Reformatting Conversion, FeatureSelection and Image Analytics of Transform to Width 85

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Conversion/ConvertType.cs

@@ -20,17 +20,22 @@ public static void Example()
             var data = mlContext.Data.LoadFromEnumerable(rawData);
 
             // Construct the pipeline.
-            var pipeline = mlContext.Transforms.Conversion.ConvertType("SurvivedInt32", "Survived", DataKind.Int32);
+            var pipeline = mlContext.Transforms.Conversion.ConvertType(
+                "SurvivedInt32", "Survived", DataKind.Int32);
 
             // Let's train our pipeline, and then apply it to the same data.
             var transformer = pipeline.Fit(data);
             var transformedData = transformer.Transform(data);
 
-            // Display original column 'Survived' (boolean) and converted column 'SurvivedInt32' (Int32)
-            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
+            // Display original column 'Survived' (boolean) and converted column 
+            // SurvivedInt32' (Int32)
+            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(
+                transformedData, true);
+
             foreach (var item in convertedData)
             {
-                Console.WriteLine("A:{0,-10}  Aconv:{1}", item.Survived, item.SurvivedInt32);
+                Console.WriteLine("A:{0,-10}  Aconv:{1}", item.Survived,
+                    item.SurvivedInt32);
             }
 
             // Output

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Conversion/ConvertTypeMultiColumn.cs

@@ -4,22 +4,33 @@
 
 namespace Samples.Dynamic
 {
-    // This example illustrates how to convert multiple columns of different types to one type, in this case System.Single. 
-    // This is often a useful data transformation before concatenating the features together and passing them to a particular estimator.
+    // This example illustrates how to convert multiple columns of different types
+    // to one type, in this case System.Single. 
+    // This is often a useful data transformation before concatenating the features
+    // together and passing them to a particular estimator.
     public static class ConvertTypeMultiColumn
     { 
         public static void Example()
         {
-            // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
-            // as well as the source of randomness.
+            // Create a new ML context, for ML.NET operations. It can be used for
+            // exception tracking and logging, as well as the source of randomness.
             var mlContext = new MLContext(seed: 1);
 
             var rawData = new[] {
-                new InputData() { Feature1 = true, Feature2 = "0.4", Feature3 = DateTime.Now, Feature4 = 0.145},
-                new InputData() { Feature1 = false, Feature2 = "0.5", Feature3 = DateTime.Today, Feature4 = 3.14},
-                new InputData() { Feature1 = false, Feature2 = "14", Feature3 = DateTime.Today, Feature4 = 0.2046},
-                new InputData() { Feature1 = false, Feature2 = "23", Feature3 = DateTime.Now, Feature4 = 0.1206},
-                new InputData() { Feature1 = true, Feature2 = "8904", Feature3 = DateTime.UtcNow, Feature4 = 8.09},
+                new InputData() { Feature1 = true, Feature2 = "0.4",
+                    Feature3 = DateTime.Now, Feature4 = 0.145},
+
+                new InputData() { Feature1 = false, Feature2 = "0.5",
+                    Feature3 = DateTime.Today, Feature4 = 3.14},
+
+                new InputData() { Feature1 = false, Feature2 = "14",
+                    Feature3 = DateTime.Today, Feature4 = 0.2046},
+
+                new InputData() { Feature1 = false, Feature2 = "23",
+                    Feature3 = DateTime.Now, Feature4 = 0.1206},
+
+                new InputData() { Feature1 = true, Feature2 = "8904",
+                    Feature3 = DateTime.UtcNow, Feature4 = 8.09},
             };
 
             // Convert the data to an IDataView.
@@ -37,17 +48,20 @@ public static void Example()
 
             // Let's fit our pipeline to the data.
             var transformer = pipeline.Fit(data);
-            // Transforming the same data. This will add the 4 columns defined in the pipeline, containing the converted
+            // Transforming the same data. This will add the 4 columns defined in
+            // the pipeline, containing the converted
             // values of the initial columns. 
             var transformedData = transformer.Transform(data);
 
             // Shape the transformed data as a strongly typed IEnumerable.
-            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
+            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(
+                transformedData, true);
 
             // Printing the results.
             Console.WriteLine("Converted1\t Converted2\t Converted3\t Converted4");
             foreach (var item in convertedData)
-                Console.WriteLine($"\t{item.Converted1}\t {item.Converted2}\t\t  {item.Converted3}\t {item.Converted4}");
+                Console.WriteLine($"\t{item.Converted1}\t {item.Converted2}\t\t  " +
+                    $"{item.Converted3}\t {item.Converted4}");
 
