Documentation for BinaryClassification.AveragedPerceptron

Microsoft.ML.sln

@@ -33,6 +33,8 @@ Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.TestFramework"
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.Predictor.Tests", "test\Microsoft.ML.Predictor.Tests\Microsoft.ML.Predictor.Tests.csproj", "{6B047E09-39C9-4583-96F3-685D84CA4117}"
 EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.Functional.Tests", "test\Microsoft.ML.Functional.Tests\Microsoft.ML.Functional.Tests.csproj", "{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}"
+EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.ResultProcessor", "src\Microsoft.ML.ResultProcessor\Microsoft.ML.ResultProcessor.csproj", "{3769FCC3-9AFF-4C37-97E9-6854324681DF}"
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.FastTree", "src\Microsoft.ML.FastTree\Microsoft.ML.FastTree.csproj", "{B7B593C5-FB8C-4ADA-A638-5B53B47D087E}"
@@ -928,6 +930,18 @@ Global
 		{5E920CAC-5A28-42FB-936E-49C472130953}.Release-Intrinsics|Any CPU.Build.0 = Release-Intrinsics|Any CPU
 		{5E920CAC-5A28-42FB-936E-49C472130953}.Release-netfx|Any CPU.ActiveCfg = Release-netfx|Any CPU
 		{5E920CAC-5A28-42FB-936E-49C472130953}.Release-netfx|Any CPU.Build.0 = Release-netfx|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Debug-Intrinsics|Any CPU.ActiveCfg = Debug-Intrinsics|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Debug-Intrinsics|Any CPU.Build.0 = Debug-Intrinsics|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Debug-netfx|Any CPU.ActiveCfg = Debug-netfx|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Debug-netfx|Any CPU.Build.0 = Debug-netfx|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Release|Any CPU.Build.0 = Release|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Release-Intrinsics|Any CPU.ActiveCfg = Release-Intrinsics|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Release-Intrinsics|Any CPU.Build.0 = Release-Intrinsics|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Release-netfx|Any CPU.ActiveCfg = Release-netfx|Any CPU
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5}.Release-netfx|Any CPU.Build.0 = Release-netfx|Any CPU
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE
@@ -1011,6 +1025,7 @@ Global
 		{85D0CAFD-2FE8-496A-88C7-585D35B94243} = {09EADF06-BE25-4228-AB53-95AE3E15B530}
 		{31D38B21-102B-41C0-9E0A-2FE0BF68D123} = {D3D38B03-B557-484D-8348-8BADEE4DF592}
 		{5E920CAC-5A28-42FB-936E-49C472130953} = {AED9C836-31E3-4F3F-8ABC-929555D3F3C4}
+		{CFED9F0C-FF81-4C96-8D5E-0436264CA7B5} = {AED9C836-31E3-4F3F-8ABC-929555D3F3C4}
 	EndGlobalSection
 	GlobalSection(ExtensibilityGlobals) = postSolution
 		SolutionGuid = {41165AF1-35BB-4832-A189-73060F82B01D}

build/Dependencies.props

@@ -43,6 +43,8 @@
   <PropertyGroup>
     <BenchmarkDotNetVersion>0.11.3</BenchmarkDotNetVersion>
     <MicrosoftMLTestModelsPackageVersion>0.0.3-test</MicrosoftMLTestModelsPackageVersion>
+    <MicrosoftMLTensorFlowTestModelsVersion>0.0.10-test</MicrosoftMLTensorFlowTestModelsVersion>
+    <MicrosoftMLOnnxTestModelsVersion>0.0.4-test</MicrosoftMLOnnxTestModelsVersion>
   </PropertyGroup>
 
