ML.NET 2.0 Samples (#967)

* Initial commit AutoML samples

* Add text classification

* Add sentence similarity

* Add placeholder directory for data files

* Update TrialRunner to use Text Classification

* All samples verified to work. Data paths updated.

* Minor updates

* Add Text classification razor MB tutorial sample

* Updated READMEs

.gitignore

@@ -331,3 +331,7 @@ ASALocalRun/
 samples/modelbuilder/ObjectDetection_StopSigns/StopSignDetectionML.Model/MLModel.zip
 samples/modelbuilder/ObjectDetection_StopSigns/StopSignDetectionML.Model/bestModel.onnx
 samples/modelbuilder/ObjectDetection_StopSigns/assets.zip
+samples/csharp/getting-started/MLNET2/Data/*.csv
+samples/csharp/getting-started/MLNET2/Data/*.txt
+samples/csharp/getting-started/MLNET2/**/*.mbconfig
+samples/modelbuilder/TextClassification_Sentiment_Razor/SentimentRazor/**/*.mbconfig

README.md

@@ -151,6 +151,8 @@ The ML.NET CLI (command-line interface) is a tool you can run on any command-pro
 
 ## AutoML API samples: (Preview state)
 
+**THESE SAMPLES USE THE 0.1.x VERSION OF THE AUTOML API. WHILE THESE APIS STILL WORK IN VERSION 0.2.x WE RECOMMEND USING THE NEW APIS INTRODUCED IN 0.2.x AND LATER. FOR 0.2.x SAMPLES, SEE [ML.NET 2.0 Samples](samples/csharp/getting-started/MLNET2/README.md)**. 
+
 ML.NET AutoML API is basically a set of libraries packaged as a NuGet package you can use from your .NET code. AutoML eliminates the task of selecting different algorithms, hyperparameters. AutoML will intelligently generate many combinations of algorithms and hyperparameters and will find high quality models for you.
 
 | AutoML API samples                    |

samples/csharp/getting-started/MLNET2/AutoMLAdvanced/AutoMLAdvanced.csproj

@@ -0,0 +1,14 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net6.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.ML.AutoML" Version="0.20.0" />
+  </ItemGroup>
+
+</Project>

samples/csharp/getting-started/MLNET2/AutoMLAdvanced/AutoMLMonitor.cs

@@ -0,0 +1,46 @@
+using Microsoft.ML.AutoML;
+
+namespace AutoMLAdvanced
+{
+    public class AutoMLMonitor : IMonitor
+    {
+        private readonly SweepablePipeline _pipeline;
+        private readonly List<TrialResult> _completedTrials;
+
+        public AutoMLMonitor(SweepablePipeline pipeline)
+        {
+            _pipeline = pipeline;
+            _completedTrials = new List<TrialResult>();
+        }
+
+        public IEnumerable<TrialResult> GetCompletedTrials() => _completedTrials;
+
+        public void ReportBestTrial(TrialResult result)
+        {
+            return;
+        }
+
+        public void ReportCompletedTrial(TrialResult result)
+        {
+            var trialId = result.TrialSettings.TrialId;
+            var timeToTrain = result.DurationInMilliseconds;
+            var pipeline = _pipeline.ToString(result.TrialSettings.Parameter);
+            Console.WriteLine($"Trial {trialId} finished training in {timeToTrain}ms with pipeline {pipeline}");
+            _completedTrials.Add(result);
+        }
+
+        public void ReportFailTrial(TrialSettings settings, Exception exception = null)
+        {
+            if (exception.Message.Contains("Operation was canceled."))
+            {
+                Console.WriteLine($"{settings.TrialId} cancelled. Time budget exceeded.");
+            }
+            Console.WriteLine($"{settings.TrialId} failed with exception {exception.Message}");
+        }
+
+        public void ReportRunningTrial(TrialSettings setting)
+        {
+            return;
+        }
+    }
+}

