transform(dataFrame));
         }
diff --git a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
index f836fd860..2e31ba6b6 100644
--- a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
+++ b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
@@ -62,7 +62,7 @@ public FeatureHasher SetCategoricalCols(IEnumerable<string> value) =>
         /// hashes. This would have been set by SetInputCol.
         /// </summary>
         /// <returns>string, the input column</returns>
-        public string GetInputCols() => (string)_jvmObject.Invoke("getInputCols");
+        public IEnumerable<string> GetInputCols() => (string[])_jvmObject.Invoke("getInputCols");
 
         /// <summary>
         /// Sets the column that the <see cref="FeatureHasher"/> should read from and convert into
@@ -95,7 +95,7 @@ public FeatureHasher SetNumFeatures(int value) =>
         
         /// <summary>
         /// Gets the name of the column the output data will be written to. This is set by
-        /// SetInputCol
+        /// SetInputCol.
         /// </summary>
         /// <returns>string, the output column</returns>
         public string GetOutputCol() => (string)_jvmObject.Invoke("getOutputCol");
@@ -120,19 +120,18 @@ public DataFrame Transform(DataFrame value) =>
         
         /// <summary>
         /// Check transform validity and derive the output schema from the input schema.
-        /// We check validity for interactions between parameters during transformSchema and
-        /// raise an exception if any parameter value is invalid. Parameter value checks which do
-        /// not depend on other parameters are handled by Param.validate().    
+        /// This checks for validity of interactions between parameters during transformSchema and
+        /// raises an exception if any parameter value is invalid.   
         ///
         /// Typical implementation should first conduct verification on schema change and parameter
         /// validity, including complex parameter interaction checks.
         /// </summary>
         /// <param name="value">
-        /// The <see cref="StructType"/> of the <see cref="DataFrame"/> which will be transformed
+        /// The <see cref="StructType"/> of the <see cref="DataFrame"/> which will be transformed.
         /// </param>
         /// <returns>
-        /// The <see cref="StructType"/> of the output schema that would have been derived form the
-        /// input schema, if Transform had been called
+        /// The <see cref="StructType"/> of the output schema that would have been derived from the
+        /// input schema, if Transform had been called.
         /// </returns>
         public StructType TransformSchema(StructType value) => 
             new StructType(

From ac262058bf34f8f0b4b9eebebc3f5dc4eb389139 Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Fri, 4 Sep 2020 08:45:53 +0100
Subject: [PATCH 03/17] tidying comments

---
 .../Microsoft.Spark/ML/Feature/FeatureHasher.cs     | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
index 2e31ba6b6..bfcec18d0 100644
--- a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
+++ b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
@@ -45,14 +45,14 @@ public static FeatureHasher Load(string path) =>
         /// <summary>
         /// Gets a list of the columns which have been specified as categorical columns.
         /// </summary>
-        /// <returns>List of categorical columns, set by `SetCategoricalCols`</returns>
+        /// <returns>List of categorical columns, set by SetCategoricalCols</returns>
         public IEnumerable<string> GetCategoricalCols() => 
             ((string[])_jvmObject.Invoke("getCategoricalCols")).ToList();
         
         /// <summary>
         /// Marks columns as categorical columns.
         /// </summary>
-        /// <param name="value">List of column names to mark as a categorical column</param>
+        /// <param name="value">List of column names to mark as categorical columns</param>
         /// <returns>New <see cref="FeatureHasher"/> object</returns>
         public FeatureHasher SetCategoricalCols(IEnumerable<string> value) => 
             WrapAsFeatureHasher(_jvmObject.Invoke("setCategoricalCols", value));
@@ -68,7 +68,7 @@ public FeatureHasher SetCategoricalCols(IEnumerable<string> value) =>
         /// Sets the column that the <see cref="FeatureHasher"/> should read from and convert into
         /// hashes.
         /// </summary>
-        /// <param name="value">The name of the column to as the source of the buckets</param>
+        /// <param name="value">The name of the column to as use the source of the hash</param>
         /// <returns>New <see cref="FeatureHasher"/> object</returns>
         public FeatureHasher SetInputCols(IEnumerable<string> value) => 
             WrapAsFeatureHasher(_jvmObject.Invoke("setInputCols", value));
@@ -104,14 +104,14 @@ public FeatureHasher SetNumFeatures(int value) =>
         /// The <see cref="FeatureHasher"/> will create a new column in the DataFrame, this is the
         /// name of the new column.
         /// </summary>
-        /// <param name="value">The name of the new column which contains the hash</param>
+        /// <param name="value">The name of the new column which will contain the hash</param>
         /// <returns>New <see cref="FeatureHasher"/> object</returns>
         public FeatureHasher SetOutputCol(string value) => 
             WrapAsFeatureHasher(_jvmObject.Invoke("setOutputCol", value));
         
