如何使用回归任务通过 ML.NET 预测多个标签？

Question

我对机器学习非常陌生，我偶然发现了以下问题。考虑到官方的纽约市出租车票价金额预测教程，假设我想预测另一个实际值，例如TripTime。我修改了我的代码如下：

public class TripFarePrediction // this class is used to store prediction result
{
    [ColumnName("Score")]
    public float FareAmount { get; set; }

    [ColumnName("Score2")]
    public float TripTime { get; set; }
}


private static ITransformer Train(MLContext mlContext, string trainDataPath)
{
    IDataView dataView = _textLoader.Read(trainDataPath);
    var pipelineForTripTime = mlContext.Transforms.CopyColumns("Label", "TripTime")
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("VendorId"))
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("RateCode"))
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("PaymentType"))
    .Append(mlContext.Transforms.Concatenate("Features", "VendorId", "RateCode", "PassengerCount", "TripDistance", "PaymentType"))
    .Append(mlContext.Regression.Trainers.FastTree());

    var pipelineForFareAmount = mlContext.Transforms.CopyColumns("Label", "FareAmount")
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("VendorId"))
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("RateCode"))
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("PaymentType"))
    .Append(mlContext.Transforms.Concatenate("Features", "VendorId", "RateCode", "PassengerCount", "TripDistance", "PaymentType"))
    .Append(mlContext.Regression.Trainers.FastTree());



    var model = pipelineForTripTime.Append(pipelineForFareAmount).Fit(dataView);
    SaveModelAsFile(mlContext, model);
    return model;
}

第一个值 ( FareAmount) 被“正确”预测（值不为零），但第二个值 ( TripTime) 为零。我的问题是如何同时预测两个或多个标签或至少使用相同的模型？这可能吗？我使用 .NET Core 2.2 和 ML.NET 0.10.0 来完成此任务。预先感谢您的任何帮助。

Answer 1

可能它不起作用，因为 Fit() 只返回“Label”和“Score”

看这里：这里

您的“TripTime”分数将被“FareAmount”覆盖。

我想，你必须建立两个模型。

编辑：你可以试试这个。将“分数”复制到正确的位置。

public class TripFarePrediction // this class is used to store prediction result
{
    [ColumnName("fareAmount")]
    public float FareAmount { get; set; }

    [ColumnName("tripTime")]
    public float TripTime { get; set; }
}


private static ITransformer Train(MLContext mlContext, string trainDataPath)
{
    IDataView dataView = _textLoader.Read(trainDataPath);
    var pipelineForTripTime = mlContext.Transforms.CopyColumns("Label", "TripTime")
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("VendorId"))
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("RateCode"))
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("PaymentType"))
    .Append(mlContext.Transforms.Concatenate("Features", "VendorId", "RateCode", "PassengerCount", "TripDistance", "PaymentType"))
    .Append(mlContext.Regression.Trainers.FastTree())
    .Append(mlContext.Transforms.CopyColumns(outputcolumn: "tripTime", inputcolumn: "Score"));

    var pipelineForFareAmount = mlContext.Transforms.CopyColumns("Label", "FareAmount")
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("VendorId"))
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("RateCode"))
    .Append(mlContext.Transforms.Categorical.OneHotEncoding("PaymentType"))
    .Append(mlContext.Transforms.Concatenate("Features", "VendorId", "RateCode", "PassengerCount", "TripDistance", "PaymentType"))
    .Append(mlContext.Regression.Trainers.FastTree())
    .Append(mlContext.Transforms.CopyColumns(outputcolumn: "fareAmount", inputcolumn: "Score"));



    var model = pipelineForTripTime.Append(pipelineForFareAmount).Fit(dataView);
    SaveModelAsFile(mlContext, model);
    return model;
}