XGBoost Convert to ONNX

How to convert XGBoost to ONNX using the onnxmltools.convert library

This tutorial and the assets can be downloaded as part of the Wallaroo Tutorials repository.

How to Convert XGBoost to ONNX

The following tutorial is a brief example of how to convert a XGBoost ML model to the ONNX standard. This allows organizations that have trained XGBoost models to convert them and use them with Wallaroo.

This tutorial assumes that you have a Wallaroo instance and are running this Notebook from the Wallaroo Jupyter Hub service.

This tutorial provides the following:

Conversion Process


The first step is to import our libraries we will be using.

import onnx
from onnxmltools.convert import convert_xgboost

from skl2onnx.common.data_types import FloatTensorType, DoubleTensorType

Set Variables

The following variables are required to be known before the process can be started:

  • number of columns: The number of columns used by the model.
  • TARGET_OPSET: Verify the TARGET_OPSET value taht will be used in the conversion process matches the current Wallaroo model uploads requirements.
# set the number of columns
ncols = 18

# derive the opset value

# from onnx.defs import onnx_opset_version
#from onnxconverter_common.onnx_ex import DEFAULT_OPSET_NUMBER
#TARGET_OPSET = min(DEFAULT_OPSET_NUMBER, onnx_opset_version())


Load the XGBoost Model

Next we will load our model that has been saved in the pickle format and unpickle it.

# load the xgboost model
with open("housing_model_xgb.pkl", "rb") as f:
    xgboost_model = pickle.load(f)

Conversion Inputs

The convert_xgboost method has the following format and requires the following inputs:

convert_xgboost({XGBoost Model}, 
                {XGBoost Model Type},
                    {Tensor Data Type}([None, {ncols}]))
  1. XGBoost Model: The XGBoost Model to convert.
  2. XGBoost Model Type: The type of XGBoost model. In this example is it a tree-based classifier.
  3. Tensor Data Type: Either FloatTensorType or DoubleTensorType from the skl2onnx.common.data_types library.
  4. ncols: Number of columns in the model.
  5. TARGET_OPSET: The target opset which can be derived in code showed below.

Convert the Model

With all of our data in place we can now convert our XBBoost model to ONNX using the convert_xgboost method.

onnx_model_converted = convert_xgboost(xgboost_model, 'tree-based classifier',
                             [('input', FloatTensorType([None, ncols]))],

Save the Model

With the model converted to ONNX, we can now save it and use it in a Wallaroo pipeline.

onnx.save_model(onnx_model_converted, "housing_model_xgb.onnx")