         /// <summary>
         /// Transforms the input <see cref="DataFrame"/>. It is recommended that you validate that
-        /// the transform will succeed by calling `TransformSchema`.
+        /// the transform will succeed by calling TransformSchema.
         /// </summary>
         /// <param name="value">Input <see cref="DataFrame"/> to transform</param>
         /// <returns>Transformed <see cref="DataFrame"/></returns>
@@ -120,7 +120,8 @@ public DataFrame Transform(DataFrame value) =>
         
         /// <summary>
         /// Check transform validity and derive the output schema from the input schema.
-        /// This checks for validity of interactions between parameters during transformSchema and
+        /// 
+        /// This checks for validity of interactions between parameters during Transform and
         /// raises an exception if any parameter value is invalid.   
         ///
         /// Typical implementation should first conduct verification on schema change and parameter

From d6094e31c49349ebe2f33c3ea57c69d089ed73a0 Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Tue, 8 Sep 2020 17:22:12 +0100
Subject: [PATCH 04/17] adding extra test for FeatureBase

---
 .../IpcTests/ML/Feature/BucketizerTests.cs    | 15 ++--------
 .../ML/Feature/CountVectorizerModelTests.cs   |  4 ++-
 .../ML/Feature/CountVectorizerTests.cs        |  2 ++
 .../IpcTests/ML/Feature/FeatureBaseTests.cs   | 29 +++++++++++++++++++
 .../IpcTests/ML/Feature/FeatureHasherTests.cs |  2 ++
 .../IpcTests/ML/Feature/HashingTFTests.cs     |  2 ++
 .../IpcTests/ML/Feature/IDFModelTests.cs      |  2 ++
 .../IpcTests/ML/Feature/IDFTests.cs           |  2 ++
 .../IpcTests/ML/Feature/TokenizerTests.cs     |  2 ++
 .../IpcTests/ML/Feature/Word2VecModelTests.cs |  2 ++
 .../IpcTests/ML/Feature/Word2VecTests.cs      |  2 ++
 11 files changed, 50 insertions(+), 14 deletions(-)
 create mode 100644 src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
index e9193fd0b..b2d75355a 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
@@ -25,7 +25,7 @@ public BucketizerTests(SparkFixture fixture)
         [Fact]
         public void TestBucketizer()
         {
-            var expectedSplits = new double[] { double.MinValue, 0.0, 10.0, 50.0, double.MaxValue };
+            var expectedSplits = new double[]{ double.MinValue, 0.0, 10.0, 50.0, double.MaxValue };
 
             string expectedHandle = "skip";
             string expectedUid = "uid";
@@ -60,18 +60,7 @@ public void TestBucketizer()
                 Assert.Equal(bucketizer.Uid(), loadedBucketizer.Uid());
             }
             
-            Assert.NotEmpty(bucketizer.ExplainParams());
-            
-            Param handleInvalidParam = bucketizer.GetParam("handleInvalid");
-            Assert.NotEmpty(handleInvalidParam.Doc);
-            Assert.NotEmpty(handleInvalidParam.Name);
-            Assert.Equal(handleInvalidParam.Parent, bucketizer.Uid());
-
-            Assert.NotEmpty(bucketizer.ExplainParam(handleInvalidParam));
-            bucketizer.Set(handleInvalidParam, "keep");
-            Assert.Equal("keep", bucketizer.GetHandleInvalid());
-             
-            Assert.Equal("error", bucketizer.Clear(handleInvalidParam).GetHandleInvalid());
+            FeatureBaseTests<Bucketizer>.TestBase(bucketizer, "handleInvalid", "keep");
         }
 
         [Fact]
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerModelTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerModelTests.cs
index 97458d173..a52b13658 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerModelTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerModelTests.cs
@@ -22,7 +22,7 @@ public CountVectorizerModelTests(SparkFixture fixture)
         }
 
         /// <summary>
-        /// Test that we can create a CountVectorizerModel, pass in a specifc vocabulary to use
+        /// Test that we can create a CountVectorizerModel, pass in a specific vocabulary to use
         /// when creating the model. Verify the standard features methods as well as load/save.
         /// </summary>
         [Fact]
@@ -68,6 +68,8 @@ public void TestCountVectorizerModel()
             Assert.IsType<int>(countVectorizerModel.GetVocabSize());
             Assert.NotEmpty(countVectorizerModel.ExplainParams());
             Assert.NotEmpty(countVectorizerModel.ToString());
+            
+            FeatureBaseTests<CountVectorizerModel>.TestBase(countVectorizerModel, "minDF", 100);
         } 
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerTests.cs
index 9e022ba69..e9651280d 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerTests.cs
@@ -67,6 +67,8 @@ public void TestCountVectorizer()
             
             Assert.NotEmpty(countVectorizer.ExplainParams());
             Assert.NotEmpty(countVectorizer.ToString());
+            
+            FeatureBaseTests<CountVectorizer>.TestBase(countVectorizer, "minDF", 0.4);
         }
         
         /// <summary>
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
new file mode 100644
index 000000000..566efd0c7
--- /dev/null
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
@@ -0,0 +1,29 @@
+
+using Microsoft.Spark.ML.Feature;
+using Microsoft.Spark.ML.Feature.Param;
+using Xunit;
+
+namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
+{
+    public class FeatureBaseTests<T>
+    {
+        internal static void TestBase(
+            FeatureBase<T> testObject, 
+            string paramName, 
+            object paramValue)
+        {
+            Assert.NotEmpty(testObject.ExplainParams());
+            
+            Param handleInvalidParam = testObject.GetParam(paramName);
+            Assert.NotEmpty(handleInvalidParam.Doc);
+            Assert.NotEmpty(handleInvalidParam.Name);
+            Assert.Equal(handleInvalidParam.Parent, testObject.Uid());
+
+            Assert.NotEmpty(testObject.ExplainParam(handleInvalidParam));
+            testObject.Set(handleInvalidParam, paramValue);
+            Assert.IsAssignableFrom<Identifiable>(testObject.Clear(handleInvalidParam));
+
+            Assert.IsType<string>(testObject.Uid());
+        }
+    }
+}
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
index 24b0b22ee..8a1c397cc 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
@@ -50,6 +50,8 @@ public void TestFeatureHasher()
             Assert.IsType<int>(hasher.GetNumFeatures());
             Assert.IsType<StructType>(hasher.TransformSchema(dataFrame.Schema()));
             Assert.IsType<DataFrame>(hasher.Transform(dataFrame));
+            
+            FeatureBaseTests<FeatureHasher>.TestBase(hasher, "numFeatures", 1000);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/HashingTFTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/HashingTFTests.cs
index df459ed7a..9d3fdf4a8 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/HashingTFTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/HashingTFTests.cs
@@ -57,6 +57,8 @@ public void TestHashingTF()
 
             hashingTf.SetBinary(true);
             Assert.True(hashingTf.GetBinary());
+            
+            FeatureBaseTests<HashingTF>.TestBase(hashingTf, "numFeatures", 1000);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFModelTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFModelTests.cs
index 202187809..3467dea0c 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFModelTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFModelTests.cs
@@ -65,6 +65,8 @@ public void TestIDFModel()
                 IDFModel loadedModel = IDFModel.Load(modelPath);
                 Assert.Equal(idfModel.Uid(), loadedModel.Uid());
             }
+            
+            FeatureBaseTests<IDFModel>.TestBase(idfModel, "minDocFreq", 1000);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFTests.cs
index 72da97887..6c635fd7d 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFTests.cs
@@ -44,6 +44,8 @@ public void TestIDFModel()
                 IDF loadedIdf = IDF.Load(savePath);
                 Assert.Equal(idf.Uid(), loadedIdf.Uid());
             }
+            
+            FeatureBaseTests<IDF>.TestBase(idf, "minDocFreq", 1000);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/TokenizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/TokenizerTests.cs
index 4b1998f50..5c8ab9a8c 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/TokenizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/TokenizerTests.cs
@@ -50,6 +50,8 @@ public void TestTokenizer()
             }
             
             Assert.Equal(expectedUid, tokenizer.Uid());
+            
+            FeatureBaseTests<Tokenizer>.TestBase(tokenizer, "inputCol", "input_col");
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecModelTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecModelTests.cs
index a5227149b..a64a70512 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecModelTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecModelTests.cs
@@ -47,6 +47,8 @@ public void TestWord2VecModel()
                 Word2VecModel loadedModel = Word2VecModel.Load(savePath);
                 Assert.Equal(model.Uid(), loadedModel.Uid());
             }
+            
+            FeatureBaseTests<Word2VecModel>.TestBase(model, "maxIter", 2);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecTests.cs
index 1d5da5335..a117d3426 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecTests.cs
@@ -67,6 +67,8 @@ public void TestWord2Vec()
                 Word2Vec loadedWord2Vec = Word2Vec.Load(savePath);
                 Assert.Equal(word2vec.Uid(), loadedWord2Vec.Uid());
             }
+            
+            FeatureBaseTests<Word2Vec>.TestBase(word2vec, "maxIter", 2);
         }
     }
 }

From ffd0cfc00f0cc484269ff434000cae3d49583c80 Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Tue, 8 Sep 2020 19:47:29 +0100
Subject: [PATCH 05/17] Trigger Build


From a0356cc836b8f47976900d37042e32337a50db64 Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Tue, 8 Sep 2020 20:15:18 +0100
Subject: [PATCH 06/17] missing file header

---
 .../IpcTests/ML/Feature/FeatureBaseTests.cs                  | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
index 566efd0c7..3daae39cc 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
@@ -1,3 +1,6 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+// See the LICENSE file in the project root for more information.
 
 using Microsoft.Spark.ML.Feature;
 using Microsoft.Spark.ML.Feature.Param;
@@ -5,7 +8,7 @@
 
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
-    public class FeatureBaseTests<T>
+    public static class FeatureBaseTests<T>
     {
         internal static void TestBase(
             FeatureBase<T> testObject, 

From 7921e049d8393229ac82b12dba304aac9eaaf88a Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Tue, 8 Sep 2020 20:19:23 +0100
Subject: [PATCH 07/17] comments

