Question

ML.Net预测分数始终返回NaN（空）。

这个想法是要教一个回归算法，以学习我的家人的日常工作。我尝试了ML.Net nuget程序包和代码示例的几个变体，但结果相同：Score == NaN。下面是一些代码和一部分数据集，这些数据是从我的家庭自动化系统记录的。

这是MSDN中电影推荐回归示例的一种变体：

        public class AutomationData
        {

            [LoadColumn(0)]
            //0 - 6
            public int Day; 
            [LoadColumn(1)]
            //example: 0947 == 9:47am
            public int TimeOfDay; 
            //Device Id
            [LoadColumn(2)]
            public int Device; 
            //This is the State of the device (0 OFF - 1 ON) 
            // Seems it has to be float? (Vector R4)
            [LoadColumn(3)]
            public float Label; 
        }

        public class AutomationPrediction
        {
            public float Label;

            public float Score;
        }

        public static void  Regression()
        {
            MLContext mlContext = new MLContext();
            IDataView trainingDataView = LoadData(mlContext).training;
            IDataView testDataView = LoadData(mlContext).test;

            ITransformer model = BuildAndTrainModel(mlContext, trainingDataView);
            EvaluateModel(mlContext, testDataView, model);

            UseModelForSinglePrediction(mlContext, model);

        }

        public static (IDataView training, IDataView test) LoadData(MLContext mlContext)
        {
            var trainingDataPath = Path.Combine(Environment.CurrentDirectory, "MachineLearning/Data", "data.csv");
            var testDataPath = Path.Combine(Environment.CurrentDirectory, "MachineLearning/Data", "data.csv");
            IDataView trainingDataView = mlContext.Data.LoadFromTextFile<AutomationData>(trainingDataPath, hasHeader: true, separatorChar: ',');
            IDataView testDataView = mlContext.Data.LoadFromTextFile<AutomationData>(testDataPath, hasHeader: true, separatorChar: ',');
            return (trainingDataView, testDataView); 
        }

        public static ITransformer BuildAndTrainModel(MLContext mlContext, IDataView trainingDataView)
        {
            IEstimator<ITransformer> estimator = mlContext.Transforms.Conversion.MapValueToKey(outputColumnName: "deviceEncoded", inputColumnName: "Device")
           .Append(mlContext.Transforms.Conversion.MapValueToKey(outputColumnName: "timeOfDayEncoded", inputColumnName: "TimeOfDay"))
            .Append(mlContext.Transforms.Conversion.MapValueToKey(outputColumnName: "dayEncoded", inputColumnName: "Day"));

            var options = new MatrixFactorizationTrainer.Options
            {
                MatrixColumnIndexColumnName = "deviceEncoded",
                MatrixRowIndexColumnName = "timeOfDayEncoded",
                LabelColumnName = "Label",
                NumberOfIterations = 20,
                ApproximationRank = 100
            };

            var trainerEstimator = estimator.Append(mlContext.Recommendation().Trainers.MatrixFactorization(options));


            ITransformer model = trainerEstimator.Fit(trainingDataView);
            return model; 
        }

        public static void EvaluateModel(MLContext mlContext, IDataView testDataView, ITransformer model)
        {

            var prediction = model.Transform(testDataView);
            var metrics = mlContext.Regression.Evaluate(prediction, label: DefaultColumnNames.Label, score: DefaultColumnNames.Score);

            Console.WriteLine("Rms: " + metrics.Rms.ToString());
            Console.WriteLine("RSquared: " + metrics.RSquared.ToString());

        }

        public static void UseModelForSinglePrediction(MLContext mlContext, ITransformer model)
        {

            var predictionEngine = model.CreatePredictionEngine<AutomationData, AutomationPrediction>(mlContext);
            var testInput = new AutomationData { Device = 117, TimeOfDay = 0945 };
            var automationPrediction = predictionEngine.Predict(testInput);
            Console.WriteLine("Prediction Score: " + Math.Round(automationPrediction.Score, 1)); //Is Always 'NaN' (null)
            if (Math.Round(automationPrediction.Score, 1) > 3.5)
            {
                Console.WriteLine("State: " + testInput.Label);
            }
            else
            {
                Console.WriteLine("State " + testInput.Label);
            }
        }

    }

这是回归算法尝试使用的data.csv的片段。

Day,TimeOfDay,Device,State
6,0827,999,1
6,0827,117,1
6,0827,117,0
6,0838,18,1
6,0838,79,1
6,0838,6,1
6,0901,117,1
6,0908,999,0
6,0910,73,0
6,0913,72,1
6,0914,72,0
6,0915,79,0
6,0915,6,0
6,0915,5,0
6,0915,4,0
6,0915,18,0
6,1015,18,1
6,1015,79,1
6,1015,6,1
6,1015,5,1
6,1015,4,1
6,1726,18,1
6,1726,79,1
6,1726,51,0
6,1726,128,0
6,1726,69,0

我希望预测状态返回的值为0或1（打开或关闭），以及得分（浮点数），这将显示回归认为正确的接近程度。

Answer 1

它返回 Nan ，因为没有足够的数据来进行预测。我的意思是，矩阵分解将以相似值的近似值进行预测。

在您的示例中，您仅使用矩阵分解中的TimeOfDay和Device列，因此，对于您要使用的单个预测（新的AutomationData {Device = 117，TimeOfDay = 0945}），该模型将返回 Nan 作为得分，因为它无法真正从学习的模型中预测值

进行测试，预测像这样的已知值

new AutomationData { Device = 73, TimeOfDay = 0910 };

您将获得实际分数。

此外，您不应该使用与测试相同的训练数据，这会使模型评估变得不必要。

毕竟，对于您的用例而言，矩阵分解可能不是理想的选择。

ML.Net预测分数返回NaN

1 个答案: