Skip to content

Latest commit

 

History

History
20 lines (14 loc) · 993 Bytes

README.md

File metadata and controls

20 lines (14 loc) · 993 Bytes

Welcome to my Project!

Started this project as part of Kaggle's 2022 NCAA Competition and wanted to use dbt to build the features used in predicting and analyzing NCAA tournament games.

Repo Includes:

  • Loading datasets from Kaggle to Bigquery via python script
  • Bulding models in dbt using SQL.
  • Adding additional data from Ken Pomeroy's site

References:

Data Lineage

Using dbt, did joins, aggregations and transforms to get the from source data (in green, Kaggle or Ken Pomery's site) tabular features using for EDA and data science. image