---
 src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
index bfcec18d0..a312318fa 100644
--- a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
+++ b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
@@ -61,11 +61,11 @@ public FeatureHasher SetCategoricalCols(IEnumerable<string> value) =>
         /// Gets the columns that the <see cref="FeatureHasher"/> should read from and convert into
         /// hashes. This would have been set by SetInputCol.
         /// </summary>
-        /// <returns>string, the input column</returns>
+        /// <returns>IEnumerable&lt;string&gt;, the input columns</returns>
         public IEnumerable<string> GetInputCols() => (string[])_jvmObject.Invoke("getInputCols");
 
         /// <summary>
-        /// Sets the column that the <see cref="FeatureHasher"/> should read from and convert into
+        /// Sets the columns that the <see cref="FeatureHasher"/> should read from and convert into
         /// hashes.
         /// </summary>
         /// <param name="value">The name of the column to as use the source of the hash</param>

From b5fcee270221d4560b4ded8b73454d3a8f319e2c Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Tue, 8 Sep 2020 20:21:21 +0100
Subject: [PATCH 08/17] naming better

---
 .../IpcTests/ML/Feature/FeatureBaseTests.cs        | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
index 3daae39cc..413b84a98 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
@@ -17,14 +17,14 @@ internal static void TestBase(
         {
             Assert.NotEmpty(testObject.ExplainParams());
             
-            Param handleInvalidParam = testObject.GetParam(paramName);
-            Assert.NotEmpty(handleInvalidParam.Doc);
-            Assert.NotEmpty(handleInvalidParam.Name);
-            Assert.Equal(handleInvalidParam.Parent, testObject.Uid());
+            Param param = testObject.GetParam(paramName);
+            Assert.NotEmpty(param.Doc);
+            Assert.NotEmpty(param.Name);
+            Assert.Equal(param.Parent, testObject.Uid());
 
-            Assert.NotEmpty(testObject.ExplainParam(handleInvalidParam));
-            testObject.Set(handleInvalidParam, paramValue);
-            Assert.IsAssignableFrom<Identifiable>(testObject.Clear(handleInvalidParam));
+            Assert.NotEmpty(testObject.ExplainParam(param));
+            testObject.Set(param, paramValue);
+            Assert.IsAssignableFrom<Identifiable>(testObject.Clear(param));
 
             Assert.IsType<string>(testObject.Uid());
         }

From 01d40f8299806e6a891c2eeb346c58c8548b3e8d Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Tue, 8 Sep 2020 22:08:54 +0100
Subject: [PATCH 09/17] indentation

---
 .../IpcTests/ML/Feature/BucketizerTests.cs                     | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
index b2d75355a..d915742e8 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
@@ -25,7 +25,8 @@ public BucketizerTests(SparkFixture fixture)
         [Fact]
         public void TestBucketizer()
         {
-            var expectedSplits = new double[]{ double.MinValue, 0.0, 10.0, 50.0, double.MaxValue };
+            var expectedSplits =
+                new double[] { double.MinValue, 0.0, 10.0, 50.0, double.MaxValue };
 
             string expectedHandle = "skip";
             string expectedUid = "uid";

From 89694dcf9616bebe900e3984a18da193deb252cd Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Wed, 9 Sep 2020 06:59:12 +0100
Subject: [PATCH 10/17] changes after feedback

---
 .../IpcTests/ML/Feature/BucketizerTests.cs               | 8 ++++----
 .../IpcTests/ML/Feature/FeatureBaseTests.cs              | 6 ++++++
 .../IpcTests/ML/Feature/FeatureHasherTests.cs            | 6 +++++-
 src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs   | 9 ++++-----
 4 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
index d915742e8..30d7f1824 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
@@ -28,10 +28,10 @@ public void TestBucketizer()
             var expectedSplits =
                 new double[] { double.MinValue, 0.0, 10.0, 50.0, double.MaxValue };
 
-            string expectedHandle = "skip";
-            string expectedUid = "uid";
-            string expectedInputCol = "input_col";
-            string expectedOutputCol = "output_col";
+            const string expectedHandle = "skip";
+            const string expectedUid = "uid";
+            const string expectedInputCol = "input_col";
+            const string expectedOutputCol = "output_col";
 