             // Transformed data.
             //

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Conversion/Hash.cs

@@ -9,8 +9,8 @@ public static class Hash
     {
         public static void Example()
         {
-            // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
-            // as well as the source of randomness.
+            // Create a new ML context, for ML.NET operations. It can be used for
+            // exception tracking and logging, as well as the source of randomness.
             var mlContext = new MLContext(seed: 1);
 
             // Get a small dataset as an IEnumerable.
@@ -24,30 +24,40 @@ public static void Example()
 
             var data = mlContext.Data.LoadFromEnumerable(rawData);
 
-            // Construct the pipeline that would hash the two columns and store the results in new columns.
-            // The first transform hashes the string column and the second transform hashes the integer column.
+            // Construct the pipeline that would hash the two columns and store the
+            // results in new columns. The first transform hashes the string column
+            // and the second transform hashes the integer column.
             //
-            // Hashing is not a reversible operation, so there is no way to retrive the original value from the hashed value. 
-            // Sometimes, for debugging, or model explainability, users will need to know what values in the original columns generated
-            // the values in the hashed columns, since the algorithms will mostly use the hashed values for further computations.
-            // The Hash method will preserve the mapping from the original values to the hashed values in the Annotations of the 
-            // newly created column (column populated with the hashed values). 
-            // 
-            // Setting the maximumNumberOfInverts parameters to -1 will preserve the full map. 
-            // If that parameter is left to the default 0 value, the mapping is not preserved.
-            var pipeline = mlContext.Transforms.Conversion.Hash("CategoryHashed", "Category", numberOfBits: 16, maximumNumberOfInverts: -1)
-                          .Append(mlContext.Transforms.Conversion.Hash("AgeHashed", "Age", numberOfBits: 8));
+            // Hashing is not a reversible operation, so there is no way to retrive
+            // the original value from the hashed value. Sometimes, for debugging,
+            // or model explainability, users will need to know what values in the
+            // original columns generated the values in the hashed columns, since
+            // the algorithms will mostly use the hashed values for further
+            // computations. The Hash method will preserve the mapping from the
+            // original values to the hashed values in the Annotations of the newly
+            // created column (column populated with the hashed values). 
+            //
+            // Setting the maximumNumberOfInverts parameters to -1 will preserve the
+            // full map. If that parameter is left to the default 0 value, the
+            // mapping is not preserved.
+            var pipeline = mlContext.Transforms.Conversion.Hash("CategoryHashed",
+                "Category", numberOfBits: 16, maximumNumberOfInverts: -1)
+                .Append(mlContext.Transforms.Conversion.Hash("AgeHashed", "Age",
+                numberOfBits: 8));
 
             // Let's fit our pipeline, and then apply it to the same data.
             var transformer = pipeline.Fit(data);
             var transformedData = transformer.Transform(data);
 
-            // Convert the post transformation from the IDataView format to an IEnumerable<TransformedData> for easy consumption.
-            var convertedData = mlContext.Data.CreateEnumerable<TransformedDataPoint>(transformedData, true);
+            // Convert the post transformation from the IDataView format to an
+            // IEnumerable <TransformedData> for easy consumption.
+            var convertedData = mlContext.Data.CreateEnumerable<
+                TransformedDataPoint>(transformedData, true);
 
             Console.WriteLine("Category CategoryHashed\t Age\t AgeHashed");
             foreach (var item in convertedData)
-                Console.WriteLine($"{item.Category}\t {item.CategoryHashed}\t\t  {item.Age}\t {item.AgeHashed}");
+                Console.WriteLine($"{item.Category}\t {item.CategoryHashed}\t\t  " +
+                    $"{item.Age}\t {item.AgeHashed}");
 
             // Expected data after the transformation.
             //
@@ -58,20 +68,24 @@ public static void Example()
             // MLB      36206            18      127
             // MLS      6013             14      62
 
