Simplify CodeGen - phase 2

src/Microsoft.ML.CodeGenerator/CodeGenerator/CSharp/AzureCodeGenerator/AzureAttachConsoleAppCodeGenerator.cs

@@ -79,8 +79,6 @@ public AzureAttachConsoleAppCodeGenerator(Pipeline pipeline, ColumnInferenceResu
                 Name = $"{_settings.OutputName}.ConsoleApp.csproj",
             };
 
-            var columns = _columnInferenceResult.TextLoaderOptions.Columns;
-            var featuresList = columns.Where((str) => str.Name != _settings.LabelName).Select((str) => str.Name).ToList();
             var sampleResult = Utils.GenerateSampleData(_settings.TrainDataset, _columnInferenceResult);
             PredictProgram = new CSharpCodeFile()
             {
@@ -94,7 +92,6 @@ public AzureAttachConsoleAppCodeGenerator(Pipeline pipeline, ColumnInferenceResu
                     HasHeader = _columnInferenceResult.TextLoaderOptions.HasHeader,
                     Separator = _columnInferenceResult.TextLoaderOptions.Separators.FirstOrDefault(),
                     Target = _settings.Target,
-                    Features = featuresList,
                     SampleData = sampleResult,
                 }.TransformText(),
                 Name = "Program.cs",

src/Microsoft.ML.CodeGenerator/CodeGenerator/CSharp/CodeGenerator.cs

@@ -432,8 +432,6 @@ private static string GeneratPredictProjectFileContent(string namespaceValue, bo
 
         private string GeneratePredictProgramCSFileContent(string namespaceValue)
         {
-            var columns = _columnInferenceResult.TextLoaderOptions.Columns;
-            var featuresList = columns.Where((str) => str.Name != _settings.LabelName).Select((str) => str.Name).ToList();
             var sampleData = Utils.GenerateSampleData(_settings.TrainDataset, _columnInferenceResult);
             PredictProgram predictProgram = new PredictProgram()
             {
@@ -444,7 +442,6 @@ private string GeneratePredictProgramCSFileContent(string namespaceValue)
                 Separator = _columnInferenceResult.TextLoaderOptions.Separators.FirstOrDefault(),
                 AllowQuoting = _columnInferenceResult.TextLoaderOptions.AllowQuoting,
                 AllowSparse = _columnInferenceResult.TextLoaderOptions.AllowSparse,
-                Features = featuresList,
                 Target = _settings.Target,
                 SampleData = sampleData,
             };

src/Microsoft.ML.CodeGenerator/Templates/Console/ModelBuilder.cs

@@ -87,21 +87,24 @@ public static void CreateModel()
             this.Write(this.ToStringHelper.ToStringWithCulture(AllowSparse.ToString().ToLowerInvariant()));
             this.Write(");\r\n");
 }
-            this.Write("            // Build training pipeline\r\n            IEstimator<ITransformer> trai" +
-                    "ningPipeline = BuildTrainingPipeline(mlContext);\r\n\r\n");
+            this.Write(@"            // Build training pipeline
+            IEstimator<ITransformer> trainingPipeline = BuildTrainingPipeline(mlContext);
+
+            // Train Model
+            ITransformer mlModel = TrainModel(mlContext, trainingDataView, trainingPipeline);
+
+");
  if(string.IsNullOrEmpty(TestPath) && !HasOnnxModel){ 
             this.Write("            // Evaluate quality of Model\r\n            Evaluate(mlContext, trainin" +
                     "gDataView, trainingPipeline);\r\n\r\n");
 }
-            this.Write("            // Train Model\r\n            ITransformer mlModel = TrainModel(mlConte" +
-                    "xt, trainingDataView, trainingPipeline);\r\n");
  if(!string.IsNullOrEmpty(TestPath) && !HasOnnxModel){ 
-            this.Write("\r\n            // Evaluate quality of Model\r\n            EvaluateModel(mlContext, " +
-                    "mlModel, testDataView);\r\n");
+            this.Write("            // Evaluate quality of Model\r\n            EvaluateModel(mlContext, ml" +
+                    "Model, testDataView);\r\n\r\n");
 }
-            this.Write("\r\n            // Save model\r\n            SaveModel(mlContext, mlModel, MODEL_FILE" +
-                    "PATH, trainingDataView.Schema);\r\n        }\r\n\r\n        public static IEstimator<I" +
-                    "Transformer> BuildTrainingPipeline(MLContext mlContext)\r\n        {\r\n");
+            this.Write("            // Save model\r\n            SaveModel(mlContext, mlModel, MODEL_FILEPA" +
+                    "TH, trainingDataView.Schema);\r\n        }\r\n\r\n        public static IEstimator<ITr" +
+                    "ansformer> BuildTrainingPipeline(MLContext mlContext)\r\n        {\r\n");
  if(PreTrainerTransforms.Count >0 ) {
             this.Write("            // Data process configuration with pipeline data transformations \r\n  " +
                     "          var dataProcessPipeline = ");

