ML.NET使用LearningPipeline類定義執行期望的機器學習任務所需的步驟，讓機器學習的流程變得直觀。

下麵用鳶尾花瓣預測快速入門的示例代碼講解流水線是如何工作的。

using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
using System;

namespace myApp
{
    class Program
    {
        // STEP 1: Define your data structures

        // IrisData is used to provide training data, and as 
        // input for prediction operations
        // - First 4 properties are inputs/features used to predict the label
        // - Label is what you are predicting, and is only set when training
        public class IrisData
        {
            [Column("0")]
            public float SepalLength;

            [Column("1")]
            public float SepalWidth;

            [Column("2")]
            public float PetalLength;

            [Column("3")]
            public float PetalWidth;

            [Column("4")]
            [ColumnName("Label")]
            public string Label;
        }

        // IrisPrediction is the result returned from prediction operations
        public class IrisPrediction
        {
            [ColumnName("PredictedLabel")]
            public string PredictedLabels;
        }

        static void Main(string[] args)
        {
            // STEP 2: Create a pipeline and load your data
            var pipeline = new LearningPipeline();

            // If working in Visual Studio, make sure the 'Copy to Output Directory' 
            // property of iris-data.txt is set to 'Copy always'
            string dataPath = "iris-data.txt";
            pipeline.Add(new TextLoader(dataPath).CreateFrom<IrisData>(separator: ','));

            // STEP 3: Transform your data
            // Assign numeric values to text in the "Label" column, because only
            // numbers can be processed during model training
            pipeline.Add(new Dictionarizer("Label"));

            // Puts all features into a vector
            pipeline.Add(new ColumnConcatenator("Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth"));

            // STEP 4: Add learner
            // Add a learning algorithm to the pipeline. 
            // This is a classification scenario (What type of iris is this?)
            pipeline.Add(new StochasticDualCoordinateAscentClassifier());

            // Convert the Label back into original text (after converting to number in step 3)
            pipeline.Add(new PredictedLabelColumnOriginalValueConverter() { PredictedLabelColumn = "PredictedLabel" });

            // STEP 5: Train your model based on the data set
            var model = pipeline.Train<IrisData, IrisPrediction>();

            // STEP 6: Use your model to make a prediction
            // You can change these numbers to test different predictions
            var prediction = model.Predict(new IrisData()
            {
                SepalLength = 3.3f,
                SepalWidth = 1.6f,
                PetalLength = 0.2f,
                PetalWidth = 5.1f,
            });

            Console.WriteLine($"Predicted flower type is: {prediction.PredictedLabels}");
        }
    }
}

創建工作流實例

首先，創建LearningPipeline實例

var pipeline = new LearningPipeline();

添加步驟

然後，調用LearningPipeline實例的Add方法向流水線添加步驟，每個步驟都繼承自ILearningPipelineItem介面。

一個基本的工作流包括以下幾個步驟，其中，藍色部分是可選的。

• 載入數據集

繼承自ILearningPipelineLoader介面。

一個工作流必須包含至少1個載入數據集步驟。

//使用TextLoader載入數據
string dataPath = "iris-data.txt";
pipeline.Add(new TextLoader(dataPath).CreateFrom<IrisData>(separator: ','));

• 數據預處理

繼承自CommonInputs.ITransformInput介面。

一個工作流可以包含0到多個數據預處理步驟，用於將已載入的數據集標準化，示例代碼中就包含2了個數據預處理步驟。

//由於Label文本數據，演算法不能識別數據，需要將其轉換為字典
pipeline.Add(new Dictionarizer("Label")); 

//演算法只能從Features列獲取數據，需要數據中的多列連接到Features列中
pipeline.Add(new ColumnConcatenator("Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth"));

• 選擇學習演算法

繼承自CommonInputs.ITrainerInput介面。

一個工作流必須且只能包含1個學習演算法。

//使用線性分類器
pipeline.Add(new StochasticDualCoordinateAscentClassifier()); 

• 標簽轉換

繼承自CommonInputs.ITransformInput介面。

一個工作流可以包含0到多個標簽轉換步驟，用於將預測得到的標簽轉換成方便識別的數據。

//將Label從字典轉換成文本數據
pipeline.Add(new PredictedLabelColumnOriginalValueConverter() { PredictedLabelColumn = "PredictedLabel" });

 執行工作流

最後，調用LearningPipeline實例的Train方法，就可以執行工作流得到預測模型。

var model = pipeline.Train<IrisData, IrisPrediction>();