Model's predicted values are not the same when using Dataiku API to retrieve the model and use it in python

Highlighted
minliang1215
Level 1
Model's predicted values are not the same when using Dataiku API to retrieve the model and use it in python

I built an XGBoost model in DSS, and retrieved it using the Dataiku API inside python recipe. However, when I use the predict() function on the retrieved model object, the predicted values are not the same as they appear in the original model.



true value and predicted value in the original model object

0 Kudos
1 Reply
UserBird Dataiker
Dataiker
Re: Model's predicted values are not the same when using Dataiku API to retrieve the model and use it in python

Hi,



The original model apply a set of preprocessing on data before doing the prediction. If you want to reproduce the result, you can use directly `my_predictor.predict()`. 



Another thing to be aware is that in the scoring recipe, for reproducebility, you should check the Force backend engine option





Cheers, 

0 Kudos
Labels (3)