Project image for bestSelectR: R Package for Best Subset Selection in R [WIP]
Feature Selection R C++ Package Development

bestSelectR: R Package for Best Subset Selection in R [WIP]

An R package for best subset selection in logistic regression models, providing efficient algorithms using C++ and user-friendly functions in R.

Project image for Senticheck: Bluesky Data Collection and Analysis [WIP]
Python NLP Transformers Airflow

Senticheck: Bluesky Data Collection and Analysis [WIP]

Bluesky data collection and sentiment analysis project using Python, Airflow, and NLP. Currently in progress.

Project image for Forest Cover Type Classification
PySpark Random Forest Feature Engineering

Forest Cover Type Classification

Predicting forest cover types using cartographic variables and machine learning with Apache Spark (PySpark).

Project image for US Crime Rate Prediction
R GAMs Feature Engineering

US Crime Rate Prediction

Predicting crime rates in the US using GAMs and statistical modelling techniques.

Project image for Parkinson's Disease Detection with Hand-Drawn Spirals
Python PyTorch CNN Feature Engineering

Parkinson's Disease Detection with Hand-Drawn Spirals

Interactive dashboard built with Python and Plotly for real-time data visualization and analytics.

Project image for Fruit Images Classification with Deep Learning
Python Transfer Learning Computer Vision PyTorch

Fruit Images Classification with Deep Learning

Image classification model for cherries, strawberries, and tomatoes classification using PyTorch and transfer learning techniques.

Project image for Crash Insights NZ
R Shiny Data Visualization

Crash Insights NZ

An interactive dashboard built with R Shiny, analysing vehicle crash data in New Zealand with dynamic filters and comprehensive visualisations.

Technologies & Tools

Programming Languages

Python R SQL JavaScript C++

Data Science & ML

Scikit-learn PyTorch Transformers PySpark

Visualization

Plotly Matplotlib Shiny Streamlit

Tools & Platforms

Git Docker Azure Airflow