             var bucketizer = new Bucketizer(expectedUid);
             bucketizer.SetInputCol(expectedInputCol)
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
index 413b84a98..cc1732c18 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
@@ -10,6 +10,12 @@ namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     public static class FeatureBaseTests<T>
     {
+        /// <summary>
+        /// Tests the common functionality across all ML.Feature classes.
+        /// </summary>
+        /// <param name="testObject">The object that implemented FeatureBase</param>
+        /// <param name="paramName">The name of a parameter that can be set on this object</param>
+        /// <param name="paramValue">A parameter value that can be set on this object</param>
         internal static void TestBase(
             FeatureBase<T> testObject, 
             string paramName, 
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
index 8a1c397cc..39cfe4f14 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
@@ -20,7 +20,11 @@ public FeatureHasherTests(SparkFixture fixture)
         {
             _spark = fixture.Spark;
         }
-
+        
+        /// <summary>
+        /// Create a <see cref="DataFrame"/>, create a <see cref="FeatureHasher"/> and test the
+        /// available methods. Test the FeatureBase methods using <see cref="FeatureBaseTests"/>.
+        /// </summary>
         [Fact]
         public void TestFeatureHasher()
         {
diff --git a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
index a312318fa..f36dc0854 100644
--- a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
+++ b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
@@ -61,7 +61,7 @@ public FeatureHasher SetCategoricalCols(IEnumerable<string> value) =>
         /// Gets the columns that the <see cref="FeatureHasher"/> should read from and convert into
         /// hashes. This would have been set by SetInputCol.
         /// </summary>
-        /// <returns>IEnumerable&lt;string&gt;, the input columns</returns>
+        /// <returns>List of the input columns, set by SetInputCols</returns>
         public IEnumerable<string> GetInputCols() => (string[])_jvmObject.Invoke("getInputCols");
 
         /// <summary>
@@ -88,7 +88,7 @@ public FeatureHasher SetInputCols(IEnumerable<string> value) =>
         /// the numFeatures parameter; otherwise the features will not be mapped evenly to the
         /// columns.
         /// </summary>
-        /// <param name="value">int</param>
+        /// <param name="value">int value of number of features</param>
         /// <returns>New <see cref="FeatureHasher"/> object</returns>
         public FeatureHasher SetNumFeatures(int value) => 
             WrapAsFeatureHasher(_jvmObject.Invoke("setNumFeatures", value));
@@ -101,8 +101,7 @@ public FeatureHasher SetNumFeatures(int value) =>
         public string GetOutputCol() => (string)_jvmObject.Invoke("getOutputCol");
 
         /// <summary>
-        /// The <see cref="FeatureHasher"/> will create a new column in the DataFrame, this is the
-        /// name of the new column.
+        /// Sets the name of the new column in the <see cref="DataFrame"/> created by Transform.
         /// </summary>
         /// <param name="value">The name of the new column which will contain the hash</param>
         /// <returns>New <see cref="FeatureHasher"/> object</returns>
@@ -122,7 +121,7 @@ public DataFrame Transform(DataFrame value) =>
         /// Check transform validity and derive the output schema from the input schema.
         /// 
         /// This checks for validity of interactions between parameters during Transform and
-        /// raises an exception if any parameter value is invalid.   
+        /// raises an exception if any parameter value is invalid.
         ///
         /// Typical implementation should first conduct verification on schema change and parameter
         /// validity, including complex parameter interaction checks.

From 2d8eaa1bbab8fb3753f1408e76097054c88cd3f5 Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Wed, 9 Sep 2020 07:00:51 +0100
Subject: [PATCH 11/17] test summary

---
 .../IpcTests/ML/Feature/BucketizerTests.cs                    | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
index 30d7f1824..bb7ae410a 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
@@ -22,6 +22,10 @@ public BucketizerTests(SparkFixture fixture)
             _spark = fixture.Spark;
         }
 
+        /// <summary>
+        /// Create a <see cref="DataFrame"/>, create a <see cref="Bucketizer"/> and test the
+        /// available methods. Test the FeatureBase methods using <see cref="FeatureBaseTests"/>.
+        /// </summary>
         [Fact]
         public void TestBucketizer()
         {

From bad829a95743bd42a3be00d42972919efa59761f Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Wed, 9 Sep 2020 07:50:16 +0100
Subject: [PATCH 12/17] trigger build


From 02f06a94b718c03af209156fa0bc8271950e878d Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Tue, 29 Sep 2020 20:47:41 +0100
Subject: [PATCH 13/17] changes after review

---
 .../IpcTests/ML/Feature/BucketizerTests.cs           |  6 +++---
 .../IpcTests/ML/Feature/CountVectorizerModelTests.cs |  6 +++---
 .../IpcTests/ML/Feature/CountVectorizerTests.cs      |  6 +++---
 .../IpcTests/ML/Feature/FeatureBaseTests.cs          | 12 ++++++++++--
 .../IpcTests/ML/Feature/FeatureHasherTests.cs        | 12 ++++++------
 .../IpcTests/ML/Feature/HashingTFTests.cs            |  6 +++---
 .../IpcTests/ML/Feature/IDFModelTests.cs             |  6 +++---
 .../IpcTests/ML/Feature/IDFTests.cs                  |  6 +++---
 .../IpcTests/ML/Feature/TokenizerTests.cs            |  6 +++---
 .../IpcTests/ML/Feature/Word2VecModelTests.cs        |  6 +++---
 .../IpcTests/ML/Feature/Word2VecTests.cs             |  6 +++---
 .../Microsoft.Spark/ML/Feature/FeatureHasher.cs      |  9 ++++++---
 12 files changed, 49 insertions(+), 38 deletions(-)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
index bb7ae410a..6f281c1ca 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
@@ -13,11 +13,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class BucketizerTests
+    public class BucketizerTests : FeatureBaseTests<Bucketizer>
     {
         private readonly SparkSession _spark;
 