 </Project>

docs/code/MlNetCookBook.md

@@ -688,11 +688,11 @@ var catColumns = data.GetColumn<string[]>(mlContext, "CategoricalFeatures").Take
 // Build several alternative featurization pipelines.
 var pipeline =
     // Convert each categorical feature into one-hot encoding independently.
-    mlContext.Transforms.Categorical.OneHotEncoding("CategoricalFeatures", "CategoricalOneHot")
+    mlContext.Transforms.Categorical.OneHotEncoding("CategoricalOneHot", "CategoricalFeatures")
     // Convert all categorical features into indices, and build a 'word bag' of these.
-    .Append(mlContext.Transforms.Categorical.OneHotEncoding("CategoricalFeatures", "CategoricalBag", CategoricalTransform.OutputKind.Bag))
+    .Append(mlContext.Transforms.Categorical.OneHotEncoding("CategoricalBag", "CategoricalFeatures", CategoricalTransform.OutputKind.Bag))
     // One-hot encode the workclass column, then drop all the categories that have fewer than 10 instances in the train set.
-    .Append(mlContext.Transforms.Categorical.OneHotEncoding("Workclass", "WorkclassOneHot"))
+    .Append(mlContext.Transforms.Categorical.OneHotEncoding("WorkclassOneHot", "Workclass"))
     .Append(mlContext.Transforms.FeatureSelection.CountFeatureSelectingEstimator("WorkclassOneHot", "WorkclassOneHotTrimmed", count: 10));
 
 // Let's train our pipeline, and then apply it to the same data.
@@ -825,20 +825,20 @@ var pipeline =
     .Append(mlContext.MulticlassClassification.Trainers.StochasticDualCoordinateAscent());
 
 // Split the data 90:10 into train and test sets, train and evaluate.
-var (trainData, testData) = mlContext.MulticlassClassification.TrainTestSplit(data, testFraction: 0.1);
+var split = mlContext.MulticlassClassification.TrainTestSplit(data, testFraction: 0.1);
 
 // Train the model.
-var model = pipeline.Fit(trainData);
+var model = pipeline.Fit(split.TrainSet);
 // Compute quality metrics on the test set.
-var metrics = mlContext.MulticlassClassification.Evaluate(model.Transform(testData));
+var metrics = mlContext.MulticlassClassification.Evaluate(model.Transform(split.TestSet));
 Console.WriteLine(metrics.AccuracyMicro);
 
 // Now run the 5-fold cross-validation experiment, using the same pipeline.
 var cvResults = mlContext.MulticlassClassification.CrossValidate(data, pipeline, numFolds: 5);
 
