About Me

Regardless of my degree of accounting, I ran a small business, delivering organic vegetables from farmers to home. As I always wanted to be a social entrepreneur and love healthy and chemical-free food, my shop was started to support eco-friendly agriculture and people's health. But up in my life popped another dot after I took an introduction to AI course while I was on working and holiday. Realizing that we can tackle problems with data, I have delved into data science since then.

Projects

NZ State Highway Traffic Analytics

ETL Pipeline  Container Orchestration  IaC  Data Engineering Zoomcamp 

This end-to-end pipeline provides daily traffic count across New Zealand State Highways which is designed to deliver key metrics such as vehicle counts, the most frequented monitoring sites, percent heavy load vehicles. The pipeline started from ingesting data from API, stored it in Google Cloud Storage, then transformed using dbt (data build tool) and uploaded it to data warehouse (Bigquery) for visualisation.

Code

COVID-19 X-ray Image Classification

Computer Vision  Deep Learning - CNN  Kaggle 

Classify X-ray images into three classes: Covid, Normal, and Viral Pneumonia using CNN model based on VGG-16 model.

Code

PM 2.5 Forecast

Time Series Analysis  Deep Learning - RNN  Data Collection 

How the quantity of an air pollutant - PM2.5 will be in the next 2 days? Analyse changes in air pollutants' levels over the period and forecast the air pollutants in the next 2 days using VAR compared to individual AR. Then, comparing PM2.5 forecast between using Autoregression and RNN models.

Code

Web Scraping for shoping on Amazon

Data Collection  Selenium  SQL 

This project uses selenium for scraping multiple amazon product search result pages and then stores the products' data scraped into sqlite3 database.

Blog Code

OKCupid Date a Scientist

Supervised ML  EDA  Codecademy

This project is a part of Codecademy – Data Science Career Path. To date someone, some people believe that zodiac sign may be a good signal to indicate whether they can get along with each other. However, many did not identify their signs. The initial goal of this project is to create a model that can predict signs for OKCupid users.

Blog Code

Biodiversity in National Parks

EDA  Data Analization  Data Visualization  Codecademy

This project is a part of Codecademy - Data Science Career Path. Given the data of species' observations in the U.S. national parks, the variations of species and species under conservation status were analysed and visualised. Then, the analysis report was written to communicate findings.

Code Report

GDP and Life Expectancy

Data Analization  Data Visualization  Codecademy

This project is a part of Codecademy - Data Science Career Path. Is there any relationship between GDP and life expectancy? If yes, the more GDP values are, the longer people were expected to live? This project aims at answering these questions.

Code
Courses & Certificates

Codecademy: Data Scientist Career Path

credentials

Python for Time Series Data Analysis

credentials

Deep Learning by DeepLearning.AI

credentials

Data Engineering Zoomcamp

credentials