samples/csharp/getting-started/MLNET2/AutoMLAdvanced/Program.cs

@@ -0,0 +1,62 @@
+// Initialize MLContext
+using AutoMLAdvanced;
+using Microsoft.ML;
+using Microsoft.ML.AutoML;
+using Microsoft.ML.Data;
+using static Microsoft.ML.DataOperationsCatalog;
+
+// Initialize MLContext
+MLContext ctx = new MLContext();
+
+var dataPath = Path.GetFullPath(@"..\..\..\..\Data\taxi-fare-train.csv");
+
+// Infer column information
+ColumnInferenceResults columnInference =
+    ctx.Auto().InferColumns(dataPath, labelColumnName: "fare_amount", groupColumns: false);
+
+// Modify column inference results
+columnInference.ColumnInformation.NumericColumnNames.Remove("rate_code");
+columnInference.ColumnInformation.CategoricalColumnNames.Add("rate_code");
+
+// Create text loader
+TextLoader loader = ctx.Data.CreateTextLoader(columnInference.TextLoaderOptions);
+
+// Load data into IDataView
+IDataView data = loader.Load(dataPath);
+
+// Split into train (80%), validation (20%) sets
+TrainTestData trainValidationData = ctx.Data.TrainTestSplit(data, testFraction: 0.2);
+
+//Define pipeline
+SweepablePipeline pipeline =
+    ctx.Auto().Featurizer(data, columnInformation: columnInference.ColumnInformation)
+        .Append(ctx.Auto().Regression(labelColumnName: columnInference.ColumnInformation.LabelColumnName, useLgbm:false));
+
+// Create AutoML experiment
+AutoMLExperiment experiment = ctx.Auto().CreateExperiment();
+
+// Configure experiment
+experiment
+    .SetPipeline(pipeline)
+    .SetRegressionMetric(RegressionMetric.RSquared, labelColumn: columnInference.ColumnInformation.LabelColumnName)
+    .SetTrainingTimeInSeconds(60)
+    .SetGridSearchTuner()
+    .SetDataset(trainValidationData);
+
+// Log experiment trials
+var monitor = new AutoMLMonitor(pipeline);
+experiment.SetMonitor(monitor);
+
+// Set checkpoints
+var checkpointPath = Path.Join(Directory.GetCurrentDirectory(), "automl");
+experiment.SetCheckpoint(checkpointPath);
+
+// Run experiment
+var cts = new CancellationTokenSource();
+TrialResult experimentResults = await experiment.RunAsync(cts.Token);
+
+// Get best model
+var model = experimentResults.Model;
+
+// Get all completed trials
+var completedTrials = monitor.GetCompletedTrials();

samples/csharp/getting-started/MLNET2/AutoMLEstimators/AutoMLEstimators.csproj

@@ -0,0 +1,14 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net6.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.ML.AutoML" Version="0.20.0" />
+  </ItemGroup>
+
+</Project>

samples/csharp/getting-started/MLNET2/AutoMLEstimators/AutoMLMonitor.cs

@@ -0,0 +1,46 @@
+using Microsoft.ML.AutoML;
+
+namespace AutoMLAdvanced
+{
+    public class AutoMLMonitor : IMonitor
+    {
+        private readonly SweepablePipeline _pipeline;
+        private readonly List<TrialResult> _completedTrials;
+
+        public AutoMLMonitor(SweepablePipeline pipeline)
+        {
+            _pipeline = pipeline;
+            _completedTrials = new List<TrialResult>();
+        }
+
+        public IEnumerable<TrialResult> GetCompletedTrials() => _completedTrials;
+
+        public void ReportBestTrial(TrialResult result)
+        {
+            return;
+        }
+
+        public void ReportCompletedTrial(TrialResult result)
+        {
+            var trialId = result.TrialSettings.TrialId;
+            var timeToTrain = result.DurationInMilliseconds;
+            var pipeline = _pipeline.ToString(result.TrialSettings.Parameter);
+            Console.WriteLine($"Trial {trialId} finished training in {timeToTrain}ms with pipeline {pipeline}");
+            _completedTrials.Add(result);
+        }
+
+        public void ReportFailTrial(TrialSettings settings, Exception exception = null)
+        {
+            if (exception.Message.Contains("Operation was canceled."))
+            {
+                Console.WriteLine($"{settings.TrialId} cancelled. Time budget exceeded.");
+            }
+            Console.WriteLine($"{settings.TrialId} failed with exception {exception.Message}");
+        }
+
+        public void ReportRunningTrial(TrialSettings setting)
+        {
+            return;
+        }
+    }
+}

