ML.NET速览

时间：2022-01-28 23:27:54

什么是ML.NET？

ML.NET是由微软创建，为.NET开发者准备的开源机器学习框架。它是跨平台的，可以在macOS，Linux及Windows上运行。

机器学习管道

ML.NET通过管道(pipeline)方式组合机器学习过程。整个管道分为以下四个部分：

  • Load Data 加载数据
  • Transform Data 转换数据
  • Choose Algorithm 选择算法
  • Train Model 训练模型

示例

建立一个控制台项目。

dotnet new console -o myApp

cd myApp

添加ML.NET类库包。

dotnet add package Microsoft.ML

在工程文件夹下创建一个名为iris-data.txt的文本文件，内容如下：

5.1,3.5,1.4,0.2,Iris-setosa

4.9,3.0,1.4,0.2,Iris-setosa

4.7,3.2,1.3,0.2,Iris-setosa

4.6,3.1,1.5,0.2,Iris-setosa

5.0,3.6,1.4,0.2,Iris-setosa

5.4,3.9,1.7,0.4,Iris-setosa

4.6,3.4,1.4,0.3,Iris-setosa

5.0,3.4,1.5,0.2,Iris-setosa

4.4,2.9,1.4,0.2,Iris-setosa

4.9,3.1,1.5,0.1,Iris-setosa

5.4,3.7,1.5,0.2,Iris-setosa

4.8,3.4,1.6,0.2,Iris-setosa

4.8,3.0,1.4,0.1,Iris-setosa

4.3,3.0,1.1,0.1,Iris-setosa

5.8,4.0,1.2,0.2,Iris-setosa

5.7,4.4,1.5,0.4,Iris-setosa

5.4,3.9,1.3,0.4,Iris-setosa

5.1,3.5,1.4,0.3,Iris-setosa

5.7,3.8,1.7,0.3,Iris-setosa

5.1,3.8,1.5,0.3,Iris-setosa

5.4,3.4,1.7,0.2,Iris-setosa

5.1,3.7,1.5,0.4,Iris-setosa

4.6,3.6,1.0,0.2,Iris-setosa

5.1,3.3,1.7,0.5,Iris-setosa

4.8,3.4,1.9,0.2,Iris-setosa

5.0,3.0,1.6,0.2,Iris-setosa

5.0,3.4,1.6,0.4,Iris-setosa

5.2,3.5,1.5,0.2,Iris-setosa

5.2,3.4,1.4,0.2,Iris-setosa

4.7,3.2,1.6,0.2,Iris-setosa

4.8,3.1,1.6,0.2,Iris-setosa

5.4,3.4,1.5,0.4,Iris-setosa

5.2,4.1,1.5,0.1,Iris-setosa

5.5,4.2,1.4,0.2,Iris-setosa

4.9,3.1,1.5,0.1,Iris-setosa

5.0,3.2,1.2,0.2,Iris-setosa

5.5,3.5,1.3,0.2,Iris-setosa

4.9,3.1,1.5,0.1,Iris-setosa

4.4,3.0,1.3,0.2,Iris-setosa

5.1,3.4,1.5,0.2,Iris-setosa

5.0,3.5,1.3,0.3,Iris-setosa

4.5,2.3,1.3,0.3,Iris-setosa

4.4,3.2,1.3,0.2,Iris-setosa

5.0,3.5,1.6,0.6,Iris-setosa

5.1,3.8,1.9,0.4,Iris-setosa

4.8,3.0,1.4,0.3,Iris-setosa

5.1,3.8,1.6,0.2,Iris-setosa

4.6,3.2,1.4,0.2,Iris-setosa

5.3,3.7,1.5,0.2,Iris-setosa

5.0,3.3,1.4,0.2,Iris-setosa

7.0,3.2,4.7,1.4,Iris-versicolor

6.4,3.2,4.5,1.5,Iris-versicolor

6.9,3.1,4.9,1.5,Iris-versicolor

5.5,2.3,4.0,1.3,Iris-versicolor

6.5,2.8,4.6,1.5,Iris-versicolor

5.7,2.8,4.5,1.3,Iris-versicolor

6.3,3.3,4.7,1.6,Iris-versicolor

4.9,2.4,3.3,1.0,Iris-versicolor

6.6,2.9,4.6,1.3,Iris-versicolor

5.2,2.7,3.9,1.4,Iris-versicolor

5.0,2.0,3.5,1.0,Iris-versicolor

5.9,3.0,4.2,1.5,Iris-versicolor

6.0,2.2,4.0,1.0,Iris-versicolor

6.1,2.9,4.7,1.4,Iris-versicolor

5.6,2.9,3.6,1.3,Iris-versicolor

6.7,3.1,4.4,1.4,Iris-versicolor

5.6,3.0,4.5,1.5,Iris-versicolor

5.8,2.7,4.1,1.0,Iris-versicolor

6.2,2.2,4.5,1.5,Iris-versicolor

5.6,2.5,3.9,1.1,Iris-versicolor

5.9,3.2,4.8,1.8,Iris-versicolor

6.1,2.8,4.0,1.3,Iris-versicolor

6.3,2.5,4.9,1.5,Iris-versicolor

6.1,2.8,4.7,1.2,Iris-versicolor