src/Microsoft.ML.CodeGenerator/Templates/Console/ModelBuilder.tt

@@ -56,19 +56,19 @@ namespace <#= Namespace #>.ConsoleApp
             // Build training pipeline
             IEstimator<ITransformer> trainingPipeline = BuildTrainingPipeline(mlContext);
 
+            // Train Model
+            ITransformer mlModel = TrainModel(mlContext, trainingDataView, trainingPipeline);
+
 <# if(string.IsNullOrEmpty(TestPath) && !HasOnnxModel){ #>
             // Evaluate quality of Model
             Evaluate(mlContext, trainingDataView, trainingPipeline);
 
 <#}#>
-            // Train Model
-            ITransformer mlModel = TrainModel(mlContext, trainingDataView, trainingPipeline);
 <# if(!string.IsNullOrEmpty(TestPath) && !HasOnnxModel){ #>
-
             // Evaluate quality of Model
             EvaluateModel(mlContext, mlModel, testDataView);
-<#}#>
 
+<#}#>
             // Save model
             SaveModel(mlContext, mlModel, MODEL_FILEPATH, trainingDataView.Schema);
         }

src/Microsoft.ML.CodeGenerator/Templates/Console/PredictProgram.cs

@@ -59,13 +59,15 @@ public virtual string TransformText()
             this.Write(" with predicted ");
             this.Write(this.ToStringHelper.ToStringWithCulture(Utils.Normalize(LabelName)));
             this.Write(" from sample data...\\n\\n\");\r\n");
-foreach(var label in Features){
+ if(SampleData != null) {
+foreach(var kv in SampleData){
             this.Write("\t\t\tConsole.WriteLine($\"");
-            this.Write(this.ToStringHelper.ToStringWithCulture(label));
+            this.Write(this.ToStringHelper.ToStringWithCulture(kv.Key));
             this.Write(": {sampleData.");
-            this.Write(this.ToStringHelper.ToStringWithCulture(Utils.Normalize(label)));
+            this.Write(this.ToStringHelper.ToStringWithCulture(kv.Key));
             this.Write("}\");\r\n");
 }
+}
 if("BinaryClassification".Equals(TaskType) ){ 
             this.Write("\t\t\tConsole.WriteLine($\"\\n\\nPredicted ");
             this.Write(this.ToStringHelper.ToStringWithCulture(Utils.Normalize(LabelName)));

src/Microsoft.ML.CodeGenerator/Templates/Console/PredictProgram.tt

@@ -36,8 +36,10 @@ namespace <#= Namespace #>.ConsoleApp
 			var predictionResult = ConsumeModel.Predict(sampleData);
 
 			Console.WriteLine("Using model to make single prediction -- Comparing actual <#= Utils.Normalize(LabelName) #> with predicted <#= Utils.Normalize(LabelName) #> from sample data...\n\n");
-<#foreach(var label in Features){#>
-			Console.WriteLine($"<#= label #>: {sampleData.<#= Utils.Normalize(label) #>}");
+<# if(SampleData != null) {#>
+<#foreach(var kv in SampleData){#>
+			Console.WriteLine($"<#= kv.Key #>: {sampleData.<#= kv.Key #>}");
+<#}#>
 <#}#>
 <#if("BinaryClassification".Equals(TaskType) ){ #>
 			Console.WriteLine($"\n\nPredicted <#= Utils.Normalize(LabelName) #>: {predictionResult.Prediction}\n\n");

src/Microsoft.ML.CodeGenerator/Utils.cs

@@ -24,6 +24,12 @@ internal static string Sanitize(string name)
             return string.Join("", name.Select(x => Char.IsLetterOrDigit(x) ? x : '_'));
         }
 