 // The results object is an array of 5 elements. For each of the 5 folds, we have metrics, model and scored test data.
 // Let's compute the average micro-accuracy.
-var microAccuracies = cvResults.Select(r => r.metrics.AccuracyMicro);
+var microAccuracies = cvResults.Select(r => r.Metrics.AccuracyMicro);
 Console.WriteLine(microAccuracies.Average());
 
 ```

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

@@ -43,7 +43,7 @@ public static void Calibration()
             var data = reader.Read(dataFile);
 
             // Split the dataset into two parts: one used for training, the other to train the calibrator
-            var (trainData, calibratorTrainingData) = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var split = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
 
             // Featurize the text column through the FeaturizeText API. 
             // Then append the StochasticDualCoordinateAscentBinary binary classifier, setting the "Label" column as the label of the dataset, and 
@@ -56,12 +56,12 @@ public static void Calibration()
                         loss: new HingeLoss())); // By specifying loss: new HingeLoss(), StochasticDualCoordinateAscent will train a support vector machine (SVM).
 
             // Fit the pipeline, and get a transformer that knows how to score new data.  
-            var transformer = pipeline.Fit(trainData);
+            var transformer = pipeline.Fit(split.TrainSet);
             IPredictor model = transformer.LastTransformer.Model;
 
             // Let's score the new data. The score will give us a numerical estimation of the chance that the particular sample 
             // bears positive sentiment. This estimate is relative to the numbers obtained. 
-            var scoredData = transformer.Transform(calibratorTrainingData);
+            var scoredData = transformer.Transform(split.TestSet);
             var scoredDataPreview = scoredData.Preview();
 
             PrintRowViewValues(scoredDataPreview);

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

@@ -5,11 +5,9 @@
 using System;
 using System.Collections.Generic;
 using System.IO;
-using System.Linq;
 using Microsoft.ML.Core.Data;
 using Microsoft.ML.Data;
-using Microsoft.ML.TimeSeries;
-using Microsoft.ML.TimeSeriesProcessing;
+using Microsoft.ML.Transforms.TimeSeries;
 
 namespace Microsoft.ML.Samples.Dynamic
 {
@@ -54,16 +52,9 @@ public static void IidChangePointDetectorTransform()
             // Setup IidSpikeDetector arguments
             string outputColumnName = nameof(ChangePointPrediction.Prediction);
             string inputColumnName = nameof(IidChangePointData.Value);
-            var args = new IidChangePointDetector.Arguments()
-            {
-                Source = inputColumnName,
-                Name = outputColumnName,
-                Confidence = 95,                // The confidence for spike detection in the range [0, 100]
-                ChangeHistoryLength = Size / 4, // The length of the sliding window on p-values for computing the martingale score. 
-            };
 
             // The transformed data.
-            var transformedData = new IidChangePointEstimator(ml, args).Fit(dataView).Transform(dataView);
+            var transformedData = ml.Transforms.IidChangePointEstimator(outputColumnName, inputColumnName, 95, Size / 4).Fit(dataView).Transform(dataView);
 
             // Getting the data of the newly created column as an IEnumerable of ChangePointPrediction.
             var predictionColumn = ml.CreateEnumerable<ChangePointPrediction>(transformedData, reuseRowObject: false);
@@ -119,16 +110,9 @@ public static void IidChangePointDetectorPrediction()
             // Setup IidSpikeDetector arguments
             string outputColumnName = nameof(ChangePointPrediction.Prediction);
             string inputColumnName = nameof(IidChangePointData.Value);
-            var args = new IidChangePointDetector.Arguments()
-            {
-                Source = inputColumnName,
-                Name = outputColumnName,
-                Confidence = 95,                // The confidence for spike detection in the range [0, 100]
-                ChangeHistoryLength = Size / 4, // The length of the sliding window on p-values for computing the martingale score. 
-            };
 
             // Time Series model.
-            ITransformer model = new IidChangePointEstimator(ml, args).Fit(dataView);
+            ITransformer model = ml.Transforms.IidChangePointEstimator(outputColumnName, inputColumnName, 95, Size / 4).Fit(dataView);
 
