Model: Artifacts, Package, Surrogate

Model Artifacts and Model Package

A model in Fiddler is a placeholder that may not need the model artifacts for monitoring purposes. However, for explainability, model artifacts are needed.

Required model artifacts include:

  • The **model file **(e.g. *.pkl)

  • A wrapper script containing all of the code needed to standardize the execution of the model.

A collection of model artifacts in a directory is referred to as a model package. To start, place your model artifacts in a new directory. This directory will be the model package you will upload to Fiddler to add or update model artifacts.

While the model file and are required artifacts in a model package, you can also optionally add other artifacts such as any serialized preprocessing objects needed to transform data before running predictions or after.

In the following, we discuss the various model artifacts.

Model File

A model file is a serialized representation of your model as a Python object.

Model files can be stored in a variety of formats. Some include

  • Pickle (.pkl)

  • Protocol buffer (.pb)

  • Hierarchical Data Format/HDF5 (.h5) wrapper script

Fiddler’s artifact upload process is framework-agnostic. Because of this, a wrapper script is needed to let Fiddler know how to interact with your particular model and framework.

The wrapper script should be named, and it should be placed in the same directory as your model artifact. Below is an example of what should look like.

from pathlib import Path
import pandas as pd

PACKAGE_PATH = Path(__file__).parent

class MyModel:

    def __init__(self):
        Here we can load in the model and any other necessary
            serialized objects from the PACKAGE_PATH.

    def predict(self, input_df):
        The predict() function should return a DataFrame of predictions
            whose columns correspond to the outputs of your model.

def get_model():
    return MyModel()

The only hard requirements for are

  • The script must be named

  • The script must implement a function called get_model, which returns a model object

  • This model object must implement a function called predict, which takes in a pandas DataFrame of model inputs and returns a pandas DataFrame of model predictions

Preprocessing objects

Another component of your model package could be any serialized preprocessing objects that are used to transform the data before or after making predictions.

You can place these in the model package directory as well.

📘 Info

For example, in the case that we have a categorical feature, we may need to encode it as one or more numeric columns before calling the model’s prediction function. In that case, we may have a serialized transform object called encoder.pkl. This should also be included in the model package directory.

requirements.txt file

📘 Info

This is only used starting at 23.1 version with Model Deployment enabled.

Each base image (see image_uri for more information on base images) comes with a few pre-installed libraries and these can be overridden by specifying requirements.txt file inside your model artifact directory where is defined.

Add the dependencies to requirements.txt file like this:


Surrogate Model

A surrogate model is an approximation of your model intended to make qualitative explainability calculations possible for scenarios where model ingestion is impossible or explainability is an occasional nice-to-have, but not a primary component of a model monitoring workflow.

Fiddler creates a surrogate when you call add_surrogate. This requires that you've already added a model using model.create.

🚧 Surrogates can currently only be created for models with tabular input types.

Fiddler produces a surrogate by training a gradient-boosted decision tree (LightGBM) to the ground-truth labels provided and with a general, predefined set of settings.

Custom dependencies

If you model artifact requires specific packages to run, Fiddler support Flexible Model Deployments. See here for details on how to configure your model with the correct requirements.

Last updated

© 2024 Fiddler AI