kennethleungty
kennethleungty copied to clipboard
kennethleungty
Data Science Portfolio
👋 Hello, I'm Kenneth Leung
- Thanks for popping by! As an avid learner, bold builder, curious explorer, and driven doer with a bias towards action, I enjoy seeking and solving meaningful problems with data and technology while having fun at the same time.
- I welcome you to join me on a journey of data science discovery! Follow me on GitHub, Medium, and LinkedIn to stay updated with more engaging and practical content.
- You can find my data science portfolio here, where every project and article was born out of inspiration, curiosity, and motivation. Feel free to connect for a chat (coffee or virtual) to discuss shared interests and topics!
How to reach me
 
Portfolio Contents
- Computer Vision
- Database Management
- Data Extraction and Web Scraping
- Data Science Certification Guides
- Data Science Toolkit
- Data Science in the Real World
- Generative AI
- Insights from Data Science Talks
- Machine Learning
- MLOps
- Natural Language Processing
- Networks and Graphs
- Sports Analytics
- Visualization
- Web Development
- Web3 and Metaverse
- Writing for DataCamp
- Writing Tips
Projects with :star: are my personal favourites, so do check them out!
Computer Vision :eye:
| Title | Article | Repo |
|---|---|---|
| Classifying Images of Alcoholic Beverages with fast.ai v2 | :link: | :link: |
| Russian Car Plate Detection with OpenCV and TesseractOCR | :link: | :link: |
| Evaluate OCR Output Quality with Character Error Rate (CER) and Word Error Rate (WER) | :link: | :link: |
| Top Python libraries for Image Augmentation in Computer Vision | :link: | :link: |
| :star: PyTorch Ignite Tutorial - Classifying Tiny ImageNet with EfficientNet | :link: | :link: |
| Practical Guide to Transfer Learning in TensorFlow for Multiclass Image Classification | :link: | :link: |
Database Management :file_cabinet:
| Title | Article | Repo |
|---|---|---|
| :star: Definitive Guide to Creating a SQL Database on Cloud with AWS and Python | :link: | :link: |
| PyMySQL - Connecting Python and SQL for Data Science | :link: | :link: |
Data Extraction and Web Scraping :toolbox:
| Title | Article | Repo |
|---|---|---|
| Using OneMap API to extract Singapore postal codes, coordinates and travel distance | - | :link: |
| A Detailed Web Scraping Walkthrough Using Python and Selenium | :link: | :link: |
| :star: How to Web Scrape Wikipedia using LangChain Agents and Tools with OpenAI's LLMs and Function Calling | 🔗 | :link: |
Data Science Certification Guides :man_student:
| Title | Article | Repo |
|---|---|---|
| 3 Steps to Get AWS Cloud Practitioner Certified in 2 Weeks | :link: | :link: |
| 3 Steps to Get Tableau Desktop Certified in 2 Weeks | :link: | - |
| :star: No-Frills Guide to Passing the AWS Certified Machine Learning Specialty Exam | :link: | - |
Data Science Toolkit :hammer_and_wrench:
| Title | Article | Repo |
|---|---|---|
| Common Python codes for Data Wrangling | - | :link: |
| Enhance your Python code’s readability with pycodestyle | :link: | - |
| Free Resources for Generating Realistic Fake Data | :link: | - |
| Most Starred and Forked GitHub Repos for Data Science and Python | :link: | - |
| Most Starred and Forked GitHub Repos for Data Science and R | :link: | - |
| Automatically Generate Machine Learning Code with Just a Few Clicks | :link: | - |
| Read and Modify Image Metadata with Python | :link: | :link: |
| Top Tips to Google Search Like a Seasoned Data Scientist | :link: | - |
| How to Swap Day and Month of Incorrectly Formatted Excel Dates | :link: | - |
Data Science in the Real World :earth_asia:
| Title | Article | Repo |
|---|---|---|
| Exploring Illegal Drugs in Singapore — A Data Perspective | :link: | :link: |
| Pharmacokinetic Modeling of Drug Concentration Trajectories using Ordinary Differential Equations (ODE) and Global Optimization with Differential Evolution | - | :link: |
| Healthcare’s AI Future — In Conversation with Andrew Ng and Fei-Fei Li | :link: | - |
| Real-World Data Science Use Cases in the Insurance Industry | :link: | - |
| :star: Failed-ML: Compilation of high-profile real-world examples of failed machine learning projects | :link: | :link: |
Generative AI :robot:
| Title | Article | Repo |
|---|---|---|
| Generative AI Pharmacist - Macy | :link: | :link: |
| :star: ChatPod - Q&A over your Podcasts with Whisper, FAISS, and LangChain | :link: | :link: |
| :star: Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A | :link: | :link: |
| Domain LLMs - Compilation of Customized LLMs for Specific Domains and Industries | - | :link: |
