Iris Clustering sample updated to v0.7 and common-code approach

samples/csharp/getting-started/BinaryClassification_CreditCardFraudDetection/Readme.md

@@ -2,7 +2,7 @@
 
 | ML.NET version | API type          | Status                        | App Type    | Data type | Scenario            | ML Task                   | Algorithms                  |
 |----------------|-------------------|-------------------------------|-------------|-----------|---------------------|---------------------------|-----------------------------|
-| v0.6           | Dynamic API | Up-to-date | Two console apps | .csv file | Fraud Detection | Two-class  classification | FastTree Binary  Classification |
+| v0.6           | Dynamic API | Needs update to 0.7 and README.md | Two console apps | .csv file | Fraud Detection | Two-class  classification | FastTree Binary  Classification |
 
 In this introductory sample, you'll see how to use ML.NET to predict a credit card fraud. In the world of machine learning, this type of prediction is known as binary classification.
 

samples/csharp/getting-started/BinaryClassification_SentimentAnalysis/README.md

@@ -8,9 +8,6 @@
 
 In this introductory sample, you'll see how to use [ML.NET](https://www.microsoft.com/net/learn/apps/machine-learning-and-ai/ml-dotnet) to predict a sentiment (positive or negative) for customer reviews. In the world of machine learning, this type of prediction is known as **binary classification**.
 
-## API version: Static and Estimators-based API
-It is important to note that this sample uses the **static API with Estimators**, available since ML.NET v0.6.
-
 ## Problem
 This problem is centered around predicting if a customer's review has positive or negative sentiment. We will use small wikipedia-detox-datasets (one dataset for training and a second dataset for model's accuracy evaluation) that were processed by humans and each comment has been assigned a sentiment label: 
 * 0 - nice/positive

samples/csharp/getting-started/Clustering_CustomerSegmentation/CustomerSegmentation.Train/Program.cs

@@ -53,7 +53,7 @@ static void Main(string[] args)
 
                 // STEP4: Evaluate accuracy of the model
                 var metrics = modelBuilder.EvaluateClusteringModel(pivotDataView);
-                Common.ConsoleHelper.PrintClusteringMetrics("KMeansPlusPlus", metrics);
+                Common.ConsoleHelper.PrintClusteringMetrics("KMeans", metrics);
 
                 // STEP5: Save/persist the model as a .ZIP file
                 modelBuilder.SaveModelAsFile(modelZip);

samples/csharp/getting-started/Clustering_CustomerSegmentation/README.md

@@ -2,7 +2,7 @@
 
 | ML.NET version | API type          | Status                        | App Type    | Data type | Scenario            | ML Task                   | Algorithms                  |
 |----------------|-------------------|-------------------------------|-------------|-----------|---------------------|---------------------------|-----------------------------|
-| v0.6           | Dynamic API | Evolving | Console app | .csv files | Customer segmentation | Clustering | K-means++ |
+| v0.6           | Dynamic API | README.md needs update | Console app | .csv files | Customer segmentation | Clustering | K-means++ |
 
 ## Problem
 

samples/csharp/getting-started/Clustering_Iris/Clustering_Iris.sln

@@ -3,7 +3,7 @@ Microsoft Visual Studio Solution File, Format Version 12.00
 # Visual Studio 15
 VisualStudioVersion = 15.0.28010.2046
 MinimumVisualStudioVersion = 10.0.40219.1
-Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Clustering_Iris", "Clustering_Iris.csproj", "{E730C84B-0F03-4C0C-9B22-68130091C900}"
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Clustering_Iris", "IrisClustering/IrisClusteringConsoleApp/Clustering_Iris.csproj", "{E730C84B-0F03-4C0C-9B22-68130091C900}"
 EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution

samples/csharp/getting-started/Clustering_Iris/IrisClustering/IrisClusteringConsoleApp/Clustering_Iris.csproj

