Merge remote-tracking branch 'origin/master' into singlis/ova

Author: singlis

build/Dependencies.props

@@ -15,7 +15,7 @@
     <GoogleProtobufPackageVersion>3.5.1</GoogleProtobufPackageVersion>
     <LightGBMPackageVersion>2.2.3</LightGBMPackageVersion>
     <MicrosoftMLOnnxRuntimePackageVersion>0.2.1</MicrosoftMLOnnxRuntimePackageVersion>
-    <MlNetMklDepsPackageVersion>0.0.0.7</MlNetMklDepsPackageVersion>
+    <MlNetMklDepsPackageVersion>0.0.0.8</MlNetMklDepsPackageVersion>
     <ParquetDotNetPackageVersion>2.1.3</ParquetDotNetPackageVersion>
     <SystemDrawingCommonPackageVersion>4.5.0</SystemDrawingCommonPackageVersion>
     <SystemIOFileSystemAccessControl>4.5.0</SystemIOFileSystemAccessControl>

docs/code/MlNetCookBook.md

@@ -303,8 +303,8 @@ var someRows = mlContext
 // This will give the entire dataset: make sure to only take several row
 // in case the dataset is huge. The is similar to the static API, except
 // you have to specify the column name and type.
-var featureColumns = transformedData.GetColumn<string[]>(mlContext, "AllFeatures")
-    .Take(20).ToArray();
+var featureColumns = transformedData.GetColumn<string[]>(transformedData.Schema["AllFeatures"])
+
 ```
 ## How do I train a regression model?
 
@@ -637,7 +637,7 @@ var pipeline =
 var normalizedData = pipeline.Fit(trainData).Transform(trainData);
 
 // Inspect one column of the resulting dataset.
-var meanVarValues = normalizedData.GetColumn<float[]>(mlContext, "MeanVarNormalized").ToArray();
+var meanVarValues = normalizedData.GetColumn<float[]>(normalizedData.Schema["MeanVarNormalized"]).ToArray();
 ```
 
 ## How do I train my model on categorical data?
@@ -682,8 +682,8 @@ var loader = mlContext.Data.CreateTextLoader(new[]
 // Load the data.
 var data = loader.Load(dataPath);
 
-// Inspect the first 10 records of the categorical columns to check that they are correctly load.
-var catColumns = data.GetColumn<string[]>(mlContext, "CategoricalFeatures").Take(10).ToArray();
+// Inspect the first 10 records of the categorical columns to check that they are correctly read.
+var catColumns = data.GetColumn<string[]>(data.Schema["CategoricalFeatures"]).Take(10).ToArray();
 
 // Build several alternative featurization pipelines.
 var pipeline =
@@ -699,8 +699,8 @@ var pipeline =
 var transformedData = pipeline.Fit(data).Transform(data);
 
 // Inspect some columns of the resulting dataset.
-var categoricalBags = transformedData.GetColumn<float[]>(mlContext, "CategoricalBag").Take(10).ToArray();
-var workclasses = transformedData.GetColumn<float[]>(mlContext, "WorkclassOneHotTrimmed").Take(10).ToArray();
+var categoricalBags = transformedData.GetColumn<float[]>(transformedData.Schema["CategoricalBag"]).Take(10).ToArray();
+var workclasses = transformedData.GetColumn<float[]>(transformedData.Schema["WorkclassOneHotTrimmed"]).Take(10).ToArray();
 
 // Of course, if we want to train the model, we will need to compose a single float vector of all the features.
 // Here's how we could do this:
@@ -756,8 +756,8 @@ var loader = mlContext.Data.CreateTextLoader(new[]
 // Load the data.
 var data = loader.Load(dataPath);
 
-// Inspect the message texts that are load from the file.
-var messageTexts = data.GetColumn<string>(mlContext, "Message").Take(20).ToArray();
+// Inspect the message texts that are read from the file.
+var messageTexts = data.GetColumn<string>(data.Schema["Message"]).Take(20).ToArray();
 
 // Apply various kinds of text operations supported by ML.NET.
 var pipeline =

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

@@ -6,6 +6,7 @@ namespace Microsoft.ML.Samples.Dynamic
 {
     public static class FastTreeRegression
     {
+        // This example requires installation of additional nuget package <a href="https://www.nuget.org/packages/Microsoft.ML.FastTree/">Microsoft.ML.FastTree</a>.
         public static void Example()
         {
             // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 

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

@@ -82,8 +82,8 @@ public static void Example()
             };
 
             // Print the data that results from the transformations.
-            var countSelectColumn = transformedData.GetColumn<VBuffer<float>>(ml, "FeaturesCountSelect");
-            var MISelectColumn = transformedData.GetColumn<VBuffer<float>>(ml, "FeaturesMISelect");
+            var countSelectColumn = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema["FeaturesCountSelect"]);
+            var MISelectColumn = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema["FeaturesMISelect"]);
             printHelper("FeaturesCountSelect", countSelectColumn);
             printHelper("FeaturesMISelect", MISelectColumn);
 

