data-normalization

FxNorm-Automix - Implementation of automatic music mixing systems. We show how we can use wet music data and repurpose it to train a fully automatic mixing system

Local-first Python CLI that turns Garmin Account Data Export into reproducible running, FIT, sleep, HRV, and training datasets with QA and provenance.

Term Project repository for System Analysis and Design course in ITM, Seoultech.

A utility for defining metadata for data types and formats.

Developed a Python-based web scraper leveraging generative AI with LangChain and GPT-4o-mini to extract and classify FDA drug approval data. Processed over 1,770 records, dynamically categorizing medications and treatment areas using LLMs to simplify complex medical information into actionable insights.

I made various data normalization operations with python scripts. Target data in CSV format

A production-ready serverless pattern for intelligent data normalization using Claude Haiku via AWS Bedrock

A large pile of interesting and/or useful information

This project predicts used car prices using a feedforward neural network regression model implemented in PyTorch. Features include car age, mileage, and other attributes. The pipeline supports feature normalization, train/validation/test splitting, and visualization of training and validation loss curves.

Clinical Decision Support System (CDSS) for Emergency Triage. Python implementation of regional healthcare protocols featuring complex logic, input normalization, and automated clinical pathways

govaitextextract extracts structured AI/tech initiative data from text for policy, news, and recruitment analysis.

An end-to-end data engineering project that extracts book metadata from the Open Library API, transforms and normalizes it into a relational PostgreSQL database, and exposes the curated dataset through a FastAPI REST API. The project also extends into an event-driven library simulation using Kafka and Redis for real-time state management.

A collection of bioinformatics and data mining scripts

A Streamlit-based clinical decision-support demo showcasing data cleaning, normalization, rule-based recommendation logic, and workbook-driven pipeline design.

Production-oriented Python pipeline for EAN product data extraction with resumable processing, validation, retry logic, and structured output.

🌟 Fraud Detection in Application 🌟 Through Isolation Forest and K-Means Clustering, the project detects suspicious patterns like inconsistent income, duplicate entries, and unrealistic employment data. This end-to-end workflow transforms raw data into actionable fraud insights — enhancing trust and accuracy.

Feature wise normalization: An effective way of normalizing data

Evidence-first technical pre-screening for web-business acquisitions. Built with Next.js, FastAPI, PostgreSQL, Redis, Dramatiq, and Playwright.

✨ Stock Price Prediction Using Tesla Dataset ✨ In this project, I analyzed Tesla’s historical stock data to forecast future closing prices using machine learning models like Random Forest Regressor. Through data cleaning, feature engineering, and rich visual analytics, I explored patterns in price trends, volatility, and trading volume.

Data cleaning and preprocessing of the Netflix titles dataset using Python and Pandas. Tasks included handling missing values, removing duplicates, normalizing categorical data, and preparing the dataset for further analysis.