@@ -0,0 +1,28 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>netcoreapp2.1</TargetFramework>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <Compile Include="..\..\..\..\common\ConsoleHelper.cs" Link="Common\ConsoleHelper.cs" />
+    <Compile Include="..\..\..\..\common\ModelBuilder.cs" Link="Common\ModelBuilder.cs" />
+    <Compile Include="..\..\..\..\common\ModelScorer.cs" Link="Common\ModelScorer.cs" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.ML" Version="0.7.0-preview-27031-8" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="datasets\iris-full.txt">
+      <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+  <ItemGroup>
+    <Folder Include="Common\" />
+  </ItemGroup>
+
+</Project>

samples/csharp/getting-started/Clustering_Iris/IrisClustering/IrisClusteringConsoleApp/DataLoader.cs

@@ -0,0 +1,42 @@
+using Microsoft.ML;
+using Microsoft.ML.Core.Data;
+using Microsoft.ML.Runtime.Data;
+using Microsoft.ML.Transforms;
+using System;
+using System.Collections.Generic;
+using System.Text;
+
+namespace Clustering_Iris
+{
+    class DataLoader
+    {
+        MLContext _mlContext;
+        private TextLoader _loader;
+
+        public DataLoader(MLContext mlContext)
+        {
+            _mlContext = mlContext;
+
+            // Create the TextLoader by defining the data columns and where to find (column position) them in the text file.
+            _loader = mlContext.Data.TextReader(new TextLoader.Arguments()
+                                                {
+                                                    Separator = "\t",
+                                                    HasHeader = true,
+                                                    Column = new[]
+                                                    {
+                                                                    new TextLoader.Column("Label", DataKind.R4, 0),
+                                                                    new TextLoader.Column("SepalLength", DataKind.R4, 1),
+                                                                    new TextLoader.Column("SepalWidth", DataKind.R4, 2),
+                                                                    new TextLoader.Column("PetalLength", DataKind.R4, 3),
+                                                                    new TextLoader.Column("PetalWidth", DataKind.R4, 4),
+                                                    }
+                                                 });
+        }
+
+        public IDataView GetDataView(string filePath)
+        {
+            return _loader.Read(filePath);
+        }
+    }
+}
+

samples/csharp/getting-started/Clustering_Iris/IrisClustering/IrisClusteringConsoleApp/DataProcessor.cs

@@ -0,0 +1,23 @@
+using Microsoft.ML;
+using Microsoft.ML.Core.Data;
+using Microsoft.ML.Runtime.Data;
+using Microsoft.ML.Transforms;
+using Microsoft.ML.Transforms.Categorical;
+using Microsoft.ML.Transforms.PCA;
+using System;
+using System.Collections.Generic;
+using System.Text;
+
+namespace Clustering_Iris
+{
+    public class DataProcessor
+    {
+        public IEstimator<ITransformer> DataProcessPipeline { get; private set; }
+
+        public DataProcessor(MLContext mlContext)
+        {
+            // Configure data transformations in the DataProcess pipeline
+            DataProcessPipeline = mlContext.Transforms.Concatenate("Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");
+        }
+    }
+}

samples/csharp/getting-started/Clustering_Iris/IrisClustering/IrisClusteringConsoleApp/DataStructures/IrisData.cs

@@ -0,0 +1,26 @@
+using Microsoft.ML.Runtime.Api;
+using System;
+using System.Collections.Generic;
+using System.Text;
+
+namespace Clustering_Iris.DataStructures
+{
+    public class IrisData
+    {
+        [Column("0")]
+        public float Label;
+
+        [Column("1")]
+        public float SepalLength;
+
+        [Column("2")]
+        public float SepalWidth;
+
+        [Column("3")]
+        public float PetalLength;
+
+        [Column("4")]
+        public float PetalWidth;
+
+    }
+}

samples/csharp/getting-started/Clustering_Iris/IrisClustering/IrisClusteringConsoleApp/DataStructures/IrisPrediction.cs

