Clean SamplesUtils

docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/Cache.cs

@@ -43,7 +43,7 @@ private static (int lines, double columnAverage, double elapsedSeconds) TimeToSc
         {
             int lines = 0;
             double columnAverage = 0.0;
-            var enumerable = mlContext.Data.CreateEnumerable<DatasetUtils.HousingRegression>(data, reuseRowObject: true);
+            var enumerable = mlContext.Data.CreateEnumerable<HousingRegression>(data, reuseRowObject: true);
             var watch = System.Diagnostics.Stopwatch.StartNew();
             foreach (var row in enumerable)
             {
@@ -58,5 +58,25 @@ private static (int lines, double columnAverage, double elapsedSeconds) TimeToSc
 
             return (lines, columnAverage, elapsed.Seconds);
         }       
+
+        /// <summary>
+        /// A class to hold the raw housing regression rows.
+        /// </summary>
+        public sealed class HousingRegression
+        {
+            public float MedianHomeValue { get; set; }
+            public float CrimesPerCapita { get; set; }
+            public float PercentResidental { get; set; }
+            public float PercentNonRetail { get; set; }
+            public float CharlesRiver { get; set; }
+            public float NitricOxides { get; set; }
+            public float RoomsPerDwelling { get; set; }
+            public float PercentPre40s { get; set; }
+            public float EmploymentDistance { get; set; }
+            public float HighwayDistance { get; set; }
+            public float TaxRate { get; set; }
+            public float TeacherRatio { get; set; }
+        }
+
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/TakeRows.cs

@@ -14,7 +14,7 @@ public static void Example()
             var mlContext = new MLContext();
 
             // Get a small dataset as an IEnumerable.
-            var enumerableOfData = Microsoft.ML.SamplesUtils.DatasetUtils.GetSampleTemperatureData(10);
+            var enumerableOfData = GetSampleTemperatureData(10);
             var data = mlContext.Data.LoadFromEnumerable(enumerableOfData);
 
             // Before we apply a filter, examine all the records in the dataset.
@@ -41,7 +41,7 @@ public static void Example()
             var filteredData = mlContext.Data.TakeRows(data, 5);
 
             // Look at the filtered data and observe that only the first 5 rows are in the resulting dataset.
-            var enumerable = mlContext.Data.CreateEnumerable<Microsoft.ML.SamplesUtils.DatasetUtils.SampleTemperatureData>(filteredData, reuseRowObject: true);
+            var enumerable = mlContext.Data.CreateEnumerable<SampleTemperatureData>(filteredData, reuseRowObject: true);
             Console.WriteLine($"Date\tTemperature");
             foreach (var row in enumerable)
             {

docs/samples/Microsoft.ML.Samples/Dynamic/NgramExtraction.cs

@@ -14,7 +14,12 @@ public static void Example()
             var ml = new MLContext();
 
             // Get a small dataset as an IEnumerable and convert to IDataView.
-            IEnumerable<Microsoft.ML.SamplesUtils.DatasetUtils.SampleSentimentData> data = Microsoft.ML.SamplesUtils.DatasetUtils.GetSentimentData();
+            var data = new List<SampleSentimentData>() {
+                new SampleSentimentData { Sentiment = true, SentimentText = "Best game I've ever played." },
+                new SampleSentimentData { Sentiment = false, SentimentText = "==RUDE== Dude, 2" },
+                new SampleSentimentData { Sentiment = true, SentimentText = "Until the next game, this is the best Xbox game!" } };
+
+            // Convert IEnumerable to IDataView.
             var trainData = ml.Data.LoadFromEnumerable(data);
 
             // Preview of the data.
@@ -71,5 +76,14 @@ public static void Example()
             // 'e' - 1 '<?>' - 2 'd' - 1 '=' - 4 '=|=' - 2 '=|R' - 1 'R' - 1 'R|U' - 1 'U' - 1 'U|D' - 1 'D' - 2 ...
             // 'B' - 0 'B|e' - 0 'e' - 6 'e|s' - 1 's' - 3 's|t' - 1 't' - 6 't|<?>' - 2 '<?>' - 9 '<?>|g' - 2 ...
         }
+
+        /// <summary>
+        /// A dataset that contains a tweet and the sentiment assigned to that tweet: 0 - negative and 1 - positive sentiment.
+        /// </summary>
+        public class SampleSentimentData
+        {
+            public bool Sentiment { get; set; }
+            public string SentimentText { get; set; }
+        }
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/TextTransform.cs