6.4,2.9,4.3,1.3,Iris-versicolor

6.6,3.0,4.4,1.4,Iris-versicolor

6.8,2.8,4.8,1.4,Iris-versicolor

6.7,3.0,5.0,1.7,Iris-versicolor

6.0,2.9,4.5,1.5,Iris-versicolor

5.7,2.6,3.5,1.0,Iris-versicolor

5.5,2.4,3.8,1.1,Iris-versicolor

5.5,2.4,3.7,1.0,Iris-versicolor

5.8,2.7,3.9,1.2,Iris-versicolor

6.0,2.7,5.1,1.6,Iris-versicolor

5.4,3.0,4.5,1.5,Iris-versicolor

6.0,3.4,4.5,1.6,Iris-versicolor

6.7,3.1,4.7,1.5,Iris-versicolor

6.3,2.3,4.4,1.3,Iris-versicolor

5.6,3.0,4.1,1.3,Iris-versicolor

5.5,2.5,4.0,1.3,Iris-versicolor

5.5,2.6,4.4,1.2,Iris-versicolor

6.1,3.0,4.6,1.4,Iris-versicolor

5.8,2.6,4.0,1.2,Iris-versicolor

5.0,2.3,3.3,1.0,Iris-versicolor

5.6,2.7,4.2,1.3,Iris-versicolor

5.7,3.0,4.2,1.2,Iris-versicolor

5.7,2.9,4.2,1.3,Iris-versicolor

6.2,2.9,4.3,1.3,Iris-versicolor

5.1,2.5,3.0,1.1,Iris-versicolor

5.7,2.8,4.1,1.3,Iris-versicolor

6.3,3.3,6.0,2.5,Iris-virginica

5.8,2.7,5.1,1.9,Iris-virginica

7.1,3.0,5.9,2.1,Iris-virginica

6.3,2.9,5.6,1.8,Iris-virginica

6.5,3.0,5.8,2.2,Iris-virginica

7.6,3.0,6.6,2.1,Iris-virginica

4.9,2.5,4.5,1.7,Iris-virginica

7.3,2.9,6.3,1.8,Iris-virginica

6.7,2.5,5.8,1.8,Iris-virginica

7.2,3.6,6.1,2.5,Iris-virginica

6.5,3.2,5.1,2.0,Iris-virginica

6.4,2.7,5.3,1.9,Iris-virginica

6.8,3.0,5.5,2.1,Iris-virginica

5.7,2.5,5.0,2.0,Iris-virginica

5.8,2.8,5.1,2.4,Iris-virginica

6.4,3.2,5.3,2.3,Iris-virginica

6.5,3.0,5.5,1.8,Iris-virginica

7.7,3.8,6.7,2.2,Iris-virginica

7.7,2.6,6.9,2.3,Iris-virginica

6.0,2.2,5.0,1.5,Iris-virginica

6.9,3.2,5.7,2.3,Iris-virginica

5.6,2.8,4.9,2.0,Iris-virginica

7.7,2.8,6.7,2.0,Iris-virginica

6.3,2.7,4.9,1.8,Iris-virginica

6.7,3.3,5.7,2.1,Iris-virginica

7.2,3.2,6.0,1.8,Iris-virginica

6.2,2.8,4.8,1.8,Iris-virginica

6.1,3.0,4.9,1.8,Iris-virginica

6.4,2.8,5.6,2.1,Iris-virginica

7.2,3.0,5.8,1.6,Iris-virginica

7.4,2.8,6.1,1.9,Iris-virginica

7.9,3.8,6.4,2.0,Iris-virginica

6.4,2.8,5.6,2.2,Iris-virginica

6.3,2.8,5.1,1.5,Iris-virginica

6.1,2.6,5.6,1.4,Iris-virginica

7.7,3.0,6.1,2.3,Iris-virginica

6.3,3.4,5.6,2.4,Iris-virginica

6.4,3.1,5.5,1.8,Iris-virginica

6.0,3.0,4.8,1.8,Iris-virginica

6.9,3.1,5.4,2.1,Iris-virginica

6.7,3.1,5.6,2.4,Iris-virginica

6.9,3.1,5.1,2.3,Iris-virginica

5.8,2.7,5.1,1.9,Iris-virginica

6.8,3.2,5.9,2.3,Iris-virginica

6.7,3.3,5.7,2.5,Iris-virginica

6.7,3.0,5.2,2.3,Iris-virginica

6.3,2.5,5.0,1.9,Iris-virginica

6.5,3.0,5.2,2.0,Iris-virginica

6.2,3.4,5.4,2.3,Iris-virginica

5.9,3.0,5.1,1.8,Iris-virginica

粘贴下面的代码到Program文件中。

using System;

using Microsoft.ML;

using Microsoft.ML.Runtime.Api;

using Microsoft.ML.Runtime.Data;

namespace myApp

{

    class Program

    {

