Data Science Portfolio

Welcome to my collection of data science experiments and solutions. Inside, you’ll find work spanning various domains, including web scraping, text processing, and machine learning. My projects include clustering and classification tasks, and sentiment analysis pipelines. Each project follows a data‑driven approach—from preprocessing and exploration to modeling and evaluation—demonstrating practical skills in turning raw information into meaningful insights. Dive in to explore methodologies, code, and results that showcase my passion for solving real‑world problems with AI and analytics.

AI related Article Detector

AI related Article Detector

Create a simple system that determines whether an article is related to AI or not using web scraping, text representation, and a classifier.

Sentiment Analysis

Sentiment Analysis

BERT-based classification pipeline with CLI, Streamlit & FastAPI deployment

Expense Tracker

Expense Tracker

A personal finance tracker where users can log and categorize their expenses.

Wikipedia Topic Clustering

Wikipedia Topic Clustering

Scrapes Wikipedia text, applies TF‑IDF vectorization, then clusters and visualizes topics with KMeans and UMAP.