Start data science with a Databricks overview

This introductory 2019 Tech Talk placed Databricks between raw data and a working machine-learning workflow. It was designed for readers who had heard of Spark but had not yet used a managed Spark workspace.

The original slide player is no longer embedded. Its Slideshare reference was 150116462.

What the session introduced

• Spark as a distributed processing engine.
• A shared workspace for notebooks and data work.
• The roles of Python, SQL, Scala, and R in the platform at that time.
• The handoff from data preparation to experiments and production work.

These points describe the 2019 session. Check current Databricks documentation before selecting a runtime, language, library, or deployment pattern.

The nine-part series

1. Data Science overview with Databricks
2. Titanic survival prediction with Azure Machine Learning Studio and Kaggle
3. Data engineering with the Titanic dataset, Databricks, and Python
4. Titanic with Databricks and Spark ML
5. Titanic with Databricks and Azure Machine Learning
6. Titanic with Databricks and AutoML
7. Titanic with Databricks and MLflow
8. Titanic with .NET and ML.NET
9. Deployment, DevOps, MLOps, and production

Use the series archive to find the retained posts.