Skip to content
View sienlonglim's full-sized avatar
11 followers · 14 following

Achievements

Achievement: Pull Sharkx2

Achievements

Achievement: Pull Sharkx2

Block or report sienlonglim

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sienlonglim/README.md
  • 👋 Hi, I’m Static Badge
  • 👀 I’m interested in Data Science, Data Engineering and Data Analytics. Anything related to AI/ML!
  • 🌱 I’m currently pursuing a Masters of Science in Analytics at Georgia Tech.
  • 💞️ I’m looking to collaborate on anything that can help me learn.
  • 📫 How to reach me Static Badge Static Badge Static Badge

Personal projects:

  1. Dagster-dbt-duckdb Pipeline
    Static Badge GitHub commit activity (branch)
  • Dagster for orchestration
  • S3 as data lake
  • Dbt for data modeling and transformation
  • DuckDB for data warehousing

  1. Document Query Bot (RAG Framework)
    Static Badge GitHub commit activity (branch) Static Badge
  • Document splitting
  • Embeddings (OpenAI)
  • Vector database (Chroma / FAISS)
  • Semantic search
  • Retrieval chain

  1. Job Finder
    Static Badge GitHub commit activity (branch) scheduled run main.py
  • Data mining
  • Automation with GitHub runners
  • S3 and SMTP integration

  1. HDB Resale Prices Predictor and Dashboard
    Static Badge GitHub commit activity (branch) Static Badge Static Badge Static Badge Static Badge
  • Large dataset involving geodata 🌏
  • Rest API calls to Data.gov.sg and OneMap API 🗺️
  • Feature creation and selection (KBest, L1 Regularisation)
  • Hyperparameter tuning (Random CV)
  • Ensemble models (Gradient boosting, Random forest)
  • Web Application (Flask) with Bootstrap 5

  1. Stock portfolio analysis (K-means), forecasting (ARIMA) and stock recommendation
    Static Badge GitHub commit activity (branch)
  • Web Scrapping (BS4)
  • ETL
  • RDBMS (MySQL)
  • K means clustering
  • ARIMA

  1. Web application for SkillsFuture website attendance taking summary
    Static Badge GitHub commit activity (branch)
  • Web Application (Flask) with Bootstrap 5
  • Telegram Bot API
  • RDBMS (MariaDB)

  1. EDA of Real Anonymized Financial Dataset with SQL (Czech Republic PKDD 99' Discovery Challenge)
    Static BadgeGitHub commit activity (branch) Static Badge
  • Database design (MariaDB - CLI, visualizer)
  • MariaDB with CLI and DBVisualizer
  • SQL queries, connectors
  • Report writing

Pinned Loading

  1. dbt-elt dbt-elt Public

    This project aims to build a modern data pipeline with CI/CD practices using Dagster and Dbt on top of DuckDB

    Jupyter Notebook

  2. ml_webapp ml_webapp Public

    This project utilises open data from Data.gov.sg to build several Machine Learning (ML) models that help predict HDB Resale Prices.

    Jupyter Notebook

  3. LangChain LangChain Public

    This project implements RAG using OpenAI's embedding models and LangChain's Python library

    Jupyter Notebook 14 2

  4. financial_analysis_forecasting financial_analysis_forecasting Public

    A web scrapper that retrieves your stock portfolio for cluster analysis and recommendation

    Jupyter Notebook 2

  5. job-finder job-finder Public

    This project automates job listing retrieval from LinkedIn via GitHub Actions

    Python

  6. healthhack healthhack Public

    This project implements RAG as a conversational model (Chatbot) for the purpose of explaining medical reports to patient. Part of HealthHack Singapore competition

    Jupyter Notebook 2