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

@@ -60,7 +60,7 @@ public static void Example()
             };
 
             // Preview of the DefaultKeys column obtained after processing the input.
-            var defaultColumn = transformedData_default.GetColumn<VBuffer<uint>>(ml, defaultColumnName);
+            var defaultColumn = transformedData_default.GetColumn<VBuffer<uint>>(transformedData_default.Schema[defaultColumnName]);
             printHelper(defaultColumnName, defaultColumn);
 
             // DefaultKeys column obtained post-transformation.
@@ -71,7 +71,7 @@ public static void Example()
             // 9 10 11 12 13 6
 
             // Previewing the CustomizedKeys column obtained after processing the input.
-            var customizedColumn = transformedData_customized.GetColumn<VBuffer<uint>>(ml, customizedColumnName);
+            var customizedColumn = transformedData_customized.GetColumn<VBuffer<uint>>(transformedData_customized.Schema[customizedColumnName]);
             printHelper(customizedColumnName, customizedColumn);
 
             // CustomizedKeys column obtained post-transformation.
@@ -87,7 +87,7 @@ public static void Example()
             transformedData_default = pipeline.Fit(trainData).Transform(trainData);
 
             // Preview of the DefaultColumnName column obtained.
-            var originalColumnBack = transformedData_default.GetColumn<VBuffer<ReadOnlyMemory<char>>>(ml, defaultColumnName);
+            var originalColumnBack = transformedData_default.GetColumn<VBuffer<ReadOnlyMemory<char>>>(transformedData_default.Schema[defaultColumnName]);
 
             foreach (var row in originalColumnBack)
             {

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

@@ -37,7 +37,7 @@ public static void Example()
             var transformed_data = transformer.Transform(trainData);
 
             // Column obtained after processing the input.
-            var ldaFeaturesColumn = transformed_data.GetColumn<VBuffer<float>>(ml, ldaFeatures);
+            var ldaFeaturesColumn = transformed_data.GetColumn<VBuffer<float>>(transformed_data.Schema[ldaFeatures]);
 
             Console.WriteLine($"{ldaFeatures} column obtained post-transformation.");
             foreach (var featureRow in ldaFeaturesColumn)

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

@@ -73,7 +73,7 @@ public static void Example()
             var metrics = ml.BinaryClassification.Evaluate(dataWithPredictions);
 
             Console.WriteLine($"Accuracy: {metrics.Accuracy}"); // 0.80
-            Console.WriteLine($"AUC: {metrics.Auc}"); // 0.64
+            Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve}"); // 0.64
             Console.WriteLine($"F1 Score: {metrics.F1Score}"); // 0.39
 
             Console.WriteLine($"Negative Precision: {metrics.NegativePrecision}"); // 0.81

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

@@ -26,8 +26,8 @@ public static void NgramTransform()
             // A pipeline to tokenize text as characters and then combine them together into ngrams
             // The pipeline uses the default settings to featurize.
 
-            var charsPipeline = ml.Transforms.Text.TokenizeCharacters("Chars", "SentimentText", useMarkerCharacters:false);
-            var ngramOnePipeline = ml.Transforms.Text.ProduceNgrams("CharsUnigrams", "Chars", ngramLength:1);
+            var charsPipeline = ml.Transforms.Text.TokenizeCharacters("Chars", "SentimentText", useMarkerCharacters: false);
+            var ngramOnePipeline = ml.Transforms.Text.ProduceNgrams("CharsUnigrams", "Chars", ngramLength: 1);
             var ngramTwpPipeline = ml.Transforms.Text.ProduceNgrams("CharsTwograms", "Chars");
             var oneCharsPipeline = charsPipeline.Append(ngramOnePipeline);
             var twoCharsPipeline = charsPipeline.Append(ngramTwpPipeline);
@@ -38,30 +38,30 @@ public static void NgramTransform()
 
             // Small helper to print the text inside the columns, in the console. 
             Action<string, IEnumerable<VBuffer<float>>, VBuffer<ReadOnlyMemory<char>>> printHelper = (columnName, column, names) =>
-           {
-               Console.WriteLine($"{columnName} column obtained post-transformation.");
-               var slots = names.GetValues();
-               foreach (var featureRow in column)
-               {
-                   foreach (var item in featureRow.Items())
-                       Console.Write($"'{slots[item.Key]}' - {item.Value} ");
-                   Console.WriteLine("");
-               }
+            {
+                Console.WriteLine($"{columnName} column obtained post-transformation.");
+                var slots = names.GetValues();
+                foreach (var featureRow in column)
+                {
+                    foreach (var item in featureRow.Items())
+                        Console.Write($"'{slots[item.Key]}' - {item.Value} ");
+                    Console.WriteLine("");
+                }
 
