Add V1 Introspective Training Tests (#2859)

* Adding introspective training scenario tests.

Author: rogancarr

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

@@ -267,5 +267,35 @@ public static void AssertMetricsStatistics(RegressionMetricsStatistics metrics)
             AssertMetricStatistics(metrics.RSquared);
             AssertMetricStatistics(metrics.LossFunction);
         }
+
+        /// <summary>
+        /// Verify that a float array has no NaNs or infinities.
+        /// </summary>
+        /// <param name="array">An array of doubles.</param>
+        public static void AssertFiniteNumbers(IList<float> array, int ignoreElementAt = -1)
+        {
+            for (int i = 0; i < array.Count; i++)
+            {
+                if (i == ignoreElementAt)
+                    continue;
+                Assert.False(float.IsNaN(array[i]));
+                Assert.False(float.IsInfinity(array[i]));
+            }
+        }
+
+        /// <summary>
+        /// Verify that a double array has no NaNs or infinities.
+        /// </summary>
+        /// <param name="array">An array of doubles.</param>
+        public static void AssertFiniteNumbers(IList<double> array, int ignoreElementAt = -1)
+        {
+            for (int i = 0; i < array.Count; i++)
+            {
+                if (i == ignoreElementAt)
+                    continue;
+                Assert.False(double.IsNaN(array[i]));
+                Assert.False(double.IsInfinity(array[i]));
+            }
+        }
     }
 }

test/Microsoft.ML.Functional.Tests/Datasets/Adult.cs

@@ -0,0 +1,69 @@
+// 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.ML.Data;
+
+namespace Microsoft.ML.Functional.Tests.Datasets
+{
+    /// <summary>
+    /// A class for the Adult test dataset.
+    /// </summary>
+    internal sealed class Adult
+    {
+        [LoadColumn(0)]
+        public bool Label { get; set; }
+
+        [LoadColumn(1)]
+        public string WorkClass { get; set; }
+
+        [LoadColumn(2)]
+        public string Education { get; set; }
+
+        [LoadColumn(3)]
+        public string MaritalStatus { get; set; }
+
+        [LoadColumn(4)]
+        public string Occupation { get; set; }
+
+        [LoadColumn(5)]
+        public string Relationship { get; set; }
+
+        [LoadColumn(6)]
+        public string Ethnicity { get; set; }
+
+        [LoadColumn(7)]
+        public string Sex { get; set; }
+
+        [LoadColumn(8)]
+        public string NativeCountryRegion { get; set; }
+
+        [LoadColumn(9)]
+        public float Age { get; set; }
+
+        [LoadColumn(10)]
+        public float FinalWeight { get; set; }
+
+        [LoadColumn(11)]
+        public float EducationNum { get; set; }
+
+        [LoadColumn(12)]
+        public float CapitalGain { get; set; }
+
+        [LoadColumn(13)]
+        public float CapitalLoss { get; set; }
+
+        [LoadColumn(14)]
+        public float HoursPerWeek { get; set; }
+
+        /// <summary>
+        /// The list of columns commonly used as categorical features.
+        /// </summary>
+        public static readonly string[] CategoricalFeatures = new string[] { "WorkClass", "Education", "MaritalStatus", "Occupation", "Relationship", "Ethnicity", "Sex", "NativeCountryRegion" };
+
+        /// <summary>
+        /// The list of columns commonly used as numerical features.
+        /// </summary>
+        public static readonly string[] NumericalFeatures = new string[] { "Age", "FinalWeight", "EducationNum", "CapitalGain", "CapitalLoss", "HoursPerWeek" };
+    }
+}

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

@@ -237,17 +237,11 @@ public void TrainAndEvaluateRegression()
         {
             var mlContext = new MLContext(seed: 1);
 
-            // Get the dataset.
-            var data = mlContext.Data.CreateTextLoader(TestDatasets.housing.GetLoaderColumns(),
-                hasHeader: TestDatasets.housing.fileHasHeader, separatorChar: TestDatasets.housing.fileSeparator)
-                .Load(GetDataPath(TestDatasets.housing.trainFilename));
-
-            // Create a pipeline to train on the sentiment data.
-            var pipeline = mlContext.Transforms.Concatenate("Features", new string[] {
-                    "CrimesPerCapita", "PercentResidental", "PercentNonRetail", "CharlesRiver", "NitricOxides", "RoomsPerDwelling",
-                    "PercentPre40s", "EmploymentDistance", "HighwayDistance", "TaxRate", "TeacherRatio"})
-                .Append(mlContext.Transforms.CopyColumns("Label", "MedianHomeValue"))
-                .Append(mlContext.Regression.Trainers.FastTree(new FastTreeRegressionTrainer.Options { NumberOfThreads = 1 }));
+            // Get the dataset
+            var data = mlContext.Data.LoadFromTextFile<HousingRegression>(GetDataPath(TestDatasets.housing.trainFilename), hasHeader: true);
+            // Create a pipeline to train on the housing data.
+            var pipeline = mlContext.Transforms.Concatenate("Features", HousingRegression.Features)
+                .Append(mlContext.Regression.Trainers.FastForest(new FastForestRegression.Options { NumberOfThreads = 1 }));
 
             // Train the model.
             var model = pipeline.Fit(data);