@@ -15,7 +15,13 @@ public static void Example()
             var ml = new MLContext();
 
             // Get a small dataset as an IEnumerable and convert to IDataView.
-            var data = Microsoft.ML.SamplesUtils.DatasetUtils.GetSentimentData();
+            // Get a small dataset as an IEnumerable and convert to IDataView.
+            var data = new List<SampleSentimentData>() {
+                new SampleSentimentData { Sentiment = true, SentimentText = "Best game I've ever played." },
+                new SampleSentimentData { Sentiment = false, SentimentText = "==RUDE== Dude, 2" },
+                new SampleSentimentData { Sentiment = true, SentimentText = "Until the next game, this is the best Xbox game!" } };
+
+            // Convert IEnumerable to IDataView.
             var trainData = ml.Data.LoadFromEnumerable(data);
 
             // Preview of the data.
@@ -78,5 +84,14 @@ public static void Example()
             // 0.25 0.25 0.25 0.25 0.5 0.25 0.25 0.25 0.25 0.25 0.25 0.25 0.25 0.7071068 0.7071068 0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.4472136 0.4472136 0.4472136 0.4472136 0.4472136
             // 0 0.125 0.125 0.125 0.125 0.25 0.25 0.25 0.125 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0.125 0.125 0.125 0.125 0.125 0.125 0.375 0.25 0.25 0.125 0.125 0.125 0.125 0.125 0.125 0.125 0.125 0.25 0.125 0.125 0.125 0.125 0.125 0.125 0.125 0.125 0.125 0.125 0.125 0.125 0.2672612 0.5345225 0 0 0 0 0 0.2672612 0.5345225 0.2672612 0.2672612 0.2672612 0.2672612        }
         }
+
+        /// <summary>
+        /// A dataset that contains a tweet and the sentiment assigned to that tweet: 0 - negative and 1 - positive sentiment.
+        /// </summary>
+        public class SampleSentimentData
+        {
+            public bool Sentiment { get; set; }
+            public string SentimentText { get; set; }
+        }
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbmAdvanced.cs

@@ -53,7 +53,7 @@ public static void Example()
             // Evaluate how the model is doing on the test data.
             var dataWithPredictions = model.Transform(split.TestSet);
             var metrics = mlContext.Regression.Evaluate(dataWithPredictions, labelColumnName: labelName);
-            Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
+            PrintMetrics(metrics);
 
             // Expected output
             //   L1: 4.97
@@ -62,5 +62,13 @@ public static void Example()
             //   RMS: 7.17
             //   RSquared: 0.08
         }
+
+        public static void PrintMetrics(RegressionMetrics metrics)
+        {
+            Console.WriteLine($"Mean Absolute Error: {metrics.MeanAbsoluteError:F2}");
+            Console.WriteLine($"Mean Squared Error: {metrics.MeanSquaredError:F2}");
+            Console.WriteLine($"Root Mean Squared Error: {metrics.RootMeanSquaredError:F2}");
+            Console.WriteLine($"RSquared: {metrics.RSquared:F2}");
+        }
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbmWithOptionsAdvanced.cs

@@ -62,7 +62,7 @@ public static void Example()
             // Evaluate how the model is doing on the test data.
             var dataWithPredictions = model.Transform(split.TestSet);
             var metrics = mlContext.Regression.Evaluate(dataWithPredictions, labelColumnName: labelName);
-            Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
+            PrintMetrics(metrics);
 
             // Expected output
             //   L1: 4.97
@@ -71,5 +71,13 @@ public static void Example()
             //   RMS: 7.17
             //   RSquared: 0.08
         }
+
+        public static void PrintMetrics(RegressionMetrics metrics)
+        {
+            Console.WriteLine($"Mean Absolute Error: {metrics.MeanAbsoluteError:F2}");
+            Console.WriteLine($"Mean Squared Error: {metrics.MeanSquaredError:F2}");
+            Console.WriteLine($"Root Mean Squared Error: {metrics.RootMeanSquaredError:F2}");
+            Console.WriteLine($"RSquared: {metrics.RSquared:F2}");
+        }
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/OrdinaryLeastSquaresAdvanced.cs

