Below are some of my projects and you can find more on my GitHub.

Osteoporosis Prediction

Designed a machine learning web app for osteoporosis prediction. The app is based on Neural Networks that being trained by the National Health and Nutrition Examination Survey (NHANES) data.

Skills: Machine Learning, Python, Web Application (Streamlit)

Code

Web App

Youtube Trending Videos ETL Pipeline and Analysis

Built a serverless ETL pipeline to get information of Youtube trending videos every day. Data is stored in AWS RDS MySQL database, analyzed by SQL, and visualized by AWS QuickSight.

Skills: Data collection with API, Python, MySQL, AWS, Docker

Code

California Hospitalization Data ETL Pipeline

Created an ETL pipeline for California hospitalization data. Data was collected from California Open Data and U.S. Census, saved in AWS S3, and visualized by Tableau.

Skills: Python, SQL, AWS, Tableau

Code

Tableau

Analysis of California 30-Day Inpatient Readmission Rates

Performed EDA and identified higher readmission rates were associated with patients that were aged 65+, males, covered by Medicare or Medi-Cal, and counties with lower ratios of rehabilitation clinics

Skills: Python, EDA, Data Visualization

Code

Airbnb Reviews Text Mining and Sentiment Analysis

Conducted text mining and sentiment analysis on Airbnb reviews in New York City, 2018-2022, to find out what guests cared about most and why they left negative reviews.

Skills: R, Text Mining, Sentiment Analysis, EDA, Data Visualization

Code