Microsoft.ML rel 0.8.0 error in fitting model

Question

I have a data set where I have 4 types of data

1. The to be predicted enum (label)
2. Trading hours enum
3. Direction enum
4. floating point values

I load the data the following configuration method, I have highlighted the text fields.

I fit my pipeline like this (screen shot due to the lines of code)

this causes an exception Result

StackTrace: 
at Microsoft.ML.Trainers.SdcaTrainerBase`3.TrainCore(IChannel ch, RoleMappedData data, LinearPredictor predictor, Int32 weightSetCount)
   at Microsoft.ML.Runtime.Learners.StochasticTrainerBase`2.TrainModelCore(TrainContext context)
   at Microsoft.ML.Runtime.Training.TrainerEstimatorBase`2.TrainTransformer(IDataView trainSet, IDataView validationSet, IPredictor initPredictor)
   at Microsoft.ML.Runtime.Data.LearningPipelineExtensions.DelegateEstimator`1.Fit(IDataView input)
   at Microsoft.ML.Runtime.Data.EstimatorChain`1.Fit(IDataView input)
   at Microsoft.ML.Runtime.Data.EstimatorChain`1.Fit(IDataView input)
   at Microsoft.ML.Runtime.Data.EstimatorChain`1.Fit(IDataView input)
   at Microsoft.ML.StaticPipe.Estimator`3.Fit(DataView`1 view)

What am I missing in my estimator?

Answer 1

the issue was in the multiclass nature of trend, ML.net is not dealing with it the way was intended, instead the datatype of enum's need to be uint values