-        public BucketizerTests(SparkFixture fixture)
+        public BucketizerTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -65,7 +65,7 @@ public void TestBucketizer()
                 Assert.Equal(bucketizer.Uid(), loadedBucketizer.Uid());
             }
             
-            FeatureBaseTests<Bucketizer>.TestBase(bucketizer, "handleInvalid", "keep");
+            TestFeatureBase(bucketizer, "handleInvalid", "keep");
         }
 
         [Fact]
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerModelTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerModelTests.cs
index a52b13658..e8ea1ade4 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerModelTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerModelTests.cs
@@ -12,11 +12,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class CountVectorizerModelTests
+    public class CountVectorizerModelTests : FeatureBaseTests<CountVectorizerModel>
     {
         private readonly SparkSession _spark;
 
-        public CountVectorizerModelTests(SparkFixture fixture)
+        public CountVectorizerModelTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -69,7 +69,7 @@ public void TestCountVectorizerModel()
             Assert.NotEmpty(countVectorizerModel.ExplainParams());
             Assert.NotEmpty(countVectorizerModel.ToString());
             
-            FeatureBaseTests<CountVectorizerModel>.TestBase(countVectorizerModel, "minDF", 100);
+            TestFeatureBase(countVectorizerModel, "minDF", 100);
         } 
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerTests.cs
index e9651280d..5d046dc87 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/CountVectorizerTests.cs
@@ -13,11 +13,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class CountVectorizerTests
+    public class CountVectorizerTests : FeatureBaseTests<CountVectorizer>
     {
         private readonly SparkSession _spark;
 
-        public CountVectorizerTests(SparkFixture fixture)
+        public CountVectorizerTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -68,7 +68,7 @@ public void TestCountVectorizer()
             Assert.NotEmpty(countVectorizer.ExplainParams());
             Assert.NotEmpty(countVectorizer.ToString());
             
-            FeatureBaseTests<CountVectorizer>.TestBase(countVectorizer, "minDF", 0.4);
+            TestFeatureBase(countVectorizer, "minDF", 0.4);
         }
         
         /// <summary>
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
index cc1732c18..01903e510 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureBaseTests.cs
@@ -4,19 +4,27 @@
 
 using Microsoft.Spark.ML.Feature;
 using Microsoft.Spark.ML.Feature.Param;
+using Microsoft.Spark.Sql;
 using Xunit;
 
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
-    public static class FeatureBaseTests<T>
+    public class FeatureBaseTests<T>
     {
+        private readonly SparkSession _spark;
+
+        protected FeatureBaseTests(SparkFixture fixture)
+        {
+            _spark = fixture.Spark;
+        }
+        
         /// <summary>
         /// Tests the common functionality across all ML.Feature classes.
         /// </summary>
         /// <param name="testObject">The object that implemented FeatureBase</param>
         /// <param name="paramName">The name of a parameter that can be set on this object</param>
         /// <param name="paramValue">A parameter value that can be set on this object</param>
-        internal static void TestBase(
+        public void TestFeatureBase(
             FeatureBase<T> testObject, 
             string paramName, 
             object paramValue)
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
index 39cfe4f14..2faac108d 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
@@ -12,11 +12,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class FeatureHasherTests
+    public class FeatureHasherTests : FeatureBaseTests<FeatureHasher>
     {
         private readonly SparkSession _spark;
         
-        public FeatureHasherTests(SparkFixture fixture)
+        public FeatureHasherTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -43,19 +43,19 @@ public void TestFeatureHasher()
                 }));
 
             FeatureHasher hasher = new FeatureHasher()
-                .SetInputCols(new List<string>() {"real", "bool", "stringNum", "string"})
+                .SetInputCols(new List<string>() { "real", "bool", "stringNum", "string" })
                 .SetOutputCol("features")
                 .SetCategoricalCols(new List<string>() {"real", "string"})
                 .SetNumFeatures(10);
 
             Assert.IsType<string>(hasher.GetOutputCol());
-            Assert.IsType <string[]>(hasher.GetInputCols());
-            Assert.IsType<List<string>>(hasher.GetCategoricalCols());
+            Assert.IsType<string[]>(hasher.GetInputCols());
+            Assert.IsType<string[]>(hasher.GetCategoricalCols());
             Assert.IsType<int>(hasher.GetNumFeatures());
             Assert.IsType<StructType>(hasher.TransformSchema(dataFrame.Schema()));
             Assert.IsType<DataFrame>(hasher.Transform(dataFrame));
             
-            FeatureBaseTests<FeatureHasher>.TestBase(hasher, "numFeatures", 1000);
+            TestFeatureBase(hasher, "numFeatures", 1000);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/HashingTFTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/HashingTFTests.cs
index 9d3fdf4a8..246b4516e 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/HashingTFTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/HashingTFTests.cs
@@ -11,11 +11,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class HashingTFTests
+    public class HashingTFTests : FeatureBaseTests<HashingTF>
     {
         private readonly SparkSession _spark;
 
