# Saving XGBOOst Model to PMML - possible now? **URL:** \ **Category:** KNIME Analytics Platform\ **Created:** [July 13, 2022, 1:34pm UTC](https://forum.knime.com/t/saving-xgboost-model-to-pmml-possible-now/45057 "2022-07-13T13:34:40Z")\ **Posts on this page:** 1\ **Showing post:** 5
**Author:** ![mlauber71](https://forum-cdn.knime.com/user_avatar/forum.knime.com/mlauber71/32/73590_2.png) [@mlauber71](https://forum.knime.com/u/mlauber71)\ **Post date:** [July 13, 2022, 10:13pm UTC](https://forum.knime.com/t/saving-xgboost-model-to-pmml-possible-now/45057/5 "2022-07-13T22:13:03Z")
@knimebine007 I toyed around with KNIME and Python and you could configure KNIME nodes that would use the XGBoost Python package and store the model in a local JSON file and reuse it with new data. The work will be done in Python but KNIME can create the workflow around. From what I see is XGBoost still under development and some settings in the cooperation between KNIME and Python and XGB are maybe a bit strange but they will work and the jobs can be repeated. The label is the column “Target” (0/1) and there is a “row\_id” present to stand for a possible customer number or ID to later bring the scores to another system. Some [XGBoost parameters](https://xgboost.readthedocs.io/en/stable/parameter.html) might have to be adapted. ![image](https://forum-cdn.knime.com/uploads/default/original/3X/9/b/9b119b5111e5e09f0bf02e13112069d8a6e51141.png) > **[use Python XGBoost package to build model and deploy that thru KNIME Python...](https://hub.knime.com/mlauber71/spaces/Public/latest/kn_example_python_xgboost~GBaTnzG3G4TsGhxo)** > > use Python XGBoost package to build model and deploy that thru KNIME Python nodes in the subfolder /data/ there is a Jupyter notebook to experiment and build X… In the subfolder /data/ there is a Jupyter notebook “_kn\_example\_python\_xgboost.ipynb_” where I tried to set up a running workflow. Data can be interchanged between [Jupyter and KNIME](https://forum.knime.com/t/unicodeencodeerror-charmap-codec-cant-encode-characters/39199/3). And notebooks might also be run from within KNIME. ![image](https://forum-cdn.knime.com/uploads/default/original/3X/b/e/be471e58693e01e2cb77707f5e6a81a5ea625b67.png) Yes indeed the whole thing might be somewhat over-engineered but I always wanted to set up such a workflow - in general you will be best served with just using the great [KNIME XGBoost integration](https://kni.me/e/Hj6XVP_9hCGqZuKK) 🙂 --- _[View the full topic](https://forum.knime.com/t/saving-xgboost-model-to-pmml-possible-now/45057)._