Multiple Disease Prediction System
Two separate clinical datasets, two separate models — and no way for anyone without a notebook to actually use either of them.
Thisara Anjana
I build machine learning and AI systems — prediction models, agentic AI applications, and the MLOps that takes them from notebook to deployment.
About
ICT undergraduate at the University of Vavuniya, Sri Lanka.
I build machine learning systems rather than one-off notebooks: the model, plus the pipeline, tracking and packaging that make it reproducible. My current focus is AI engineering — retrieval-augmented and agentic applications on top of solid ML fundamentals.
Everything claimed on this page links to a public repository. If there is no repository behind it, it is marked as coursework instead.
- AI Engineering
- Machine Learning
- Agentic AI
- MLOps
- Data Science
Skills
Grouped by what I actually use them for.
AI / Machine Learning
- Python
- Scikit-learn
- Pandas
- NumPy
- Machine Learning
- Deep Learning
AI Engineering
- LangChain
- RAG
- Agentic AI
- LLM Applications
- Context Engineering
MLOps / Cloud
- MLflow
- Docker
- AWS
- Airflow
- GitHub Actions
Development
- SQL
- Git
- GitHub
- REST APIs
Featured Projects
Applied machine learning, AI and software engineering — each one backed by a public repository.
Music Recommendation System
Recommendation has no single right answer, so it can't be evaluated the way a classifier is.
Manorcraft — Home Services Platform
A home services brand needs more than a brochure page: customers book jobs, technicians pick them up and an admin has to see both.
Airflow ETL Pipeline with PostgreSQL
A one-off script that loads data is fine once. It isn't fine on a schedule, where a failed step needs to be visible, retried and re-run from where it broke.
End-to-End Data Science Project
Research notebooks and shipped code usually diverge: the notebook explores, the app re-implements, and the two disagree.
MLflow Experiment Tracking on AWS
Comparing model runs from terminal output does not scale past a handful of experiments, and a model on a laptop can't be used by anything else.
Certifications
Short courses with verifiable certificates. Open one to read it without leaving the page.
Experience & Education
A short progression, with the project work each stage led to.
Final-Year BICT (Hons.) Undergraduate
University of Vavuniya, Sri Lanka
ICT undergraduate
Started the ICT degree at the University of Vavuniya — programming, databases and networking as the base, with statistics and software design alongside.
Programming fundamentals
Small self-contained projects to get comfortable writing code that others run: a Sudoku solver, a Space Invaders clone, a desktop chat app and an Android video player.
Machine learning models
Supervised learning on real datasets — heart disease, Parkinson's and diabetes prediction, sonar rock-vs-mine classification, fake news detection and laptop price regression — plus a music recommender.
Data engineering
Moved from hand-run notebooks to scheduled work: an Airflow DAG doing extract, transform and load into PostgreSQL, running under docker-compose.
Reproducible pipelines
Staged training with DVC so preprocess → train → evaluate re-runs from a commit, with data and models tracked as pointers rather than blobs.
MLOps & deployment
Experiments tracked in MLflow, the app packaged in Docker behind Flask, tests wired into GitHub Actions, and tracking plus serving moved onto AWS.
BSc (Hons) Information and Communication Technology
Undergraduate degree covering programming, databases, networking and systems, alongside self-directed work in machine learning and MLOps.
Programming · Databases · Networking · Software design · Statistics · Systems
Technical Activity
Everything I build is public and readable.
- 23
- Public repositories
- 5
- Languages used
- 0
- Total stars