Closed jonathanpeppers closed 2 years ago
Context: https://docs.microsoft.com/en-us/dotnet/api/microsoft.ml.data.multiclassclassificationmetrics.confusionmatrix?view=ml-dotnet Context: https://docs.microsoft.com/en-us/dotnet/machine-learning/how-to-guides/train-machine-learning-model-cross-validation-ml-net Context: https://github.com/dotnet/csharp-notebooks/blob/main/machine-learning/04-Model%20Evaluation.ipynb (Cross Validation)
I think we want to know the % accuracy of predicting a phrase is negative, some of those stats are printed here:
https://github.com/jonathanpeppers/inclusive-code-reviews-ml/blob/7ecf6a4c2cae94359da674973f89fc1fbe7d3fc9/ml.net/InclusiveCodeReviews.ConsoleApp/ModelBuilder.cs#L118-L151
I think we should fail the conversion process if the number goes lower than what we expect -- and also track progress of increasing the number.
Context: https://docs.microsoft.com/en-us/dotnet/api/microsoft.ml.data.multiclassclassificationmetrics.confusionmatrix?view=ml-dotnet Context: https://docs.microsoft.com/en-us/dotnet/machine-learning/how-to-guides/train-machine-learning-model-cross-validation-ml-net Context: https://github.com/dotnet/csharp-notebooks/blob/main/machine-learning/04-Model%20Evaluation.ipynb (Cross Validation)
I think we want to know the % accuracy of predicting a phrase is negative, some of those stats are printed here:
https://github.com/jonathanpeppers/inclusive-code-reviews-ml/blob/7ecf6a4c2cae94359da674973f89fc1fbe7d3fc9/ml.net/InclusiveCodeReviews.ConsoleApp/ModelBuilder.cs#L118-L151
I think we should fail the conversion process if the number goes lower than what we expect -- and also track progress of increasing the number.