             // Create a time series prediction engine from the model.
             var engine = model.CreateTimeSeriesPredictionFunction<IidChangePointData, ChangePointPrediction>(ml);

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

@@ -1,11 +1,9 @@
 using System;
 using System.Collections.Generic;
 using System.IO;
-using System.Linq;
 using Microsoft.ML.Core.Data;
 using Microsoft.ML.Data;
-using Microsoft.ML.TimeSeries;
-using Microsoft.ML.TimeSeriesProcessing;
+using Microsoft.ML.Transforms.TimeSeries;
 
 namespace Microsoft.ML.Samples.Dynamic
 {
@@ -51,16 +49,9 @@ public static void IidSpikeDetectorTransform()
             // Setup IidSpikeDetector arguments
             string outputColumnName = nameof(IidSpikePrediction.Prediction);
             string inputColumnName = nameof(IidSpikeData.Value);
-            var args = new IidSpikeDetector.Arguments()
-            {
-                Source = inputColumnName,
-                Name = outputColumnName,
-                Confidence = 95,                // The confidence for spike detection in the range [0, 100]
-                PvalueHistoryLength = Size / 4  // The size of the sliding window for computing the p-value; shorter windows are more sensitive to spikes.
-            };
 
             // The transformed data.
-            var transformedData = new IidSpikeEstimator(ml, args).Fit(dataView).Transform(dataView);
+            var transformedData = ml.Transforms.IidSpikeEstimator(outputColumnName, inputColumnName, 95, Size / 4).Fit(dataView).Transform(dataView);
 
             // Getting the data of the newly created column as an IEnumerable of IidSpikePrediction.
             var predictionColumn = ml.CreateEnumerable<IidSpikePrediction>(transformedData, reuseRowObject: false);
@@ -108,16 +99,8 @@ public static void IidSpikeDetectorPrediction()
             // Setup IidSpikeDetector arguments
             string outputColumnName = nameof(IidSpikePrediction.Prediction);
             string inputColumnName = nameof(IidSpikeData.Value);
-            var args = new IidSpikeDetector.Arguments()
-            {
-                Source = inputColumnName,
-                Name = outputColumnName,
-                Confidence = 95,                // The confidence for spike detection in the range [0, 100]
-                PvalueHistoryLength = Size / 4  // The size of the sliding window for computing the p-value; shorter windows are more sensitive to spikes.
-            };
-
             // The transformed model.
-            ITransformer model = new IidSpikeEstimator(ml, args).Fit(dataView);
+            ITransformer model = ml.Transforms.IidChangePointEstimator(outputColumnName, inputColumnName, 95, Size).Fit(dataView);
 
             // Create a time series prediction engine from the model.
             var engine = model.CreateTimeSeriesPredictionFunction<IidSpikeData, IidSpikePrediction>(ml);

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

@@ -57,7 +57,7 @@ public static void LogisticRegression()
 
             IDataView data = reader.Read(dataFilePath);
 
-            var (trainData, testData) = ml.BinaryClassification.TrainTestSplit(data, testFraction: 0.2);
+            var split = ml.BinaryClassification.TrainTestSplit(data, testFraction: 0.2);
 
             var pipeline = ml.Transforms.Concatenate("Text", "workclass", "education", "marital-status",
                     "relationship", "ethnicity", "sex", "native-country")
@@ -66,9 +66,9 @@ public static void LogisticRegression()
                     "education-num", "capital-gain", "capital-loss", "hours-per-week"))
                 .Append(ml.BinaryClassification.Trainers.LogisticRegression());
 
-            var model = pipeline.Fit(trainData);
+            var model = pipeline.Fit(split.TrainSet);
 
-            var dataWithPredictions = model.Transform(testData);
+            var dataWithPredictions = model.Transform(split.TestSet);
 
             var metrics = ml.BinaryClassification.Evaluate(dataWithPredictions);
 

docs/samples/Microsoft.ML.Samples/Dynamic/PermutationFeatureImportance/PFIHelper.cs

@@ -1,7 +1,8 @@
 using System;
 using System.Linq;
 using Microsoft.Data.DataView;
-using Microsoft.ML.Learners;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
 using Microsoft.ML.SamplesUtils;
 using Microsoft.ML.Trainers.HalLearners;
 

docs/samples/Microsoft.ML.Samples/Dynamic/PermutationFeatureImportance/PfiBinaryClassificationExample.cs

@@ -1,6 +1,6 @@
 using System;
 using System.Linq;
-using Microsoft.ML.Learners;
+using Microsoft.ML.Trainers;
 
 namespace Microsoft.ML.Samples.Dynamic.PermutationFeatureImportance