| :star: Text-to-Audio Generation with Bark, Clearly Explained | :link: | :link: |
| Guide to ChatGPT's Advanced Settings — Top P, Frequency Penalties, Temperature, and More | :link: | - |
| Inside the Leaked System Prompts of GPT-4, Gemini 1.5, Claude 3, and More | :link: | - |
Insights from Data Science Talks :man_teacher:
| Title | Article | Repo |
|---|---|---|
| Bridging AI’s Proof-of-Concept to Production Gap — Insights from Andrew Ng | :link: | - |
Machine Learning :slot_machine:
| Title | Article | Repo |
|---|---|---|
| Exploring Condominium Rental Prices with Web Scraping and Exploratory Data Analysis | :link: | :link: |
| Using Ensemble Regressors to Predict Condominium Rental Prices | :link: | :link: |
| The Dying ReLU Problem, Clearly Explained | :link: | - |
| Why Bootstrapping Actually Works | :link: | - |
| :star: Assumptions of Logistic Regression, Clearly Explained | :link: | :link: |
| Data-Centric AI Competition - Tips and Tricks of a Top 5% Finish | :link: | :link: |
| Credit Card Fraud Detection with AutoXGB | :link: | :link: |
| :star: Micro, Macro & Weighted Averages of F1 Score, Clearly Explained | :link: | - |
| Principal Component Regression - Clearly Explained and Implemented | :link: | :link: |
| :star: Feature Selection with Simulated Annealing in Python, Clearly Explained | :link: | :link: |
| Quick Primer on Types of Missing Data and Imputation Techniques | :link: | - |
| Imputation of Missing Data in Tables with DataWig | :link: | :link: |
MLOps - Machine Learning Operations :man_mechanic:
| Title | Article | Repo |
|---|---|---|
| Key Learning Points from MLOps Specialization — Course 1/4 | :link: | :link: |
| Key Learning Points from MLOps Specialization — Course 2/4 | :link: | :link: |
| Key Learning Points from MLOps Specialization — Course 3/4 | :link: | :link: |
| Key Learning Points from MLOps Specialization — Course 4/4 | :link: | :link: |
| :star: End-to-End AutoML Pipeline with H2O AutoML, MLflow, FastAPI, and Streamlit for Insurance Cross-Sell | :link: | :link: |
| :star: How to Dockerize Machine Learning Applications Built with H2O, MLflow, FastAPI, and Streamlit | :link: | :link: |
| :star: Building and Managing an Isolation Forest Anomaly Detection Pipeline with Kedro | :link: | :link: |
Natural Language Processing :bookmark_tabs:
| Title | Article | Repo |
|---|---|---|
| COVID-19 Vaccine — What’s the Public Sentiment? | :link: | :link: |
| Keyword Extraction and Analysis Pipeline with KeyBERT and Taipy | :link: | :link: |
Networks and Graphs :globe_with_meridians:
| Title | Article | Repo |
|---|---|---|
| :star: Network Analysis and Visualization of Drug-Drug Interactions | :link: | :link: |
| How to Deploy Interactive Pyvis Network Graphs on Streamlit | :link: | :link: |
| A No-Code Approach to Building Knowledge Graphs | :link: | :link: |
Sports Analytics :soccer:
| Title | Article | Repo |
|---|---|---|
| :star: Analyzing English Premier League VAR Football Decisions | :link: | :link: |
| Combining Python and R for FIFA Football World Ranking Analysis | :link: | :link: |
Visualization :chart_with_upwards_trend:
| Title | Article | Repo |
|---|---|---|
| Uniform Singapore Energy Price and Demand Forecast Dashboard (with Plotly Dash) | - | :link: |
| Visualizing Fortune 500 Companies in a Bar Chart Race | :link: | :link: |
| How to Easily Draw Neural Network Architecture Diagrams | :link: | :link: |
Web Development :desktop_computer:
| Title | Article | Repo |
|---|---|---|
| :star: Post COVID-19 Vaccination Wait-Time Tracker (with Python Flask) | :link: | :link: |
| From HTTP to HTTPS — Easily Secure Flask Web Apps With Talisman | :link: | - |
| :star: Food King Directory (in collaboration with Night Owl Cinematics) | :link: | :link: |
Web3 and Metaverse :man_technologist:
| Title | Article | Repo |
|---|---|---|
| The Web3 / Metaverse Glossary — A Keyword Guide to the Tech Future | :link: | - |
Writing for DataCamp :writing_hand:
| Title | Article | Repo |
|---|---|---|
| :star: What Mature Data Infrastructure Looks Like | :link: | - |
| Democratizing Data in Government Agencies | :link: | - |
| A Survey Into Data Governance Tools | :link: | - |
| Scaling Data Science With Data Governance | :link: | - |
| 3 Reasons Why All Teams Should Learn SQL | :link: | - |
| 3 Reasons Why All Teams Should Learn R | :link: | - |
| How Tableau Helps Your Organization Achieve Greater Data Insights | :link: | - |
| How PowerBI Helps Your Organization Achieve Greater Data Insights | :link: | - |
Writing Tips :scroll:
| Title | Article | Repo |
|---|---|---|
| Create a Clickable Table of Contents for Your Medium Posts | :link: | - |
kennethleungty