-        public HashingTFTests(SparkFixture fixture)
+        public HashingTFTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -58,7 +58,7 @@ public void TestHashingTF()
             hashingTf.SetBinary(true);
             Assert.True(hashingTf.GetBinary());
             
-            FeatureBaseTests<HashingTF>.TestBase(hashingTf, "numFeatures", 1000);
+            TestFeatureBase(hashingTf, "numFeatures", 1000);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFModelTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFModelTests.cs
index 3467dea0c..1894373a6 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFModelTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFModelTests.cs
@@ -11,11 +11,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class IDFModelTests
+    public class IDFModelTests : FeatureBaseTests<IDFModel>
     {
         private readonly SparkSession _spark;
 
-        public IDFModelTests(SparkFixture fixture)
+        public IDFModelTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -66,7 +66,7 @@ public void TestIDFModel()
                 Assert.Equal(idfModel.Uid(), loadedModel.Uid());
             }
             
-            FeatureBaseTests<IDFModel>.TestBase(idfModel, "minDocFreq", 1000);
+            TestFeatureBase(idfModel, "minDocFreq", 1000);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFTests.cs
index 6c635fd7d..64698ac9a 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/IDFTests.cs
@@ -11,11 +11,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class IDFTests
+    public class IDFTests : FeatureBaseTests<IDF>
     {
         private readonly SparkSession _spark;
 
-        public IDFTests(SparkFixture fixture)
+        public IDFTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -45,7 +45,7 @@ public void TestIDFModel()
                 Assert.Equal(idf.Uid(), loadedIdf.Uid());
             }
             
-            FeatureBaseTests<IDF>.TestBase(idf, "minDocFreq", 1000);
+            TestFeatureBase(idf, "minDocFreq", 1000);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/TokenizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/TokenizerTests.cs
index 5c8ab9a8c..af76ac523 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/TokenizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/TokenizerTests.cs
@@ -11,11 +11,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class TokenizerTests
+    public class TokenizerTests : FeatureBaseTests<Tokenizer>
     {
         private readonly SparkSession _spark;
 
-        public TokenizerTests(SparkFixture fixture)
+        public TokenizerTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -51,7 +51,7 @@ public void TestTokenizer()
             
             Assert.Equal(expectedUid, tokenizer.Uid());
             
-            FeatureBaseTests<Tokenizer>.TestBase(tokenizer, "inputCol", "input_col");
+            TestFeatureBase(tokenizer, "inputCol", "input_col");
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecModelTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecModelTests.cs
index a64a70512..04c7d7a79 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecModelTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecModelTests.cs
@@ -11,11 +11,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class Word2VecModelTests
+    public class Word2VecModelTests : FeatureBaseTests<Word2VecModel>
     {
         private readonly SparkSession _spark;
 
-        public Word2VecModelTests(SparkFixture fixture)
+        public Word2VecModelTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -48,7 +48,7 @@ public void TestWord2VecModel()
                 Assert.Equal(model.Uid(), loadedModel.Uid());
             }
             
-            FeatureBaseTests<Word2VecModel>.TestBase(model, "maxIter", 2);
+            TestFeatureBase(model, "maxIter", 2);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecTests.cs
index a117d3426..1c36eb2c2 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/Word2VecTests.cs
@@ -11,11 +11,11 @@
 namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
 {
     [Collection("Spark E2E Tests")]
-    public class Word2VecTests
+    public class Word2VecTests : FeatureBaseTests<Word2Vec>
     {
         private readonly SparkSession _spark;
 
-        public Word2VecTests(SparkFixture fixture)
+        public Word2VecTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
@@ -68,7 +68,7 @@ public void TestWord2Vec()
                 Assert.Equal(word2vec.Uid(), loadedWord2Vec.Uid());
             }
             
-            FeatureBaseTests<Word2Vec>.TestBase(word2vec, "maxIter", 2);
+            TestFeatureBase(word2vec, "maxIter", 2);
         }
     }
 }
diff --git a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
index f36dc0854..fb89b1051 100644
--- a/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
+++ b/src/csharp/Microsoft.Spark/ML/Feature/FeatureHasher.cs
@@ -40,14 +40,16 @@ internal FeatureHasher(JvmObjectReference jvmObject) : base(jvmObject)
         public static FeatureHasher Load(string path) =>
             WrapAsFeatureHasher(
                 SparkEnvironment.JvmBridge.CallStaticJavaMethod(
-                    s_featureHasherClassName,"load", path));
+                    s_featureHasherClassName,
+                    "load",
+                    path));
         
         /// <summary>
         /// Gets a list of the columns which have been specified as categorical columns.
         /// </summary>
         /// <returns>List of categorical columns, set by SetCategoricalCols</returns>
         public IEnumerable<string> GetCategoricalCols() => 
-            ((string[])_jvmObject.Invoke("getCategoricalCols")).ToList();
+            (string[])_jvmObject.Invoke("getCategoricalCols");
         