-               Console.WriteLine("===================================================");
-           };
+                Console.WriteLine("===================================================");
+            };
             // Preview of the CharsUnigrams column obtained after processing the input.
             VBuffer<ReadOnlyMemory<char>> slotNames = default;
             transformedData_onechars.Schema["CharsUnigrams"].GetSlotNames(ref slotNames);
-            var charsOneGramColumn = transformedData_onechars.GetColumn<VBuffer<float>>(ml, "CharsUnigrams");
+            var charsOneGramColumn = transformedData_onechars.GetColumn<VBuffer<float>>(transformedData_onechars.Schema["CharsUnigrams"]);
             printHelper("CharsUnigrams", charsOneGramColumn, slotNames);
 
             // CharsUnigrams column obtained post-transformation.
             // 'B' - 1 'e' - 6 's' - 1 't' - 1 '<?>' - 4 'g' - 1 'a' - 2 'm' - 1 'I' - 1 ''' - 1 'v' - 2 ...
             // 'e' - 1 '<?>' - 2 'd' - 1 '=' - 4 'R' - 1 'U' - 1 'D' - 2 'E' - 1 'u' - 1 ',' - 1 '2' - 1
             // 'B' - 0 'e' - 6 's' - 3 't' - 6 '<?>' - 9 'g' - 2 'a' - 2 'm' - 2 'I' - 0 ''' - 0 'v' - 0 ...
             // Preview of the CharsTwoGrams column obtained after processing the input.
-            var charsTwoGramColumn = transformedData_twochars.GetColumn<VBuffer<float>>(ml, "CharsTwograms");
+            var charsTwoGramColumn = transformedData_twochars.GetColumn<VBuffer<float>>(transformedData_onechars.Schema["CharsUnigrams"]);
             transformedData_twochars.Schema["CharsTwograms"].GetSlotNames(ref slotNames);
             printHelper("CharsTwograms", charsTwoGramColumn, slotNames);
 

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

@@ -44,7 +44,7 @@ public static void Example()
             var transformedData = transformer.Transform(trainData);
 
             // Getting the data of the newly created column, so we can preview it.
-            var normalizedColumn = transformedData.GetColumn<float>(ml, "Induced");
+            var normalizedColumn = transformedData.GetColumn<float>(transformedData.Schema["Induced"]);
 
             // A small printing utility.
             Action<string, IEnumerable<float>> printHelper = (colName, column) =>
@@ -72,8 +72,8 @@ public static void Example()
             var multiColtransformedData = multiColtransformer.Transform(trainData);
 
             // Getting the newly created columns. 
-            var normalizedInduced = multiColtransformedData.GetColumn<float>(ml, "LogInduced");
-            var normalizedSpont = multiColtransformedData.GetColumn<float>(ml, "LogSpontaneous");
+            var normalizedInduced = multiColtransformedData.GetColumn<float>(multiColtransformedData.Schema["LogInduced"]);
+            var normalizedSpont = multiColtransformedData.GetColumn<float>(multiColtransformedData.Schema["LogSpontaneous"]);
 
             printHelper("LogInduced", normalizedInduced);
 

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

@@ -41,7 +41,7 @@ public static void Example()
             // The transformed (projected) data.
             var transformedData = rffPipeline.Fit(trainData).Transform(trainData);
             // Getting the data of the newly created column, so we can preview it.
-            var randomFourier = transformedData.GetColumn<VBuffer<float>>(ml, nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features));
+            var randomFourier = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema[nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features)]);
 
             printHelper(nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features), randomFourier);
 
@@ -59,7 +59,7 @@ public static void Example()
             // The transformed (projected) data.
             transformedData = lpNormalizePipeline.Fit(trainData).Transform(trainData);
             // Getting the data of the newly created column, so we can preview it.
-            var lpNormalize= transformedData.GetColumn<VBuffer<float>>(ml, nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features));
+            var lpNormalize= transformedData.GetColumn<VBuffer<float>>(transformedData.Schema[nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features)]);
 
             printHelper(nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features), lpNormalize);
 
@@ -77,7 +77,7 @@ public static void Example()
             // The transformed (projected) data.
             transformedData = gcNormalizePipeline.Fit(trainData).Transform(trainData);
             // Getting the data of the newly created column, so we can preview it.
-            var gcNormalize = transformedData.GetColumn<VBuffer<float>>(ml, nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features));
+            var gcNormalize = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema[nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features)]);
 
             printHelper(nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features), gcNormalize);
 

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

@@ -54,14 +54,14 @@ public static void Example()
             };
 
