ModuleExceptionMessage:ColumnUniqueValuesExceeded: Number of unique values in column: ds is greater than allowed.

Vik Manne 6 Reputation points
2020-08-12T17:42:15.8+00:00

We are trying to train a model using the Boosted Tree Regression model and running into the "ModuleExceptionMessage:ColumnUniqueValuesExceeded: Number of unique values in column: "ds" is greater than allowed." error.

This is a time series data and it is going to have unique values in the timestamp - how are we supposed to get around the issue.

PS: When using the exact same dataset in the classic studio it runs fine and does not throw this error.

The big picture: We are happy with studio based results on the prediction however, there isn't a way to fully end to end automate, meaning retrain the model with latest data and use the API to download the results in classic version. We are looking to use the new Azure ML pipelines and endpoints etc but quite frankly all of this is turning out be quite complex than needed for some reason. And the documentation to retrain the models shows a mixture of classic and new azure ml steps which is quite frustrating.

Azure Machine Learning
Azure Machine Learning
An Azure machine learning service for building and deploying models.
2,846 questions

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.