How to get the Probability of a prediction from Real Time Inference model

Machine Learning

Dive into the world of machine learning on the Databricks platform. Explore discussions on algorithms, model training, deployment, and more. Connect with ML enthusiasts and experts.

Hello,

I have used AutoML to create a model. When using that model I want to have the probability of the predictions returned. I was able to do this in a notebook with:

loaded_model = mlflow.pyfunc.load_model(logged_model)

# Predict on a Pandas DataFrame.

import pandas as pd

loaded_model.predict_proba(pd.DataFrame(data))

I have since registered the model and deployed a Real Time Inference endpoint for this model.

When calling the API I only get a true/false response like so:

{

"predictions": [

true

]

}

It is not clear to me how to change or update the model to return a probability. Any help would be much appreciated.