Snowflake SnowPro Advanced Data Scientist Certification Exam

• Setup Environment: Use stages and tables to ingest and organize raw data from S3 into Snowflake
• Data Engineering: Leverage Snowpark for Python DataFrames in Snowflake Notebook to perform data transformations such as group by, aggregate, pivot, and join to prep the data for downstream applications.
• Data Pipelines: Use Snowflake Tasks to turn your data pipeline code into operational pipelines with integrated monitoring.
• Machine Learning: Process data and run training job in Snowflake Notebook using the Snowpark ML library, and register...
• Streamlit: Build an interactive Streamlit application using Python (no web development experience required) to help visualize the ROI of different advertising spend budgets.

• Familiar ClientSide Libraries Snowpark brings deeply integrated, DataFramestyle programming and OSS compatible APIs to the languages data practitioners like to use. It also includes the Snowpark ML API for more efficient ML modeling (public preview) and ML operations (private preview).
• Flexible Runtime Constructs Snowpark provides flexible runtime constructs that allow users to bring in and run custom logic. Developers can seamlessly build data pipelines, ML models, and data applications with UserDefined Functions and Stored Procedures.

• Summary of Functions
• Scalar functions
• Aggregate Functions
• Window Functions
• Table Functions
• System Functions
• Userdefined functions (UDFs)

• Heavy focus on Cortex features like Analyst, Agents, Search, and finetuning, plus Snowflake Copilot integration

• Setup, preprocessing docs (invoices/contracts), extraction with PARSE_DOCUMENT

Familiarity with basic ML concepts — training and test splits, regression, classification — is helpful. The course focuses on implementing ML workflows inside Snowflake using the Snowpark ML library rather than building algorithms from mathematical first principles.

Snowpark is a developer framework that lets you write Python (or Java and Scala) DataFrames that execute directly on Snowflake's compute engine without moving data out. It replaces the need to extract data to external Python environments for transformation, feature engineering, and model training.

The course covers Cortex ML functions including forecasting, classification, and sentiment analysis; Cortex Analyst for natural language queries; Cortex Search; Cortex Agents; and Snowflake Copilot integration — covering the full breadth of Snowflake's built-in AI capabilities.

Yes. The course content maps to the SnowPro Advanced Data Scientist exam objectives including Snowpark for Python, ML pipeline construction, Cortex AI features, Document AI, native statistical functions, and Streamlit application development within Snowflake.

Snowflake's Cortex feature set supports connections to external LLM providers. The course covers how to configure external model connections and use Cortex Analyst alongside OpenAI models to build hybrid AI workflows that combine Snowflake's data access with external generative AI capabilities.

Streamlit-in-Snowflake lets you build and deploy interactive Python web applications directly inside your Snowflake account — no separate hosting or infrastructure required. Data scientists use it to build dashboards, model demos, and interactive analytics tools with direct, secure access to Snowflake data and registered ML models.