samples/csharp/getting-started/MLNET2/AutoMLEstimators/Program.cs

@@ -0,0 +1,75 @@
+// Initialize MLContext
+using AutoMLAdvanced;
+using Microsoft.ML;
+using Microsoft.ML.AutoML;
+using Microsoft.ML.AutoML.CodeGen;
+using Microsoft.ML.Data;
+using Microsoft.ML.SearchSpace;
+using Microsoft.ML.SearchSpace.Option;
+using Microsoft.ML.Trainers;
+using static Microsoft.ML.DataOperationsCatalog;
+
+// Initialize MLContext
+MLContext ctx = new MLContext();
+
+var dataPath = Path.GetFullPath(@"..\..\..\..\Data\taxi-fare-train.csv");
+
+// Infer column information
+ColumnInferenceResults columnInference =
+    ctx.Auto().InferColumns(dataPath, labelColumnName: "fare_amount", groupColumns: false);
+
+// Create text loader
+TextLoader loader = ctx.Data.CreateTextLoader(columnInference.TextLoaderOptions);
+
+// Load data into IDataView
+IDataView data = loader.Load(dataPath);
+
+// Split into train (80%), validation (20%) sets
+TrainTestData trainValidationData = ctx.Data.TrainTestSplit(data, testFraction: 0.2);
+
+// Initialize default Scda search space
+var sdcaSearchSpace = new SearchSpace<SdcaOption>();
+
+// Modify L1 search space range
+sdcaSearchSpace["L1Regularization"] = new UniformSingleOption(min: 0.01f, max: 2.0f, logBase: false, defaultValue: 0.01f);
+
+// Use the search space to define a custom factory to create an SdcaRegressionTrainer
+var sdcaFactory = (MLContext ctx, SdcaOption param) =>
+{
+    var sdcaOption = new SdcaRegressionTrainer.Options();
+    sdcaOption.L1Regularization = param.L1Regularization;
+    sdcaOption.L2Regularization = 0.02f;
+
+    sdcaOption.LabelColumnName = columnInference.ColumnInformation.LabelColumnName;
+
+    return ctx.Regression.Trainers.Sdca(sdcaOption);
+};
+
+// Define Sdca sweepable estimator (SdcaRegressionTrainer + SdcaOption search space)
+var sdcaSweepableEstimator = ctx.Auto().CreateSweepableEstimator(sdcaFactory, sdcaSearchSpace);
+
+// Add sweepable estimator to sweepable pipeline
+SweepablePipeline pipeline =
+    ctx.Auto().Featurizer(data, columnInformation: columnInference.ColumnInformation)
+        .Append(sdcaSweepableEstimator);
+
+// Create AutoML experiment
+AutoMLExperiment experiment = ctx.Auto().CreateExperiment();
+
+// Configure experiment
+experiment
+    .SetPipeline(pipeline)
+    .SetRegressionMetric(RegressionMetric.RSquared, labelColumn: columnInference.ColumnInformation.LabelColumnName)
+    .SetTrainingTimeInSeconds(60)
+    .SetDataset(trainValidationData);
+
+// Log experiment trials
+var monitor = new AutoMLMonitor(pipeline);
+experiment.SetMonitor(monitor);
+
+// Run experiment
+var cts = new CancellationTokenSource();
+TrialResult experimentResults = await experiment.RunAsync(cts.Token);
+
+// Get best model
+var model = experimentResults.Model;

samples/csharp/getting-started/MLNET2/AutoMLQuickStart/AutoMLQuickStart.csproj

@@ -0,0 +1,14 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net6.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.ML.AutoML" Version="0.20.0" />
+  </ItemGroup>
+
+</Project>

samples/csharp/getting-started/MLNET2/AutoMLQuickStart/Program.cs

@@ -0,0 +1,53 @@
+// Initialize MLContext
+using Microsoft.ML;
+using Microsoft.ML.AutoML;
+using Microsoft.ML.Data;
+using static Microsoft.ML.DataOperationsCatalog;
+
+// Initialize MLContext
+MLContext ctx = new MLContext();
+
+// Define data path
+var dataPath = Path.GetFullPath(@"..\..\..\..\Data\taxi-fare-train.csv");
+
+// Infer column information
+ColumnInferenceResults columnInference =
+    ctx.Auto().InferColumns(dataPath, labelColumnName: "fare_amount", groupColumns: false);
+
+// Create text loader
+TextLoader loader = ctx.Data.CreateTextLoader(columnInference.TextLoaderOptions);
+
+// Load data into IDataView
+IDataView data = loader.Load(dataPath);
+
+// Split into train (80%), validation (20%) sets
+TrainTestData trainValidationData = ctx.Data.TrainTestSplit(data, testFraction: 0.2);
+
+//Define pipeline
+SweepablePipeline pipeline =
+    ctx.Auto().Featurizer(data, columnInformation: columnInference.ColumnInformation)
+        .Append(ctx.Auto().Regression(labelColumnName: columnInference.ColumnInformation.LabelColumnName));
+
+// Create AutoML experiment
+AutoMLExperiment experiment = ctx.Auto().CreateExperiment();
+
+// Configure experiment
+experiment
+    .SetPipeline(pipeline)
+    .SetRegressionMetric(RegressionMetric.RSquared, labelColumn: columnInference.ColumnInformation.LabelColumnName)
+    .SetTrainingTimeInSeconds(60)
+    .SetDataset(trainValidationData);
+
+// Log experiment trials
+ctx.Log += (_, e) => {
+    if (e.Source.Equals("AutoMLExperiment"))
+    {
+        Console.WriteLine(e.RawMessage);
+    }
+};
+
+// Run experiment
+TrialResult experimentResults = await experiment.RunAsync();
+
+// Get best model
+var model = experimentResults.Model;