         /// <summary>
         /// Marks columns as categorical columns.
@@ -135,7 +137,8 @@ public DataFrame Transform(DataFrame value) =>
         /// </returns>
         public StructType TransformSchema(StructType value) => 
             new StructType(
-                (JvmObjectReference)_jvmObject.Invoke("transformSchema", 
+                (JvmObjectReference)_jvmObject.Invoke(
+                    "transformSchema", 
                     DataType.FromJson(_jvmObject.Jvm, value.Json)));
 
         private static FeatureHasher WrapAsFeatureHasher(object obj) => 

From ecb9e5f66424d313b23a7ff79141b656c875d1fa Mon Sep 17 00:00:00 2001
From: Ed Elliott <GOEDDIEUK@GMail.com>
Date: Tue, 29 Sep 2020 20:23:35 +0000
Subject: [PATCH 14/17] formatting

---
 .../IpcTests/ML/Feature/FeatureHasherTests.cs             | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
index 2faac108d..50fecd630 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
@@ -15,12 +15,12 @@ namespace Microsoft.Spark.E2ETest.IpcTests.ML.Feature
     public class FeatureHasherTests : FeatureBaseTests<FeatureHasher>
     {
         private readonly SparkSession _spark;
-        
+
         public FeatureHasherTests(SparkFixture fixture) : base(fixture)
         {
             _spark = fixture.Spark;
         }
-        
+
         /// <summary>
         /// Create a <see cref="DataFrame"/>, create a <see cref="FeatureHasher"/> and test the
         /// available methods. Test the FeatureBase methods using <see cref="FeatureBaseTests"/>.
@@ -45,7 +45,7 @@ public void TestFeatureHasher()
             FeatureHasher hasher = new FeatureHasher()
                 .SetInputCols(new List<string>() { "real", "bool", "stringNum", "string" })
                 .SetOutputCol("features")
-                .SetCategoricalCols(new List<string>() {"real", "string"})
+                .SetCategoricalCols(new List<string>() { "real", "string" })
                 .SetNumFeatures(10);
 
             Assert.IsType<string>(hasher.GetOutputCol());
@@ -54,7 +54,7 @@ public void TestFeatureHasher()
             Assert.IsType<int>(hasher.GetNumFeatures());
             Assert.IsType<StructType>(hasher.TransformSchema(dataFrame.Schema()));
             Assert.IsType<DataFrame>(hasher.Transform(dataFrame));
-            
+
             TestFeatureBase(hasher, "numFeatures", 1000);
         }
     }

From b28c1a732f846281758bb44d3a04942d9c99f74e Mon Sep 17 00:00:00 2001
From: Ed Elliott <GOEDDIEUK@GMail.com>
Date: Tue, 29 Sep 2020 20:26:36 +0000
Subject: [PATCH 15/17] formatting

---
 .../IpcTests/ML/Feature/FeatureHasherTests.cs                 | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
index 50fecd630..fe169a9f0 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/FeatureHasherTests.cs
@@ -31,8 +31,8 @@ public void TestFeatureHasher()
             DataFrame dataFrame = _spark.CreateDataFrame(
                 new List<GenericRow>
                 {
-                    new GenericRow(new object[] {2.0D, true, "1", "foo"}),
-                    new GenericRow(new object[] {3.0D, false, "2", "bar"})
+                    new GenericRow(new object[] { 2.0D, true, "1", "foo" }),
+                    new GenericRow(new object[] { 3.0D, false, "2", "bar" })
                 },
                 new StructType(new List<StructField>
                 {

From e94a601ed74cc56f6799e714a1840f9fec5f22a4 Mon Sep 17 00:00:00 2001
From: Ed Elliott <GOEDDIEUK@GMail.com>
Date: Tue, 29 Sep 2020 20:30:54 +0000
Subject: [PATCH 16/17] Reverting change

---
 .../IpcTests/ML/Feature/BucketizerTests.cs                | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
index 6f281c1ca..949ba06da 100644
--- a/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
+++ b/src/csharp/Microsoft.Spark.E2ETest/IpcTests/ML/Feature/BucketizerTests.cs
@@ -32,10 +32,10 @@ public void TestBucketizer()
             var expectedSplits =
                 new double[] { double.MinValue, 0.0, 10.0, 50.0, double.MaxValue };
 
-            const string expectedHandle = "skip";
-            const string expectedUid = "uid";
-            const string expectedInputCol = "input_col";
-            const string expectedOutputCol = "output_col";
+            string expectedHandle = "skip";
+            string expectedUid = "uid";
+            string expectedInputCol = "input_col";
+            string expectedOutputCol = "output_col";
 
             var bucketizer = new Bucketizer(expectedUid);
             bucketizer.SetInputCol(expectedInputCol)

From 54d55dec7105025505bbf1ae397d7b1d79cc8057 Mon Sep 17 00:00:00 2001
From: GOEddieUK <goeddie@gmail.com>
Date: Fri, 2 Oct 2020 08:59:53 +0100
Subject: [PATCH 17/17] retrigger build