             // Preview the result of breaking string into array of words.
-            var originalText = transformedDataDefault.GetColumn<VBuffer<ReadOnlyMemory<char>>>(ml, originalTextColumnName);
+            var originalText = transformedDataDefault.GetColumn<VBuffer<ReadOnlyMemory<char>>>(transformedDataDefault.Schema[originalTextColumnName]);
             printHelper(originalTextColumnName, originalText);
             // Best|game|I've|ever|played.|
             // == RUDE ==| Dude,| 2 |
             // Until | the | next | game,| this |is| the | best | Xbox | game!|
 
             // Preview the result of cleaning with default stop word remover.
-            var defaultRemoverData = transformedDataDefault.GetColumn<VBuffer<ReadOnlyMemory<char>>>(ml, "DefaultRemover");
+            var defaultRemoverData = transformedDataDefault.GetColumn<VBuffer<ReadOnlyMemory<char>>>(transformedDataDefault.Schema["DefaultRemover"]);
             printHelper("DefaultRemover", defaultRemoverData);
             // Best|game|I've|played.|
             // == RUDE ==| Dude,| 2 |
@@ -70,7 +70,7 @@ public static void Example()
 
 
             // Preview the result of cleaning with default customized stop word remover.
-            var customizeRemoverData = transformedDataCustomized.GetColumn<VBuffer<ReadOnlyMemory<char>>>(ml, "RemovedWords");
+            var customizeRemoverData = transformedDataCustomized.GetColumn<VBuffer<ReadOnlyMemory<char>>>(transformedDataCustomized.Schema["RemovedWords"]);
             printHelper("RemovedWords", customizeRemoverData);
 
             // Best|game|I've|ever|played.|

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

@@ -58,7 +58,7 @@ public static void Example()
             };
 
             // Preview of the DefaultTextFeatures column obtained after processing the input.
-            var defaultColumn = transformedData_default.GetColumn<VBuffer<float>>(ml, defaultColumnName);
+            var defaultColumn = transformedData_default.GetColumn<VBuffer<float>>(transformedData_default.Schema[defaultColumnName]);
             printHelper(defaultColumnName, defaultColumn);
 
             // DefaultTextFeatures column obtained post-transformation.
@@ -68,7 +68,7 @@ public static void Example()
             // 0 0.1230915 0.1230915 0.1230915 0.1230915 0.246183 0.246183 0.246183 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 0 0.1230915 0 0 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.3692745 0.246183 0.246183 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.246183 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.1230915 0.2886751 0 0 0 0 0 0 0 0.2886751 0.5773503 0.2886751 0.2886751 0.2886751 0.2886751 0.2886751 0.2886751
 
             // Preview of the CustomizedTextFeatures column obtained after processing the input.
-            var customizedColumn = transformedData_customized.GetColumn<VBuffer<float>>(ml, customizedColumnName);
+            var customizedColumn = transformedData_customized.GetColumn<VBuffer<float>>(transformedData_customized.Schema[customizedColumnName]);
             printHelper(customizedColumnName, customizedColumn);
 
             // CustomizedTextFeatures column obtained post-transformation.

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/FieldAwareFactorizationMachinewWithOptions.cs

@@ -32,8 +32,8 @@ public static void Example()
                     FieldAwareFactorizationMachine(
                         new FieldAwareFactorizationMachineBinaryClassificationTrainer.Options
                         {
-                            FeatureColumn = "Features",
-                            LabelColumn = "Sentiment",
+                            FeatureColumnName = "Features",
+                            LabelColumnName = "Sentiment",
                             LearningRate = 0.1f,
                             NumberOfIterations = 10
                         }));

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/SDCALogisticRegression.cs

@@ -62,8 +62,8 @@ public static void Example()
             var advancedPipeline = mlContext.Transforms.Text.FeaturizeText("SentimentText", "Features")
                                   .Append(mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscent(
                                       new SdcaBinaryTrainer.Options { 
-                                        LabelColumn = "Sentiment",
-                                        FeatureColumn = "Features",
+                                        LabelColumnName = "Sentiment",
+                                        FeatureColumnName = "Features",
                                         ConvergenceTolerance = 0.01f,  // The learning rate for adjusting bias from being regularized
                                         NumThreads = 2, // Degree of lock-free parallelism 
                                       }));

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/LightGbm.cs

@@ -49,7 +49,7 @@ public static void Example()
             var metrics = mlContext.MulticlassClassification.Evaluate(dataWithPredictions, label: "LabelIndex");
 
             // Check if metrics are reasonable.
-            Console.WriteLine($"Macro accuracy: {metrics.AccuracyMacro:F4}, Micro accuracy: {metrics.AccuracyMicro:F4}.");
+            Console.WriteLine($"Macro accuracy: {metrics.MacroAccuracy:F4}, Micro accuracy: {metrics.MicroAccuracy:F4}.");
             // Console output:
             //   Macro accuracy: 0.8655, Micro accuracy: 0.8651.