Question

我是机器学习的新手，我偶然发现了以下问题。考虑到an official NYC Taxi fare amount prediction tutorial，假设我想预测另一个实际值，例如TripTime。我修改了我的代码，如下所示：

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“正确地”预测（值不是零），但是第二个值（TripTime）为零。我的问题是如何一次或至少使用同一模型预测两个或多个标签？这有可能吗？我正在使用.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

可能不起作用，因为Fit（）仅返回“ Label”和“ Score”

查看此处：here

您从“旅行时间”中获得的分数将被“票价金额”所覆盖。

我想，您必须构建两个模型。

编辑：你可以试试看将“得分”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;
}

如何使用回归任务使用ML.NET预测多个标签？

1 个答案: