Closed vruusmann closed 2 years ago
See https://github.com/jpmml/jpmml-sklearn/issues/166#issuecomment-928173571
The pipeline has currently no idea that the XGBoost step interprets data differently from other steps. For example, in the linked issue, XGBoost thinks that 1 values represent missing values, whereas all other steps take 1 values valid values.
1
Was fixed in https://github.com/jpmml/jpmml-sklearn/commit/64a6e5a47a83cfec19152012ea38c150fd814123
See https://github.com/jpmml/jpmml-sklearn/issues/166#issuecomment-928173571
The pipeline has currently no idea that the XGBoost step interprets data differently from other steps. For example, in the linked issue, XGBoost thinks that
1
values represent missing values, whereas all other steps take1
values valid values.