ML.NET使用LearningPipeline类定义执行期望的机器学习任务所需的步骤，让机器学习的流程变得直观。
下面用鸢尾花瓣预测快速入门的示例代码讲解流水线是如何工作的。
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}");
}
}
}
创建工作流实例
首先，创建LearningPipeline实例
var pipeline = new LearningPipeline();
添加步骤
然后，调用LearningPipeline实例的Add方法向流水线添加步骤，每个步骤都继承自ILearningPipelineItem接口。
一个基本的工作流包括以下几个步骤，其中，蓝色部分是可选的。
- 加载数据集
继承自ILearningPipelineLoader接口。
一个工作流必须包含至少1个加载数据集步骤。
//使用TextLoader加载数据 string dataPath = "iris-data.txt"; pipeline.Add(new TextLoader(dataPath).CreateFrom<IrisData>(separator: ','));
- 数据预处理
继承自CommonInputs.ITransformInput接口。
一个工作流可以包含0到多个数据预处理步骤，用于将已加载的数据集标准化，示例代码中就包含2了个数据预处理步骤。
//由于Label文本数据，算法不能识别数据，需要将其转换为字典
pipeline.Add(new Dictionarizer("Label"));
//算法只能从Features列获取数据，需要数据中的多列连接到Features列中
pipeline.Add(new ColumnConcatenator("Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth"));
- 选择学习算法
继承自CommonInputs.ITrainerInput接口。
一个工作流必须且只能包含1个学习算法。
//使用线性分类器 pipeline.Add(new StochasticDualCoordinateAscentClassifier());
- 标签转换
继承自CommonInputs.ITransformInput接口。
一个工作流可以包含0到多个标签转换步骤，用于将预测得到的标签转换成方便识别的数据。
//将Label从字典转换成文本数据
pipeline.Add(new PredictedLabelColumnOriginalValueConverter() { PredictedLabelColumn = "PredictedLabel" });
执行工作流
最后，调用LearningPipeline实例的Train方法，就可以执行工作流得到预测模型。
var model = pipeline.Train<IrisData, IrisPrediction>();