Snowflake Data Science Training

This course is intended for:

• Data scientists who build and train machine learning models.
• Data scientists and data analysts who use machine learning models to conduct predictive and prescriptive analytics.

We recommend that attendees of this course have:

• Basic knowledge of SQL is required.
• Foundational knowledge of databases.
• Python or some other object-oriented programming language.
• A background in data science, machine learning, or statistical modeling is required.
• Completion of “Snowflake Foundations” one-day course or equivalent Snowflake knowledge.

Module 1: Overview of Data Science with Snowflake

• Introduction to Data Science Workload
• Connecting to Snowflake

Module 2: Snowflake Data Storage

• Supported Object Types
• Supported Data Types
• SQL Support
• Cortex ML
• Cortex LLM
• The Variant Data Type
• Introduction to Unstructured Data
• Leveraging Unstructured Data
• What is Snowpark?

Module 3: Acquire Data

• Accessing External Data
• Loading Data into Snowflake
• Accessing Snowflake Data Worldwide with the Data Cloud

Module 4: Prepare Data

• Sampling Data
• Tidying Tables
• Transforming Data with Snowpark
• Table Streams and Tasks

Module 5: Perform EDA (Exploratory Data Analysis)

• Tools for EDA
• Univariate Regression in Snowflake
• Approximation Functions

Module 6: Perform Feature Engineering

• Feature Engineering in Snowflake
• Feature Engineering with Snowpark

Module 7: Train Models

• Overview of Machine Learning
• Snowpark ML
• Training Models with Snowpark Stored Procedures
• Stored Procedures
• Auto ML

Module 8: Deploy Models

• Batch Scoring
• Python Worksheets
• Snowflake User-Defined Functions (UDFs)
• Snowpark UDFs for Model Inference
• External Functions

Module 9: Beyond Deployment: ML Ops

• Improve Runtime Performance
• Monitoring
• ML Ops