        public class IrisData

        {

            public float SepalLength;

            public float SepalWidth;

            public float PetalLength;

            public float PetalWidth;

            public string Label;

        }

        public class IrisPrediction

        {

            [ColumnName("PredictedLabel")]

            public string PredictedLabels;

        }

        static void Main(string[] args)

        {

            var mlContext = new MLContext();

            string dataPath = "iris-data.txt";

            var reader = mlContext.Data.TextReader(new TextLoader.Arguments()

            {

                Separator = ",",

                HasHeader = true,

                Column = new[]

                {

                    new TextLoader.Column("SepalLength", DataKind.R4, 0),

                    new TextLoader.Column("SepalWidth", DataKind.R4, 1),

                    new TextLoader.Column("PetalLength", DataKind.R4, 2),

                    new TextLoader.Column("PetalWidth", DataKind.R4, 3),

                    new TextLoader.Column("Label", DataKind.Text, 4)

                }

            });

            IDataView trainingDataView = reader.Read(new MultiFileSource(dataPath));

            var pipeline = mlContext.Transforms.Categorical.MapValueToKey("Label")

                .Append(mlContext.Transforms.Concatenate("Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth"))

                .Append(mlContext.MulticlassClassification.Trainers.StochasticDualCoordinateAscent(label: "Label", features: "Features"))

                .Append(mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));

            var model = pipeline.Fit(trainingDataView);

            var prediction = model.MakePredictionFunction<IrisData, IrisPrediction>(mlContext).Predict(

                new IrisData()

                {

                    SepalLength = 3.3f,

                    SepalWidth = 1.6f,

                    PetalLength = 0.2f,

                    PetalWidth = 5.1f,

                });

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

        }

    }

}

通过dotnet run命令运行程序后可得到预测结果。

Predicted flower type is: Iris-virginica

解例

例子中定义了两个类，IrisData与IrisPrediction。IrisData类是用于训练的数据结构，而IrisPrediction则用于预测。

MLContext类用于定义ML.NET的上下文(context)，可以理解为是它的运行时环境。

接着，创建一个TextReader，用于读取数据集文件，可以看到其中规定了读取的格式。这里即是机器学习管道的第一步。

第二步，转换IrisData类中Label属性的类型，使之成为数值类型，因为只有数值类型的数据才能在模型训练中被使用。再将SepalLength，SepalWidth，PetalLength与PetalWidth合并为一，统合为数据集的Features。

第三步，为训练选择合适的算法，并传入标签(Label)和特征(Features)。

第四步，训练模型。

完成模型后，就可以用它进行预测了。因为最后预测的结果是字符串类型，所以在上述第三步的操作后有必要加上转换操作，把结果从数值类型再转回字符串类型。

相关文章