+        /// <summary>
+        /// Take the first line of data from inputFile and parse it as a dictionary using schema from columnInference.
+        /// </summary>
+        /// <param name="inputFile">path to input file.</param>
+        /// <param name="columnInference">Column Inferernce Result.</param>
+        /// <returns>A dictionary which key is sanitized column name and value is first line of data.</returns>
         internal static IDictionary<string, string> GenerateSampleData(string inputFile, ColumnInferenceResults columnInference)
         {
             try

test/Microsoft.ML.CodeGenerator.Tests/ApprovalTests/ConsoleCodeGeneratorTests.AzureCodeGeneratorTest.Program.cs.approved.txt

@@ -16,20 +16,6 @@ namespace Test.ConsoleApp
             var predictionResult = ConsumeModel.Predict(sampleData);
 
             Console.WriteLine("Using model to make single prediction -- Comparing actual Label with predicted Label from sample data...\n\n");
-            Console.WriteLine($"Age: {sampleData.Age}");
-            Console.WriteLine($"Workclass: {sampleData.Workclass}");
-            Console.WriteLine($"Fnlwgt: {sampleData.Fnlwgt}");
-            Console.WriteLine($"Education: {sampleData.Education}");
-            Console.WriteLine($"Education_num: {sampleData.Education_num}");
-            Console.WriteLine($"Marital_status: {sampleData.Marital_status}");
-            Console.WriteLine($"Occupation: {sampleData.Occupation}");
-            Console.WriteLine($"Relationship: {sampleData.Relationship}");
-            Console.WriteLine($"Race: {sampleData.Race}");
-            Console.WriteLine($"Sex: {sampleData.Sex}");
-            Console.WriteLine($"Capital_gain: {sampleData.Capital_gain}");
-            Console.WriteLine($"Capital_loss: {sampleData.Capital_loss}");
-            Console.WriteLine($"Hours_per_week: {sampleData.Hours_per_week}");
-            Console.WriteLine($"Native_country: {sampleData.Native_country}");
             Console.WriteLine($"\n\nPredicted Label value {predictionResult.Prediction} \nPredicted Label scores: [{String.Join(",", predictionResult.Score)}]\n\n");
             Console.WriteLine("=============== End of process, hit any key to finish ===============");
             Console.ReadKey();

test/Microsoft.ML.CodeGenerator.Tests/ApprovalTests/ConsoleCodeGeneratorTests.AzureImageCodeGeneratorTest.Program.cs.approved.txt

@@ -16,7 +16,6 @@ namespace CodeGenTest.ConsoleApp
             var predictionResult = ConsumeModel.Predict(sampleData);
 
             Console.WriteLine("Using model to make single prediction -- Comparing actual Label with predicted Label from sample data...\n\n");
-            Console.WriteLine($"ImageSource: {sampleData.ImageSource}");
             Console.WriteLine($"\n\nPredicted Label value {predictionResult.Prediction} \nPredicted Label scores: [{String.Join(",", predictionResult.Score)}]\n\n");
             Console.WriteLine("=============== End of process, hit any key to finish ===============");
             Console.ReadKey();

test/Microsoft.ML.CodeGenerator.Tests/ApprovalTests/ConsoleCodeGeneratorTests.ConsoleAppProgramCSFileContentTest.approved.txt

@@ -20,11 +20,6 @@ namespace TestNamespace.ConsoleApp
             var predictionResult = ConsumeModel.Predict(sampleData);
 
             Console.WriteLine("Using model to make single prediction -- Comparing actual Label with predicted Label from sample data...\n\n");
-            Console.WriteLine($"col1: {sampleData.Col1}");
-            Console.WriteLine($"col2: {sampleData.Col2}");
-            Console.WriteLine($"col3: {sampleData.Col3}");
-            Console.WriteLine($"col4: {sampleData.Col4}");
-            Console.WriteLine($"col5: {sampleData.Col5}");
             Console.WriteLine($"\n\nPredicted Label: {predictionResult.Prediction}\n\n");
             Console.WriteLine("=============== End of process, hit any key to finish ===============");
             Console.ReadKey();

test/Microsoft.ML.CodeGenerator.Tests/ApprovalTests/ConsoleCodeGeneratorTests.PredictionProgramCSFileContentTest.approved.txt

@@ -20,11 +20,6 @@ namespace TestNamespace.ConsoleApp
             var predictionResult = ConsumeModel.Predict(sampleData);
 
             Console.WriteLine("Using model to make single prediction -- Comparing actual Label with predicted Label from sample data...\n\n");
-            Console.WriteLine($"col1: {sampleData.Col1}");
-            Console.WriteLine($"col2: {sampleData.Col2}");
-            Console.WriteLine($"col3: {sampleData.Col3}");
-            Console.WriteLine($"col4: {sampleData.Col4}");
-            Console.WriteLine($"col5: {sampleData.Col5}");
             Console.WriteLine($"\n\nPredicted Label: {predictionResult.Prediction}\n\n");
             Console.WriteLine("=============== End of process, hit any key to finish ===============");
             Console.ReadKey();

test/Microsoft.ML.CodeGenerator.Tests/ApprovalTests/ConsoleCodeGeneratorTests.Recommendation_GenerateConsoleAppProjectContents_VerifyPredictProgram.approved.txt

@@ -20,8 +20,6 @@ namespace TestNamespace.ConsoleApp
             var predictionResult = ConsumeModel.Predict(sampleData);
 
             Console.WriteLine("Using model to make single prediction -- Comparing actual Label with predicted Label from sample data...\n\n");
-            Console.WriteLine($"userId: {sampleData.UserId}");
-            Console.WriteLine($"movieId: {sampleData.MovieId}");
             Console.WriteLine($"\n\nPredicted Label: {predictionResult.Score}\n\n");
             Console.WriteLine("=============== End of process, hit any key to finish ===============");
             Console.ReadKey();

test/Microsoft.ML.CodeGenerator.Tests/ApprovalTests/TemplateTest.TestModelBuilder_noOnnx_noTestData.approved.txt

@@ -0,0 +1,94 @@
+// This file was auto-generated by ML.NET Model Builder. 
+
+using System;
+using System.Collections.Generic;
+using System.IO;
+using System.Linq;
+using Microsoft.ML;
+using Microsoft.ML.Data;
+using Namespace.Model;
+Using package1
+namespace Namespace.ConsoleApp
+{
+    public static class ModelBuilder
+    {
+        private static string TRAIN_DATA_FILEPATH = @"Path";
+        private static string MODEL_FILEPATH = @"/path/to/model";
+        // Create MLContext to be shared across the model creation workflow objects 
+        // Set a random seed for repeatable/deterministic results across multiple trainings.
+        private static MLContext mlContext = new MLContext(seed: 1);
+
+        public static void CreateModel()
+        {
+            // Load Data
+            IDataView trainingDataView = mlContext.Data.LoadFromTextFile<ModelInput>(
+                                            path: TRAIN_DATA_FILEPATH,
+                                            hasHeader : false,
+                                            separatorChar : ',',
+                                            allowQuoting : true,
+                                            allowSparse: true);
+
+            // Build training pipeline
+            IEstimator<ITransformer> trainingPipeline = BuildTrainingPipeline(mlContext);
+
+            // Train Model
+            ITransformer mlModel = TrainModel(mlContext, trainingDataView, trainingPipeline);
+
+            // Evaluate quality of Model
+            Evaluate(mlContext, trainingDataView, trainingPipeline);
+
+            // Save model
+            SaveModel(mlContext, mlModel, MODEL_FILEPATH, trainingDataView.Schema);
+        }
+
+        public static IEstimator<ITransformer> BuildTrainingPipeline(MLContext mlContext)
+        {
+            // Data process configuration with pipeline data transformations 
+            var dataProcessPipeline = mlContext.Transforms.PreTrainerTransformer1
+                                      .AppendCacheCheckpoint(mlContext);
+            // Set the training algorithm 
+            var trainer = mlContext.Task1.Trainers.Trainer
+                                      .Append(mlContext.Transforms.PostTrainerTransformer1);
+
+            var trainingPipeline = dataProcessPipeline.Append(trainer);
+
+            return trainingPipeline;
+        }
+
+        public static ITransformer TrainModel(MLContext mlContext, IDataView trainingDataView, IEstimator<ITransformer> trainingPipeline)
+        {
+            Console.WriteLine("=============== Training  model ===============");
+
+            ITransformer model = trainingPipeline.Fit(trainingDataView);
+
+            Console.WriteLine("=============== End of training process ===============");
+            return model;
+        }
+
+        private static void Evaluate(MLContext mlContext, IDataView trainingDataView, IEstimator<ITransformer> trainingPipeline)
+        {
+            // Cross-Validate with single dataset (since we don't have two datasets, one for training and for evaluate)
+            // in order to evaluate and get the model's accuracy metrics
+            Console.WriteLine("=============== Cross-validating to get model's accuracy metrics ===============");
+        }
+
+        private static void SaveModel(MLContext mlContext, ITransformer mlModel, string modelRelativePath, DataViewSchema modelInputSchema)
+        {
+            // Save/persist the trained model to a .ZIP file
+            Console.WriteLine($"=============== Saving the model  ===============");
+            mlContext.Model.Save(mlModel, modelInputSchema, GetAbsolutePath(modelRelativePath));
+            Console.WriteLine("The model is saved to {0}", GetAbsolutePath(modelRelativePath));
+        }
+
+        public static string GetAbsolutePath(string relativePath)
+        {
+            FileInfo _dataRoot = new FileInfo(typeof(Program).Assembly.Location);
+            string assemblyFolderPath = _dataRoot.Directory.FullName;
+
+            string fullPath = Path.Combine(assemblyFolderPath, relativePath);
+
+            return fullPath;
+        }
+
+    }
+}

test/Microsoft.ML.CodeGenerator.Tests/ApprovalTests/TemplateTest.TestPredictProgram_WithSampleData.approved.txt

@@ -21,6 +21,9 @@ namespace Namespace.ConsoleApp
 			var predictionResult = ConsumeModel.Predict(sampleData);
 
 			Console.WriteLine("Using model to make single prediction -- Comparing actual LabelName with predicted LabelName from sample data...\n\n");
+			Console.WriteLine($"key1: {sampleData.key1}");
+			Console.WriteLine($"key2: {sampleData.key2}");
+			Console.WriteLine($"key3: {sampleData.key3}");
             Console.WriteLine("=============== End of process, hit any key to finish ===============");
             Console.ReadKey();
         }

test/Microsoft.ML.CodeGenerator.Tests/ApprovalTests/TemplateTest.cs

@@ -55,5 +55,31 @@ public void TestConsumeModel()
 
             Approvals.Verify(consumeModel.TransformText());
         }
+
+        [Fact]
+        [UseReporter(typeof(DiffReporter))]
+        [MethodImpl(MethodImplOptions.NoInlining)]
+        public void TestModelBuilder_noOnnx_noTestData()
+        {
+            var modelBuilder = new ModelBuilder()
+            {
+                Namespace = "Namespace",
+                HasOnnxModel = false,
+                Path = "Path",
+                Separator = ',',
+                PreTrainerTransforms = new string[] { "PreTrainerTransformer1" },
+                Trainer = "Trainer",
+                TaskType = "Task1",
+                GeneratedUsings = "Using package1",
+                AllowQuoting = true,
+                AllowSparse = true,
+                LabelName = "Label",
+                CacheBeforeTrainer = true,
+                PostTrainerTransforms = new string[] { "PostTrainerTransformer1" },
+                MLNetModelpath = "/path/to/model",
+            };
+
+            Approvals.Verify(modelBuilder.TransformText());
+        }
     }
 }