-            // For the Category column, where we set the maximumNumberOfInverts parameter, the names of the original categories, 
-            // and their correspondance with the generated hash values is preserved in the Annotations in the format of indices and values. 
-            // the indices array will have the hashed values, and the corresponding element, position-wise, in the values array will 
-            // contain the original value. 
+            // For the Category column, where we set the maximumNumberOfInverts
+            // parameter, the names of the original categories, and their
+            // correspondance with the generated hash values is preserved in the
+            // Annotations in the format of indices and values.the indices array
+            // will have the hashed values, and the corresponding element,
+            // position -wise, in the values array will contain the original value. 
             //
             // See below for an example on how to retrieve the mapping. 
             var slotNames = new VBuffer<ReadOnlyMemory<char>>();
-            transformedData.Schema["CategoryHashed"].Annotations.GetValue("KeyValues", ref slotNames);
+            transformedData.Schema["CategoryHashed"].Annotations.GetValue(
+                "KeyValues", ref slotNames);
 
             var indices = slotNames.GetIndices();
             var categoryNames = slotNames.GetValues();
 
             for (int i = 0; i < indices.Length; i++)
-                Console.WriteLine($"The original value of the {indices[i]} category is {categoryNames[i]}");
+                Console.WriteLine($"The original value of the {indices[i]} " +
+                    $"category is {categoryNames[i]}");
 
             // Output Data
             // 

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Conversion/KeyToValueToKey.cs

@@ -11,8 +11,8 @@ public class KeyToValueToKey
     {
         public static void Example()
         {
-            // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
-            // as well as the source of randomness.
+            // Create a new ML context, for ML.NET operations. It can be used for
+            // exception tracking and logging, as well as the source of randomness.
             var mlContext = new MLContext();
 
             // Get a small dataset as an IEnumerable.
@@ -27,25 +27,40 @@ public static void Example()
 
             // A pipeline to convert the terms of the 'Review' column in 
             // making use of default settings.
-            var defaultPipeline = mlContext.Transforms.Text.TokenizeIntoWords("TokenizedText", nameof(DataPoint.Review))
-                .Append(mlContext.Transforms.Conversion.MapValueToKey(nameof(TransformedData.Keys), "TokenizedText"));
+            var defaultPipeline = mlContext.Transforms.Text.TokenizeIntoWords(
+                "TokenizedText", nameof(DataPoint.Review)).Append(mlContext
+                .Transforms.Conversion.MapValueToKey(nameof(TransformedData.Keys),
+                "TokenizedText"));
 
-            // Another pipeline, that customizes the advanced settings of the ValueToKeyMappingEstimator.
-            // We can change the maximumNumberOfKeys to limit how many keys will get generated out of the set of words, 
-            // and condition the order in which they get evaluated by changing keyOrdinality from the default ByOccurence (order in which they get encountered) 
-            // to value/alphabetically.
-            var customizedPipeline = mlContext.Transforms.Text.TokenizeIntoWords("TokenizedText", nameof(DataPoint.Review))
-                .Append(mlContext.Transforms.Conversion.MapValueToKey(nameof(TransformedData.Keys), "TokenizedText", maximumNumberOfKeys: 10,
-                keyOrdinality: ValueToKeyMappingEstimator.KeyOrdinality.ByValue));
+            // Another pipeline, that customizes the advanced settings of the
+            // ValueToKeyMappingEstimator. We can change the maximumNumberOfKeys to
+            // limit how many keys will get generated out of the set of words, and
+            // condition the order in which they get evaluated by changing
+            // keyOrdinality from the default ByOccurence (order in which they get
+            // encountered) to value/alphabetically.
+            var customizedPipeline = mlContext.Transforms.Text.TokenizeIntoWords(
+                "TokenizedText", nameof(DataPoint.Review)).Append(mlContext
+                .Transforms.Conversion.MapValueToKey(nameof(TransformedData.Keys),
+                "TokenizedText", maximumNumberOfKeys: 10, keyOrdinality:
+                ValueToKeyMappingEstimator.KeyOrdinality.ByValue));
 
             // The transformed data.
-            var transformedDataDefault = defaultPipeline.Fit(trainData).Transform(trainData);
-            var transformedDataCustomized = customizedPipeline.Fit(trainData).Transform(trainData);
+            var transformedDataDefault = defaultPipeline.Fit(trainData).Transform(
+                trainData);
+
+            var transformedDataCustomized = customizedPipeline.Fit(trainData)
+                .Transform(trainData);
 
