Pinned Loading

1. -ml-pipeline-k8s -ml-pipeline-k8s Public

   ML price prediction pipeline with FastAPI, MLflow, Docker and Kubernetes. Predicts producer prices for coffee, cocoa and bananas across major producing countries.

   Python

2. greenthread-dbt greenthread-dbt Public

   dbt + PostgreSQL analytics engineering project with staging/marts models, tests, and revenue anomaly detection

3. un-agri-commodity-pipeline un-agri-commodity-pipeline Public

   End-to-end PySpark medallion pipeline processing 22M+ rows of UN FAO trade data for coffee, cocoa and banana supply chains across 10 producer countries.

   Python

4. aws-lakehouse-analytics-engineering aws-lakehouse-analytics-engineering Public

   End-to-end cloud ELT pipeline on AWS using Terraform, AWS Glue, dbt, and Athena. Serverless data platform with layered SQL transformations and analytics-ready models.

   Python

5. ecommerce-crm-analytics ecommerce-crm-analytics Public

   RFM segmentation, churn prediction (XGBoost AUC 0.997), CLV modelling and A/B campaign evaluation on 100K+ orders from the Olist Brazilian E-Commerce dataset. Identifies 55,852 high-risk customers …

   Jupyter Notebook

6. un-agri-commodity-streaming un-agri-commodity-streaming Public

   Real-time Kafka streaming pipeline for UN FAO agricultural commodity data with PySpark Structured Streaming, data quality checks and 14/14 tests passing.

   Python