@@ -55,7 +55,7 @@ public static void Example()
             var dataWithPredictions = model.Transform(split.TestSet);
             var metrics = mlContext.Regression.Evaluate(dataWithPredictions);
 
-            ConsoleUtils.PrintMetrics(metrics);
+            PrintMetrics(metrics);
 
             // Expected output:
             //   L1: 4.15
@@ -64,5 +64,13 @@ public static void Example()
             //   RMS: 5.65
             //   RSquared: 0.56
         }
+
+        public static void PrintMetrics(RegressionMetrics metrics)
+        {
+            Console.WriteLine($"Mean Absolute Error: {metrics.MeanAbsoluteError:F2}");
+            Console.WriteLine($"Mean Squared Error: {metrics.MeanSquaredError:F2}");
+            Console.WriteLine($"Root Mean Squared Error: {metrics.RootMeanSquaredError:F2}");
+            Console.WriteLine($"RSquared: {metrics.RSquared:F2}");
+        }
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/OrdinaryLeastSquaresWithOptionsAdvanced.cs

@@ -59,7 +59,7 @@ public static void Example()
             var dataWithPredictions = model.Transform(split.TestSet);
             var metrics = mlContext.Regression.Evaluate(dataWithPredictions);
 
-            ConsoleUtils.PrintMetrics(metrics);
+            PrintMetrics(metrics);
 
             // Expected output:
             //   L1: 4.14
@@ -68,5 +68,13 @@ public static void Example()
             //   RMS: 5.69
             //   RSquared: 0.56
         }
+
+        public static void PrintMetrics(RegressionMetrics metrics)
+        {
+            Console.WriteLine($"Mean Absolute Error: {metrics.MeanAbsoluteError:F2}");
+            Console.WriteLine($"Mean Squared Error: {metrics.MeanSquaredError:F2}");
+            Console.WriteLine($"Root Mean Squared Error: {metrics.RootMeanSquaredError:F2}");
+            Console.WriteLine($"RSquared: {metrics.RSquared:F2}");
+        }
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Projection/VectorWhiten.cs

@@ -17,7 +17,7 @@ public static void Example()
             var ml = new MLContext();
 
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
-            var data = Microsoft.ML.SamplesUtils.DatasetUtils.GetVectorOfNumbersData();
+            var data = GetVectorOfNumbersData();
             var trainData = ml.Data.LoadFromEnumerable(data);
 
             // Preview of the data.
@@ -40,14 +40,14 @@ public static void Example()
             };
 
             // A pipeline to project Features column into white noise vector.
-            var whiteningPipeline = ml.Transforms.VectorWhiten(nameof(Microsoft.ML.SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features),
+            var whiteningPipeline = ml.Transforms.VectorWhiten(nameof(SampleVectorOfNumbersData.Features),
                 kind: Microsoft.ML.Transforms.WhiteningKind.ZeroPhaseComponentAnalysis);
             // The transformed (projected) data.
             var transformedData = whiteningPipeline.Fit(trainData).Transform(trainData);
             // Getting the data of the newly created column, so we can preview it.
-            var whitening = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema[nameof(Microsoft.ML.SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features)]);
+            var whitening = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema[nameof(SampleVectorOfNumbersData.Features)]);
 
-            printHelper(nameof(Microsoft.ML.SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features), whitening);
+            printHelper(nameof(SampleVectorOfNumbersData.Features), whitening);
 
