https://github.com/paty-oliveira/snowflake-sephora-analytics
Repository to analyse customer reviews from Sephora products
https://github.com/paty-oliveira/snowflake-sephora-analytics
dbt hcl kaggle llm snowflake snowflake-cortex terraform
Last synced: about 2 months ago
JSON representation
Repository to analyse customer reviews from Sephora products
- Host: GitHub
- URL: https://github.com/paty-oliveira/snowflake-sephora-analytics
- Owner: paty-oliveira
- Created: 2025-05-14T17:43:07.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-06T14:43:08.000Z (about 1 year ago)
- Last Synced: 2025-06-21T16:41:31.928Z (12 months ago)
- Topics: dbt, hcl, kaggle, llm, snowflake, snowflake-cortex, terraform
- Language: HCL
- Homepage:
- Size: 8.2 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
This project analyzes customer reviews from the Sephora product dataset using Snowflake Cortex LLM functions to extract sentiment insights at scale. It demonstrates a modern data stack pipeline - from infrastructure as code with Terraform, to transformation and modeling with dbt, all running on Snowflake.
**Goal:** Use Snowflake Cortex's LLM capabilities to perform sentiment analysis on customer reviews.
**Dataset:** Kaggle Sephora product reviews dataset.
**Stack:**
- Infrastructure: *Terraform*
- Cloud Data Platform: *Snowflake*
- Transformation: *dbt*
- LLM Analysis: *Snowflake Cortex* function - `COMPLETE()`
**Features:**
- Provision Snowflake objects (warehouse, databases, schemas, roles) using Terraform
- Load and structure Sephora reviews into Snowflake
- Transform raw data using dbt models
- Apply Cortex LLM functions to summarize customer sentiment
- Enable downstream usage: dashboards, product team insights, or ML training