             // Getting the resulting data as an IEnumerable.
             // This will contain the newly created columns.
-            IEnumerable<TransformedData> defaultData = mlContext.Data.CreateEnumerable<TransformedData>(transformedDataDefault, reuseRowObject: false);
-            IEnumerable<TransformedData> customizedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedDataCustomized, reuseRowObject: false);
+            IEnumerable<TransformedData> defaultData = mlContext.Data.
+                CreateEnumerable<TransformedData>(transformedDataDefault,
+                reuseRowObject: false);
+
+            IEnumerable<TransformedData> customizedData = mlContext.Data.
+                CreateEnumerable<TransformedData>(transformedDataCustomized,
+                reuseRowObject: false);
+
             Console.WriteLine($"Keys");
             foreach (var dataRow in defaultData)
                 Console.WriteLine($"{string.Join(',', dataRow.Keys)}");
@@ -65,13 +80,17 @@ public static void Example()
             //  8,2,9,7,6,4
             //  3,10,0,0,0
             //  3,10,0,0,0,8
-            // Retrieve the original values, by appending the KeyToValue etimator to the existing pipelines
-            // to convert the keys back to the strings.
-            var pipeline = defaultPipeline.Append(mlContext.Transforms.Conversion.MapKeyToValue(nameof(TransformedData.Keys)));
+            // Retrieve the original values, by appending the KeyToValue etimator to
+            // the existing pipelines to convert the keys back to the strings.
+            var pipeline = defaultPipeline.Append(mlContext.Transforms.Conversion
+                .MapKeyToValue(nameof(TransformedData.Keys)));
+
             transformedDataDefault = pipeline.Fit(trainData).Transform(trainData);
 
             // Preview of the DefaultColumnName column obtained.
-            var originalColumnBack = transformedDataDefault.GetColumn<VBuffer<ReadOnlyMemory<char>>>(transformedDataDefault.Schema[nameof(TransformedData.Keys)]);
+            var originalColumnBack = transformedDataDefault.GetColumn<VBuffer<
+                ReadOnlyMemory<char>>>(transformedDataDefault.Schema[nameof(
+                TransformedData.Keys)]);
 
             foreach (var row in originalColumnBack)
             {

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Conversion/MapKeyToBinaryVector.cs

@@ -7,14 +7,16 @@ namespace Samples.Dynamic
 {
     class MapKeyToBinaryVector
     {
-        /// This example demonstrates the use of MapKeyToVector by mapping keys to floats[] of 0 and 1, representing the number in binary format. 
-        /// Because the ML.NET KeyType maps the missing value to zero, counting starts at 1, so the uint values
-        /// converted to KeyTypes will appear skewed by one. 
+        /// This example demonstrates the use of MapKeyToVector by mapping keys to
+        /// floats[] of 0 and 1, representing the number in binary format. 
+        /// Because the ML.NET KeyType maps the missing value to zero, counting
+        /// starts at 1, so the uint values converted to KeyTypes will appear
+        /// skewed by one. 
         /// See https://github.com/dotnet/machinelearning/blob/master/docs/code/IDataViewTypeSystem.md#key-types
         public static void Example()
         {
-            // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
-            // as well as the source of randomness.
+            // Create a new ML context, for ML.NET operations. It can be used for
+            // exception tracking and logging, as well as the source of randomness.
             var mlContext = new MLContext();
 
             // Get a small dataset as an IEnumerable.
@@ -30,18 +32,21 @@ public static void Example()
             var data = mlContext.Data.LoadFromEnumerable(rawData);
 
             // Constructs the ML.net pipeline
-            var pipeline = mlContext.Transforms.Conversion.MapKeyToBinaryVector("TimeframeVector", "Timeframe");
+            var pipeline = mlContext.Transforms.Conversion.MapKeyToBinaryVector(
+                "TimeframeVector", "Timeframe");
 
             // Fits the pipeline to the data.
             IDataView transformedData = pipeline.Fit(data).Transform(data);
 
             // Getting the resulting data as an IEnumerable.
             // This will contain the newly created columns.
-            IEnumerable<TransformedData> features = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, reuseRowObject: false);
+            IEnumerable<TransformedData> features = mlContext.Data.CreateEnumerable<
+                TransformedData>(transformedData, reuseRowObject: false);
 
             Console.WriteLine($" Timeframe           TimeframeVector");
             foreach (var featureRow in features)
-                Console.WriteLine($"{featureRow.Timeframe}\t\t\t{string.Join(',', featureRow.TimeframeVector)}");
+                Console.WriteLine($"{featureRow.Timeframe}\t\t\t" +
+                    $"{string.Join(',', featureRow.TimeframeVector)}");
 
             // Timeframe             TimeframeVector
             // 10                      0,1,0,0,1 //binary representation of 9, the original value