Machine Learning in your Data Warehouse using Python
summary
Loads telecom rows into Snowflake via Snowpark for Python, transforms into four dimension tables with the DataFrame API, trains a random forest in Deepnote and reports 98% balanced accuracy, packages the model as a Python UDF and deploys it back into Snowflake so predictions run without exporting data, writes results to a new table, and demonstrates that UDFs run on Snowflake compute and no data movement is required.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 0:45Goals and tools
- 1:47Motivation
- 3:12Deepnote and Snowpark
- 3:56Data pipeline setup
- 5:01Loading data
- 6:06Transforming data
- 7:31Staging tables
- 8:14Exploratory analysis
- 10:45Churn prediction model
- 11:51Deploying model
- 12:53Finalizing results
- 14:15Q&A
related talks
27mMachine Learning in the Warehouse with Python
29mScaling Python-Powered Machine Learning With Snowflake
23mAcceleratinag Data Science and Machine Learning with Snowflake DataTech
32mScalable Python and SQL Data Engineering without Migraines
21mUsing DBT and Python to Build Production Pipelines in Snowflake
37mIn database Machine Learning with Python in SQL Server
13mLightning Talk: Highlights of the Snowflake Elastic Data Warehouse
01h 13mBuilding a Semantic AI Layer in Snowflake: From Metrics to AI Insights