Hi, I was wondering if there a function to get the posterior probability of a data point belonging to a specific class instead of the class labels in a binary classification problem?
I tried reading through the API docs and could not get through. I have my own functions in PySpark that do this, but I wanted to know if I could leverage MLLib's PySpark API for the same? For e.g. : # Evaluating the model on training data labelsAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features))) where model is a trained classifier. PS: Sci-kit learn has this feature which is helpful in machine learning tasks: model.predict_proba() Thanks, *Vedant Dhandhania*