Week 1
- Introduction : Systems Thinking in Data-Driven Engineering
- Modern analytical architectures
- Mapping data pipelines to use cases
- Assessment: Concept map of a smart engineering system
2. Data Management and Scalable Engineering Systems
- 3h – Architectures: Data lakes, Delta Lake, streaming vs batch
- 3h – Tools: SQL, NoSQL, Delta tables, Parquet, ingestion with Kafka/MQTT
- 3h – Practice: Build a data pipeline using Pandas, SQL, and Kafka
- 3h – Capstone Kickoff: Define project goal, dataset, and tech stack
Key Outcomes:
- Design data pipelines for high-volume engineering datasets
- Efficient querying using SQL-like interfaces
- Launch capstone project with clear objectives
Week 2
- 3. Data Processing, Querying, and Feature Engineering
- 3h – High Volume Distributed processing (Dask, Spark), time-windowed analytics
- 3h – Advanced data cleaning, temporal aggregation, joins
- 3h – Practice: Use Dask/PySpark on sensor & spatial data
- 3h – Capstone: Build pipeline skeleton, run initial EDA
- – Satellite/open data integration
- – Tools: GeoPandas, Rasterio
- – Assessment: Remote sensing notebook + map visuals
Key Outcomes:
- Handle large time-series and sensor data efficiently
- Engineer features for machine learning and forecasting
- Develop reproducible workflows for data prep
Week 3
- 4. Analytics, AI Models, and Scalable Inference
- 3h – ML/DL model selection: forecasting, classification, clustering
- 3h – MLOps: model versioning, training pipelines, drift detection
- 3h – Practice: Train & log ML models using MLflow; deploy via FastAPI
- 3h – Capstone: Model training & first deployment demo
Key Outcomes:
- Implement and track scalable machine learning workflows
- Set up real-time or batch inference systems
- Translate data science models into deployed services
Week 4
5. Real-Time Decision Systems and Final Project Delivery
- 3h – Decision systems: optimization, control, dashboards
- 3h – Cloud deployment (Colab, AWS, Streamlit, Docker)
- 3h – Practice: Build dashboard + run cloud deployment
- 3h – Capstone: Final testing + presentations
Key Outcomes:
- Integrate analytics into actionable, real-time dashboards
- Complete and deploy full-stack capstone project
- Deliver technical presentation and documentation
Capstone Summary
Deliverables by end of Week 4:
- A GitHub repo with data pipeline, model, and deployment scripts
- Streamlit/FastAPI interface or cloud-hosted dashboard
- Documentation + 10-min presentation (recorded or live)
