Databricks ML Professional

Practice Exam Questions & Study Guide

Section 1 of this course is free Notes for every focus area and practice questions. Create a free account, no card needed.

Full practice exams

100 questions from every section, weighted like the real exam. Practise at your own pace, or take it timed (150 min) for a score with a breakdown by section.

No matching topics. Try a different term.
1

Model Development (44%)Free

Covers building scalable ML pipelines with SparkML, distributed training and hyperparameter tuning, advanced MLflow usage, and Feature Store concepts for automated feature pipelines. (44% of scored content)

1.1: Using Spark ML

5 Question Sets Available

Covers selecting, constructing, tuning, evaluating, and scoring SparkML models for various use cases and inference types.

Focus Areas:
  • Identify when SparkML is recommended based on the data, model, and use case requirements
  • Construct an ML pipeline using SparkML
  • Apply the appropriate estimator and/or transformer given a use case
  • Tune a SparkML model using MLlib
  • Evaluate a SparkML model
  • Score a Spark ML model for a batch or streaming use case
  • Select SparkML model or single node model for an inference based on type: batch, real-time, streaming

1.2: Scaling and Tuning

1 Question Sets Available

Covers distributed training pipelines, hyperparameter tuning with Optuna and Ray, parallelization strategies, and the Pandas Function API for group-specific model training.

Focus Areas:
  • Scale distributed training pipelines using SparkML and pandas Function APIs/UDFs
  • Perform distributed hyperparameter tuning using Optuna and integrate it with MLflow
  • Perform distributed hyperparameter tuning using Ray
  • Evaluate the trade-offs between vertical and horizontal scaling for machine learning workloads in Databricks environments
  • Evaluate and select appropriate parallelization (model parallelism, data parallelism) strategies for large-scale ML training
  • Compare Ray and Spark for distributing ML training workloads
  • Use the Pandas Function API to parallelize group-specific model training and perform inference

1.3: Advanced MLflow Usage

1 Question Sets Available

Covers using nested runs, logging custom metrics and artifacts programmatically, and creating custom model objects with real-time feature engineering in MLflow.

Focus Areas:
  • Utilize nested runs using MLflow for tracking complex experiments
  • Log custom metrics, parameters, and artifacts programmatically in MLflow to track advanced experimentation workflows
  • Create custom model objects using real-time feature engineering

1.4: Advanced Feature Store Concepts

1 Question Sets Available

Covers point-in-time correctness, automated feature pipelines, online tables, streaming feature ingestion, and on-demand features for consistent use across training and production.

Focus Areas:
  • Ensure point-in-time correctness in feature lookups to prevent data leakage during model training and inference
  • Build automated pipelines for feature computation using the FeatureEngineering Client
  • Configure online tables for low-latency applications using Databricks SDK
  • Design scalable solutions for ingesting and processing streaming data to generate features in real time
  • Develop on-demand features using feature serving for consistent use across training and production environments
2

MLOps (44%)

Covers model lifecycle management, validation testing, environment architectures with Databricks Asset Bundles, automated retraining workflows, and drift detection using Lakehouse Monitoring. (44% of scored content)

2.1: Model Lifecycle Management

1 Question Sets Available

Covers designing and implementing model lifecycle pipeline architecture for environment transitions and mapping Databricks features to lifecycle management activities.

Focus Areas:
  • Describe and implement the architecture components of model lifecycle pipelines used to manage environment transitions in the deploy code strategy
  • Map Databricks features to activities of the model lifecycle management process

2.2: Validation Testing

1 Question Sets Available

Covers implementing unit and integration tests for ML systems across development environment stages and evaluating approaches for organizing functions and tests.

Focus Areas:
  • Implement unit tests for individual functions in Databricks notebooks to ensure they produce expected outputs when given specific inputs
  • Identify types of testing performed (unit and integration) in various environment stages (dev, test, prod, etc.)
  • Design an integration test for machine learning systems that incorporates common pipelines: feature engineering, training, evaluation, deployment, and inference
  • Compare the benefits and challenges of approaches for organizing functions and unit tests

2.3: Environment Architectures

1 Question Sets Available

Covers designing scalable Databricks ML environments and defining and configuring ML assets using Databricks Asset Bundles (DABs).

Focus Areas:
  • Design and implement scalable Databricks environments for machine learning projects using best practices
  • Define and configure Databricks ML assets using DABs (Databricks Asset Bundles): model serving endpoints; MLflow experiments; ML registered models

2.4: Automated Retraining

1 Question Sets Available

Covers implementing automated retraining workflows triggered by drift or performance alerts and developing strategies for selecting top-performing models.

Focus Areas:
  • Implement automated retraining workflows that can be triggered by data drift detection or performance degradation alerts
  • Develop a strategy for selecting top-performing models during automated retraining

2.5: Drift Detection and Lakehouse Monitoring

1 Question Sets Available

Covers applying statistical tests for drift detection, building monitors for various table types, configuring alerting, and evaluating model performance using Lakehouse Monitoring.

Focus Areas:
  • Apply any statistical tests from the drift metrics table in Lakehouse Monitoring to detect drift in numerical and categorical data and evaluate the significance of observed changes
  • Identify the data table type and Lakehouse Monitoring feature that will resolve a use case need and explain why
  • Build a monitor for a snapshot, time series, or inference table using Lakehouse Monitoring
  • Identify the key components of common monitoring pipelines: logging, drift detection, model performance, model health, etc
  • Design and configure alerting mechanisms to notify stakeholders when drift metrics exceed predefined thresholds
  • Detect data drift by comparing current data distributions to a known baseline or between successive time windows
  • Evaluate model performance trends over time using an inference table
  • Define custom metrics in Lakehouse Monitoring metrics tables
  • Evaluate metrics based on different data granularities and feature slicing
  • Monitor endpoint health by tracking infrastructure metrics such as latency, request rate, error rate; CPU usage, and memory usage
3

Model Deployment (12%)

Covers deployment strategies such as blue-green and canary, model rollout management, and custom model serving via PyFunc, REST API, and the MLflow Deployments SDK. (12% of scored content)

3.1: Deployment Strategies

1 Question Sets Available

Covers comparing deployment strategies for high-traffic applications and implementing model rollout using Databricks Model Serving.

Focus Areas:
  • Compare deployment strategies (e.g. blue-green and canary) and evaluate their suitability for high-traffic applications
  • Implement a model rollout strategy using Databricks Model Serving

3.2: Custom Model Serving

1 Question Sets Available

Covers registering custom PyFunc models in Unity Catalog, querying custom models via REST API or MLflow Deployments SDK, and deploying custom model objects.

Focus Areas:
  • Register a custom PyFunc model and log custom artifacts in Unity Catalog
  • Query custom models via REST API or MLflow Deployments SDK
  • Deploy custom model objects using MLflow deployments SDK; REST API or user interface