Data Science Workshop (Badge 6)

Course Overview

Our Data Science Workshop (DSCW) introduces participants to the exciting world of Artificial Intelligence and Machine Learning within Snowflake. Learners will get hands-on experience with Cortex Playground, Cortex Analyst, various Large Language Models (LLMs), prompt engineering, forecasting, and classification. This workshop is highly interactive, featuring hands-on lab work and automated DORA checks to ensure understanding! It's designed to be fast-paced, informative, light in tone, and rich with scenario-based learning.

Prior Knowledge & Experience

We strongly advise completing Badge 1: Data Warehousing Workshop and Badge 2: Collaboration, Marketplace & Cost Estimation Workshop before starting this course. While not mandatory, having completed Badges 3, 4, and 5 of the Hands-On Essentials Series will further position learners for success in this advanced workshop.

Scenario Based

We join Camilla and Klaus, who you might recognize from previous adventures, as they decide to level up their skills by diving into Snowflake's AI and Machine Learning capabilities. Camilla, a nurse and youth futebol coach, and Klaus, who works in Data Operations, team up on a project centered around soccer statistics. Together, they'll explore how to use Snowflake's cutting-edge tools to analyze data from Camilla's team, from navigating the Cortex Playground to building predictive models. 

Learning Objectives 

• •Navigate and Leverage Snowflake's AI/ML Studio: Effectively utilize key components like Cortex Playground for LLM interaction and Cortex Analyst for creating semantic models to enable data insights.
• •Apply Core AI/ML Principles in Snowflake: Understand and implement fundamental AI/ML concepts, including prompt engineering, criteria for LLM selection (e.g., cost, availability), and structuring data with dimensions and measures.
• •Develop and Interpret Forecasting Models: Build, evaluate, and refine time-series forecasting models within Snowflake to predict future outcomes, including data preparation and understanding model predictions.
• •Construct and Analyze Classification Models: Create and assess classification models in Snowflake to categorize data effectively, including the interpretation of model outputs and feature importance.
• •Execute Foundational Snowflake Data Operations: Manage the Snowflake environment by setting up accounts, creating database objects, loading data, and defining table relationships in preparation for AI/ML tasks.
• •Solve Practical Data Science Challenges: Apply AI/ML techniques and Snowflake tools to address scenario-based problems, demonstrating an ability to translate theoretical knowledge into practical solutions.