Addressing PR Comments.

test/Microsoft.ML.Functional.Tests/DataTransformation.cs

@@ -21,10 +21,10 @@ public DataTransformation(ITestOutputHelper output) : base(output)
         }
 
         /// <summary>
-        /// Extensibility: Add a new column.
+        /// Extensibility: Add a new column that is a function of other columns.
         /// </summary>
         [Fact]
-        void ExtensibilityAddingOneColumn()
+        void ExtensibilityAddAColumnAsAFunctionOfMultipleColumns()
         {
             // Concurrency must be 1 to assure that the mapping is done sequentially.
             var mlContext = new MLContext(seed: 1, conc: 1);
@@ -39,11 +39,19 @@ void ExtensibilityAddingOneColumn()
             int numSamples = 10;
             data = mlContext.Data.TakeRows(data, numSamples);
 
+            // Create a stand-alone function to produce a random number.
+            float angiospermCosine(float petalWidth, float petalLength, float sepalWidth, float sepalLength)
+            {
+                var petalMagnitude = Math.Sqrt(petalWidth * petalWidth + petalLength * petalLength);
+                var sepalMagnitude = Math.Sqrt(sepalWidth * sepalWidth + sepalLength * sepalLength);
+                return (float)((petalWidth * sepalWidth + petalLength * sepalLength) / (petalMagnitude * sepalMagnitude));
+            }
+
             // Create a function that generates a column.
             Action<Iris, IrisWithOneExtraColumn> generateGroupId = (input, output) =>
             {
                 output.Label = input.Label;
-                output.Float1 = GetRandomNumber(input.Label + input.PetalLength + input.PetalWidth + input.SepalLength + input.SepalWidth);
+                output.Float1 = angiospermCosine(input.PetalLength, input.PetalWidth, input.SepalLength, input.SepalWidth);
                 output.PetalLength = input.PetalLength;
                 output.PetalWidth = input.PetalWidth;
                 output.SepalLength = input.SepalLength;
@@ -60,8 +68,8 @@ void ExtensibilityAddingOneColumn()
             var transformedRows = mlContext.Data.CreateEnumerable<IrisWithOneExtraColumn>(transformedData, reuseRowObject: true);
             foreach (var row in transformedRows)
             {
-                var randomNumber = GetRandomNumber(row.Label + row.PetalLength + row.PetalWidth + row.SepalLength + row.SepalWidth);
-                Assert.Equal(randomNumber, row.Float1);
+                var cosineDistance = angiospermCosine(row.PetalLength, row.PetalWidth, row.SepalLength, row.SepalWidth);
+                Assert.Equal(cosineDistance, row.Float1);
             }
         }
 
@@ -113,59 +121,6 @@ void ExtensibilityAddingTwoColumns()
             }
         }
 
-        /// <summary>
-        /// Extensibility: Add a new column that is a function of other columns.
-        /// </summary>
-        [Fact]
-        void ExtensibilityAddAColumnAsAFunctionOfMultipleColumns()
-        {
-            // Concurrency must be 1 to assure that the mapping is done sequentially.
-            var mlContext = new MLContext(seed: 1, conc: 1);
-
-            // Load the Iris dataset
-            var data = mlContext.Data.LoadFromTextFile<Iris>(
-                GetDataPath(TestDatasets.iris.trainFilename),
-                hasHeader: TestDatasets.iris.fileHasHeader,
-                separatorChar: TestDatasets.iris.fileSeparator);
-
-            // Subsample it down to the first 10 rows.
-            int numSamples = 10;
-            data = mlContext.Data.TakeRows(data, numSamples);
-
-            // Create a stand-alone function to produce a random number.
-            float angiospermCosine(float petalWidth, float petalLength, float sepalWidth, float sepalLength)
-            {
-                var petalMagnitude = Math.Sqrt(petalWidth * petalWidth + petalLength * petalLength);
-                var sepalMagnitude = Math.Sqrt(sepalWidth * sepalWidth + sepalLength * sepalLength);
-                return (float)((petalWidth * sepalWidth + petalLength * sepalLength) / (petalMagnitude * sepalMagnitude));
-            }
-
-            // Create a function that generates a column.
-            Action<Iris, IrisWithOneExtraColumn> generateGroupId = (input, output) =>
-            {
-                output.Label = input.Label;
-                output.Float1 = angiospermCosine(input.PetalLength, input.PetalWidth, input.SepalLength, input.SepalWidth);
-                output.PetalLength = input.PetalLength;
-                output.PetalWidth = input.PetalWidth;
-                output.SepalLength = input.SepalLength;
-                output.SepalWidth = input.SepalWidth;
-            };
-
-            // Create a pipeline to execute the custom function.
-            var pipeline = mlContext.Transforms.CustomMapping(generateGroupId, null);
-
-            // Transform the data.
-            var transformedData = pipeline.Fit(data).Transform(data);
-
-            // Verify that the column has the correct data.
-            var transformedRows = mlContext.Data.CreateEnumerable<IrisWithOneExtraColumn>(transformedData, reuseRowObject: true);
-            foreach (var row in transformedRows)
-            {
-                var cosineDistance = angiospermCosine(row.PetalLength, row.PetalWidth, row.SepalLength, row.SepalWidth);
-                Assert.Equal(cosineDistance, row.Float1);
-            }
-        }
-
         /// <summary>
         /// Extensibility: Featurize text using custom word-grams, char-grams, and normalization.
         /// </summary>
@@ -204,7 +159,7 @@ void ExtensibilityModifyTextFeaturization()
         }
 
         /// <summary>
-        /// Extensibility: Featurize text using custom word-grams, char-grams, and normalization.
+        /// Extensibility: Apply a normalizer to columns in the dataset.
         /// </summary>
         [Fact]
         void ExtensibilityNormalizeColumns()