Skip to content
View nqabasikeyi's full-sized avatar

Block or report nqabasikeyi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
nqabasikeyi/README.md

Nqaba Sikeyi

Data scientist | Machine learning for climate and Earth-observation data MSc Computer Science candidate (Copperbelt University, expected 2027) · Zimbabwean, currently in Zambia Python · SQL · scikit-learn · geospatial analysis · PostgreSQL

I build machine learning and data analysis projects on satellite and climate data, and I explain the results in plain language, a skill from two years of teaching Computer Science and Mathematics.

Open to: data science and ML roles, research (PhD) positions, remote work or relocation.


Featured work

Urban Age Classification: cross-city transfer learning Classifies urban development age from multi-temporal Landsat features. Trains on Madrid and tests on Amsterdam, comparing zero-shot prediction with few-shot adaptation at 5–200 labelled pixels per class. Python, scikit-learn.

Zimbabwe Drought Analysis, 1981–2024 A 44-year assessment of meteorological drought using SPEI and SPI at four timescales, with Bulawayo as a local case study. Shows how accounting for evaporative demand changes drought assessments compared with rainfall alone. Google Earth Engine, pandas, SciPy.

Smart-Campus Distributed Monitoring and Load Balancing Simulated edge and fog services with threshold alerts and workload redistribution, plus a browser dashboard. Python, Flask, Docker Compose.

Netflix Titles ETL Pipeline Cleans and normalises a raw dataset into a relational schema and loads it into PostgreSQL. Python, SQL.


Skills

Machine learning and analysis: scikit-learn, pandas, NumPy, SciPy, time-series analysis, model evaluation, domain adaptation Geospatial and climate data: Landsat, ERA5-Land, TerraClimate, Google Earth Engine Data and software: SQL, PostgreSQL, Python, Flask, Docker Compose, Git/GitHub Learning now: PyTorch, PySpark, cloud (AWS) fundamentals


Find me

Portfolio · Kaggle · LinkedIn · X

Pinned Loading

  1. Zimbabwe-Drought-SPEI-Analysis Zimbabwe-Drought-SPEI-Analysis Public

    Climate drought analysis for Zimbabwe and Bulawayo (1981 - 2024) using SPEI, SPI, ERA5-Land and TerraClimate datasets. Examines drought severity, evapotranspiration methods, long-term variability, …

    Jupyter Notebook 1

  2. urban-age-classification urban-age-classification Public

    A machine learning project using Landsat satellite imagery to classify urban building ages. Explores feature engineering, model optimization, and cross-city transfer learning from Madrid to Amsterd…

    Jupyter Notebook 1

  3. iot-edge-load-balancing iot-edge-load-balancing Public

    This project was developed for the Distributed Systems course at CBU. It explores performance transparency in distributed systems within an IoT environment by simulating a smart campus architecture…

    Python 2