Namra Aziz

At Aga Khan University, I applied K-Modes clustering to data from diabetic patients to identify clinical subgroups for decision support and precision treatment strategies.

I also built a containerized Hadoop–Spark–Hive–Jupyter environment for genomic data analytics and processed FASTA data with Biopython in PySpark.

For digital recommendations to people with diabetes, I designed and deployed an MVP web application using Streamlit and Supabase. I also developed a news retrieval system with semantic search and a Streamlit interface.

My work includes an RNN recommender system, geospatial analysis for public health, and collaboration on an R Markov Model. I teach Python data analytics to healthcare researchers and developed a mathematics course outline for an upcoming health data science program.