说说 ML.NET and AutoML

经常参加培训讲座。发现最受欢迎的讲座之一是"ML.NET和AutoML的介绍"。ML.NET是一个代码库，可用于创建经典（非神经网络）机器学习预测模型。AutoML 是命令行工具中的非正式术语，可自动为您生成ML.NET代码。

以下是我使用的两个数据文件，演示ML.NET程序的源代码，以及 AutoML 的 shell 命令。目标是从年龄、工作类型、年收入和工作满意度中预测一个人的性别。

文件：employees_norm_train.tsv

文件：employees_norm_test.tsv

文件：GenderMLdotNETProgram.cs

•  

using System;using Microsoft.ML;using Microsoft.ML.Data;using Microsoft.ML.Trainers;namespace GenderMLdotNET{  class GenderMLdotNETProgram  {    static void Main(string[] args)    {      Console.WriteLine("\nBegin ML.NET gender demo \n");      MLContext mlc = new MLContext(seed: 1);
      // 1. load data and create data pipeline      Console.WriteLine("\nLoading norm data into memory \n");      string trainDataPath =        "..\\..\\..\\Data\\employees_norm_train.tsv";
      IDataView trainData =        mlc.Data.LoadFromTextFile        (trainDataPath, '\t', hasHeader: true);
      var a = mlc.Transforms.Categorical.OneHotEncoding(new[]       { new InputOutputColumnPair("job", "job") });      var b = mlc.Transforms.Categorical.OneHotEncoding(new[]        { new InputOutputColumnPair("satisfac", "satisfac") });      var c = mlc.Transforms.Concatenate("Features", new[]        { "age", "job", "income", "satisfac" });      var dataPipe = a.Append(b).Append(c);
      Console.WriteLine("Creating logistic regression model");      var options =        new LbfgsLogisticRegressionBinaryTrainer.Options()      {        LabelColumnName = "isMale",        FeatureColumnName = "Features",        MaximumNumberOfIterations = 100,        OptimizationTolerance = 1e-8f      };
      var trainer =        mlc.BinaryClassification.Trainers.        LbfgsLogisticRegression(options);      var trainPipe = dataPipe.Append(trainer);      Console.WriteLine("Starting training");      ITransformer model = trainPipe.Fit(trainData);      Console.WriteLine("Training complete");
      // 3. evaluate model      IDataView predictions = model.Transform(trainData);      var metrics = mlc.BinaryClassification.        EvaluateNonCalibrated(predictions, "isMale", "Score");      Console.Write("Model accuracy on training data = ");      Console.WriteLine(metrics.Accuracy.ToString("F4") + "\n");
      // 4. use model      ModelInput X = new ModelInput();      X.Age = 0.32f; X.Job = "mgmt"; X.Income = 0.4900f;      X.Satisfac = "medium";
      var pe = mlc.Model.CreatePredictionEngine(model);      var Y = pe.Predict(X);      Console.Write("Set age = 32, job = mgmt, income = $49K, ");      Console.WriteLine("satisfac = medium");      Console.Write("Predicted isMale : ");      Console.WriteLine(Y.PredictedLabel);
      Console.WriteLine("\nEnd ML.NET demo ");      Console.ReadLine();    } // Main  } // Program
  class ModelOutput  {    [ColumnName("predictedLabel")]    public bool PredictedLabel { get; set; }
    [ColumnName("score")]    public float Score { get; set; }  }
  class ModelInput  {    [ColumnName("isMale"), LoadColumn(0)]    public bool IsMale { get; set; }
    [ColumnName("age"), LoadColumn(1)]    public float Age { get; set; }
    [ColumnName("job"), LoadColumn(2)]    public string Job { get; set; }
    [ColumnName("income"), LoadColumn(3)]    public float Income { get; set; }
    [ColumnName("satisfac"), LoadColumn(4)]    public string Satisfac { get; set; }  }} // ns

AutoML命令：

•  

mlnet auto-train ^--task binary-classification ^--dataset ".\Data\employees_norm_train.tsv" ^--test-dataset ".\Data\employees_norm_test.tsv" ^--label-column-name isMale ^--max-exploration-time 60 ^--name PredictGenderAutoML