 {

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

@@ -54,7 +54,7 @@ public static void SDCA_BinaryClassification()
             // Step 3: Run Cross-Validation on this pipeline.
             var cvResults = mlContext.BinaryClassification.CrossValidate(data, pipeline, labelColumn: "Sentiment");
 
-            var accuracies = cvResults.Select(r => r.metrics.Accuracy);
+            var accuracies = cvResults.Select(r => r.Metrics.Accuracy);
             Console.WriteLine(accuracies.Average());
 
             // If we wanted to specify more advanced parameters for the algorithm, 
@@ -70,7 +70,7 @@ public static void SDCA_BinaryClassification()
 
             // Run Cross-Validation on this second pipeline.
             var cvResults_advancedPipeline = mlContext.BinaryClassification.CrossValidate(data, pipeline, labelColumn: "Sentiment", numFolds: 3);
-            accuracies = cvResults_advancedPipeline.Select(r => r.metrics.Accuracy);
+            accuracies = cvResults_advancedPipeline.Select(r => r.Metrics.Accuracy);
             Console.WriteLine(accuracies.Average());
 
         }

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

@@ -1,11 +1,9 @@
 using System;
 using System.Collections.Generic;
 using System.IO;
-using System.Linq;
 using Microsoft.ML.Core.Data;
 using Microsoft.ML.Data;
-using Microsoft.ML.TimeSeries;
-using Microsoft.ML.TimeSeriesProcessing;
+using Microsoft.ML.Transforms.TimeSeries;
 
 namespace Microsoft.ML.Samples.Dynamic
 {
@@ -49,19 +47,9 @@ public static void SsaChangePointDetectorTransform()
             // Setup SsaChangePointDetector arguments
             var inputColumnName = nameof(SsaChangePointData.Value);
             var outputColumnName = nameof(ChangePointPrediction.Prediction);
-            var args = new SsaChangePointDetector.Arguments()
-            {
-                Source = inputColumnName,
-                Name = outputColumnName,
-                Confidence = 95,                          // The confidence for spike detection in the range [0, 100]
-                ChangeHistoryLength = 8,                  // The length of the window for detecting a change in trend; shorter windows are more sensitive to spikes.
-                TrainingWindowSize = TrainingSize,        // The number of points from the beginning of the sequence used for training.
-                SeasonalWindowSize = SeasonalitySize + 1  // An upper bound on the largest relevant seasonality in the input time series."
-
-            };
 
             // The transformed data.
-            var transformedData = new SsaChangePointEstimator(ml, args).Fit(dataView).Transform(dataView);
+            var transformedData = ml.Transforms.SsaChangePointEstimator(outputColumnName, inputColumnName, 95, 8, TrainingSize, SeasonalitySize + 1).Fit(dataView).Transform(dataView);
 
             // Getting the data of the newly created column as an IEnumerable of ChangePointPrediction.
             var predictionColumn = ml.CreateEnumerable<ChangePointPrediction>(transformedData, reuseRowObject: false);
@@ -120,19 +108,9 @@ public static void SsaChangePointDetectorPrediction()
             // Setup SsaChangePointDetector arguments
             var inputColumnName = nameof(SsaChangePointData.Value);
             var outputColumnName = nameof(ChangePointPrediction.Prediction);
-            var args = new SsaChangePointDetector.Arguments()
-            {
-                Source = inputColumnName,
-                Name = outputColumnName,
-                Confidence = 95,                         // The confidence for spike detection in the range [0, 100]
-                ChangeHistoryLength = 8,                 // The length of the window for detecting a change in trend; shorter windows are more sensitive to spikes. 
-                TrainingWindowSize = TrainingSize,       // The number of points from the beginning of the sequence used for training.
-                SeasonalWindowSize = SeasonalitySize + 1 // An upper bound on the largest relevant seasonality in the input time series."
-
-            };
 
             // Train the change point detector.
-            ITransformer model = new SsaChangePointEstimator(ml, args).Fit(dataView);
+            ITransformer model = ml.Transforms.SsaChangePointEstimator(outputColumnName, inputColumnName, 95, 8, TrainingSize, SeasonalitySize + 1).Fit(dataView);
 
             // Create a prediction engine from the model for feeding new data.
             var engine = model.CreateTimeSeriesPredictionFunction<SsaChangePointData, ChangePointPrediction>(ml);