Обучение настроениям не удалось с ML.NET - PullRequest
0 голосов
/ 11 октября 2019

Я создал файл .csv, содержащий предложения и результаты, а также идентификатор. Я выбрал Sentiment Analysis в качестве опции. Я выбрал колонку Result в качестве предсказываемого и предложения для ввода, однако это дает мне исключение.

Id  Result  Sentiment Text
1   1   I loved the sunset that day.
2   0   I was not a fun experience. 
3   1   I am happy.
4   0   Her mother died yesterday and I am really worried about her.
5   1   It was a good day filled with little children laughing in the part.
6   1   Both great!
7   0   The situation was strange and I was angry.
8   0   The car was very nasty, old and dirty.
9   1   I saw a cute couple holding hands on a sunny day. 
10  0   I hate how some people do not listen to you.
11  0   I was sad because they didn't give me the promotion they promised. 
12  0   I worked hard with no pay-off. 
13  1   They gave me the best inventor award and I am excited.
14  1   I finally bought the quality laptop that I needed. 
15  0   I can't believe he lied in front all of the staff. 

Ошибка:

|     Trainer                              Accuracy      AUC    AUPRC  F1-score  Duration #Iteration             |
AUC is not defined when there is no positive class in the data
Parameter name: PosSample
AUC is not defined when there is no positive class in the data
Parameter name: PosSample
Value cannot be null.
Parameter name: items
Training failed with the exception: System.ArgumentNullException: Value cannot be null.
Parameter name: items
   at System.Collections.Immutable.Requires.FailArgumentNullException(String parameterName)
   at System.Collections.Immutable.ImmutableArray.Create[T](T[] items, Int32 start, Int32 length)
   at Microsoft.ML.Trainers.FastTree.RegressionTreeBase..ctor(InternalRegressionTree tree)
   at Microsoft.ML.Trainers.FastTree.TreeEnsembleModelParametersBasedOnRegressionTree.<>c.<CreateTreeEnsembleFromInternalDataStructure>b__5_0(InternalRegressionTree tree)
   at System.Linq.Enumerable.WhereSelectListIterator`2.MoveNext()
   at System.Collections.Generic.List`1..ctor(IEnumerable`1 collection)
   at System.Linq.Enumerable.ToList[TSource](IEnumerable`1 source)
   at Microsoft.ML.Trainers.FastTree.TreeEnsemble`1..ctor(IEnumerable`1 trees, IEnumerable`1 treeWeights, Double bias)
   at Microsoft.ML.Trainers.FastTree.TreeEnsembleModelParametersBasedOnRegressionTree.CreateTreeEnsembleFromInternalDataStructure()
   at Microsoft.ML.Trainers.LightGbm.LightGbmBinaryTrainer.CreatePredictor()
   at Microsoft.ML.Trainers.LightGbm.LightGbmTrainerBase`4.TrainModelCore(TrainContext context)
   at Microsoft.ML.Trainers.TrainerEstimatorBase`2.TrainTransformer(IDataView trainSet, IDataView validationSet, IPredictor initPredictor)
   at Microsoft.ML.Data.EstimatorChain`1.Fit(IDataView input)
   at Microsoft.ML.AutoML.RunnerUtil.TrainAndScorePipeline[TMetrics](MLContext context, SuggestedPipeline pipeline, IDataView trainData, IDataView validData, String labelColumn, IMetricsAgent`1 metricsAgent, ITransformer preprocessorTransform, FileInfo modelFileInfo, DataViewSchema modelInputSchema, AutoMLLogger logger)
...