@@ -0,0 +1,17 @@
+using Microsoft.ML.Runtime.Api;
+using System;
+using System.Collections.Generic;
+using System.Text;
+
+namespace Clustering_Iris.DataStructures
+{
+    // IrisPrediction is the result returned from prediction operations
+    public class IrisPrediction
+    {
+        [ColumnName("PredictedLabel")]
+        public uint SelectedClusterId;
+
+        [ColumnName("Score")]
+        public float[] Distance;
+    }
+}

samples/csharp/getting-started/Clustering_Iris/IrisClustering/IrisClusteringConsoleApp/Program.cs

@@ -0,0 +1,82 @@
+using System;
+using System.IO;
+
+using Microsoft.ML;
+using Common;
+using Clustering_Iris.DataStructures;
+
+namespace Clustering_Iris
+{
+    internal static class Program
+    {
+        private static string AppPath => Path.GetDirectoryName(Environment.GetCommandLineArgs()[0]);
+
+        private static string BaseDatasetsLocation = @"../../../../Data";
+        private static string DataPath = $"{BaseDatasetsLocation}/iris-full.txt";
+
+        private static string BaseModelsPath = @"../../../../MLModels";
+        private static string ModelPath = $"{BaseModelsPath}/IrisModel.zip";
+
+        private static void Main(string[] args)
+        {
+            //Create the MLContext to share across components for deterministic results
+            MLContext mlContext = new MLContext(seed: 1);  //Seed set to any number so you have a deterministic environment
+
+            //STEP 1: Common data loading
+            DataLoader dataLoader = new DataLoader(mlContext);
+            var trainingDataView = dataLoader.GetDataView(DataPath);
+
+            //STEP 2: Process data transformations in pipeline
+            var dataProcessor = new DataProcessor(mlContext);
+            var dataProcessPipeline = dataProcessor.DataProcessPipeline;
+
+            // (Optional) Peek data in training DataView after applying the ProcessPipeline's transformations  
+            Common.ConsoleHelper.PeekDataViewInConsole<IrisData>(mlContext, trainingDataView, dataProcessPipeline, 10);
+            Common.ConsoleHelper.PeekVectorColumnDataInConsole(mlContext, "Features", trainingDataView, dataProcessPipeline, 10);
+
+            // STEP 3: Create and train the model                
+            var modelBuilder = new ModelBuilder<IrisData, IrisPrediction>(mlContext, dataProcessPipeline);
+            var trainer = mlContext.Clustering.Trainers.KMeans(features: "Features", clustersCount: 3);
+            modelBuilder.AddTrainer(trainer);
+            var trainedModel = modelBuilder.Train(trainingDataView);
+
+            // STEP4: Evaluate accuracy of the model
+            var metrics = modelBuilder.EvaluateClusteringModel(trainingDataView);
+            Common.ConsoleHelper.PrintClusteringMetrics("KMeans", metrics);
+
+            // STEP5: Save/persist the model as a .ZIP file
+            modelBuilder.SaveModelAsFile(ModelPath);
+
+            Console.WriteLine("=============== End of training process ===============");
+
+            Console.WriteLine("=============== Predict a cluster for a single case (Single Iris data sample) ===============");
+
+            // Test with one sample text 
+            var sampleIrisData = new IrisData()
+            {
+                SepalLength = 3.3f,
+                SepalWidth = 1.6f,
+                PetalLength = 0.2f,
+                PetalWidth = 5.1f,
+            };
+
+            //Create the clusters: Create data files and plot a chart
+            var modelScorer = new ModelScorer<IrisData, IrisPrediction>(mlContext);
+            modelScorer.LoadModelFromZipFile(ModelPath);
+
+            var prediction = modelScorer.PredictSingle(sampleIrisData);
+
+            Console.WriteLine($"Cluster assigned for setosa flowers:"+prediction.SelectedClusterId);
+
+            Console.WriteLine("=============== End of process, hit any key to finish ===============");
+            Console.ReadKey();           
+        }
+    }
+
+
+
+
+
+
+
+}