This repository presents a curated collection of applied data science projects, demonstrating the practical use of machine learning, data analysis, and visualization techniques.
-
Food Hazard Detection – Food:
This project contains code developed for the Food Hazard Detection Competition. It focuses on leveraging natural language processing and machine learning methods to detect potential food-related hazards from textual data. -
City Segmentation via Clustering – Clustering:
This notebook explores the GSV-Cities dataset from Kaggle. The objective is to apply unsupervised learning techniques, particularly clustering algorithms, to identify patterns and segment urban areas based on geospatial and visual data attributes. -
Proverb Analysis – Proverb:
This project investigates proverbs using data-centric methods. It includes tasks such as annotation agreement analysis and visualization using Python libraries, aiming to uncover linguistic and cultural patterns embedded in proverbs.