             // Features column obtained post-transformation.
             //
@@ -58,5 +58,38 @@ public static void Example()
             // 0.454  0.523  0.593  0.664  1.886 -0.757 -0.687 -0.022  0.176  0.310
             // 0.863  0.938  1.016  1.093 -1.326 -0.096 -0.019  0.189  0.330  0.483
         }
+
+        private class SampleVectorOfNumbersData
+        {
+            [VectorType(10)]
+            public float[] Features { get; set; }
+        }
+
+        /// <summary>
+        /// Returns a few rows of the infertility dataset.
+        /// </summary>
+        private static IEnumerable<SampleVectorOfNumbersData> GetVectorOfNumbersData()
+        {
+            var data = new List<SampleVectorOfNumbersData>();
+            data.Add(new SampleVectorOfNumbersData { Features = new float[10] { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 } });
+            data.Add(new SampleVectorOfNumbersData { Features = new float[10] { 1, 2, 3, 4, 5, 6, 7, 8, 9, 0 } });
+            data.Add(new SampleVectorOfNumbersData
+            {
+                Features = new float[10] { 2, 3, 4, 5, 6, 7, 8, 9, 0, 1 }
+            });
+            data.Add(new SampleVectorOfNumbersData
+            {
+                Features = new float[10] { 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, }
+            });
+            data.Add(new SampleVectorOfNumbersData
+            {
+                Features = new float[10] { 5, 6, 7, 8, 9, 0, 1, 2, 3, 4 }
+            });
+            data.Add(new SampleVectorOfNumbersData
+            {
+                Features = new float[10] { 6, 7, 8, 9, 0, 1, 2, 3, 4, 5 }
+            });
+            return data;
+        }
     }
 }

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Projection/VectorWhitenWithOptions.cs

@@ -16,7 +16,7 @@ public static void Example()
             var ml = new MLContext();
 
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
-            var data = Microsoft.ML.SamplesUtils.DatasetUtils.GetVectorOfNumbersData();
+            var data = GetVectorOfNumbersData();
             var trainData = ml.Data.LoadFromEnumerable(data);
 
             // Preview of the data.
@@ -40,13 +40,13 @@ public static void Example()
 
 
             // A pipeline to project Features column into white noise vector.
-            var whiteningPipeline = ml.Transforms.VectorWhiten(nameof(Microsoft.ML.SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features), kind: Microsoft.ML.Transforms.WhiteningKind.PrincipalComponentAnalysis, rank: 4);
+            var whiteningPipeline = ml.Transforms.VectorWhiten(nameof(SampleVectorOfNumbersData.Features), kind: Microsoft.ML.Transforms.WhiteningKind.PrincipalComponentAnalysis, rank: 4);
             // The transformed (projected) data.
             var transformedData = whiteningPipeline.Fit(trainData).Transform(trainData);
             // Getting the data of the newly created column, so we can preview it.
-            var whitening = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema[nameof(Microsoft.ML.SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features)]);
+            var whitening = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema[nameof(SampleVectorOfNumbersData.Features)]);
 
-            printHelper(nameof(Microsoft.ML.SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features), whitening);
+            printHelper(nameof(SampleVectorOfNumbersData.Features), whitening);
 
             // Features column obtained post-transformation.
             // -0.979  0.867  1.449  1.236
@@ -56,5 +56,38 @@ public static void Example()
             // -0.972 -1.338 -0.028  0.614
             // -0.938 -1.405  0.752 -0.967
         }
+
+        private class SampleVectorOfNumbersData
+        {
+            [VectorType(10)]
+            public float[] Features { get; set; }
+        }
+
+        /// <summary>
+        /// Returns a few rows of the infertility dataset.
+        /// </summary>
+        private static IEnumerable<SampleVectorOfNumbersData> GetVectorOfNumbersData()
+        {
+            var data = new List<SampleVectorOfNumbersData>();
+            data.Add(new SampleVectorOfNumbersData { Features = new float[10] { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 } });
+            data.Add(new SampleVectorOfNumbersData { Features = new float[10] { 1, 2, 3, 4, 5, 6, 7, 8, 9, 0 } });
+            data.Add(new SampleVectorOfNumbersData
+            {
+                Features = new float[10] { 2, 3, 4, 5, 6, 7, 8, 9, 0, 1 }
+            });
+            data.Add(new SampleVectorOfNumbersData
+            {
+                Features = new float[10] { 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, }
+            });
+            data.Add(new SampleVectorOfNumbersData
+            {
+                Features = new float[10] { 5, 6, 7, 8, 9, 0, 1, 2, 3, 4 }
+            });
+            data.Add(new SampleVectorOfNumbersData
+            {
+                Features = new float[10] { 6, 7, 8, 9, 0, 1, 2, 3, 4, 5 }
+            });
+            return data;
+        }
     }
 }