Kuan Wei's repositories
Predict-Electricity-Demand-in-Ontario
This repository contains files and code for the project - "Forecasting Ontario’s Electrical Demand Using Machine Learning" - authored by Kuan Wei, Lucas Crea, Manuel Sage, and Jiarui Xie. We collected the hourly electricity demand in Ontario from the years 2017 to 2020 (https://www.ieso.ca/en/Power-Data/Data-Directory). Other features used for the predictions include time (converted into sine-cosine encoding), temperature (a weighted average temperature across six weather stations in the major population centers across the province: Hamilton, Kitchener, London, Ottawa, Toronto and Windsor, from https://climate.weather.gc.ca), and holiday information. Four machine learning models (RF, FCNN, LSTM, GRU) are used and their model performances are compared.
Implementing-A-Multi-Layer-Artificial-Neuron-Network-From-Scratch
In this notebook, I share a multi-layer artificial neural network that I developed from scratch with the feature of customizing the number of layers and the number of neurons in each layer. I also include the full math derivations using two simple examples to illustrate the principle of the algorithm. At the end, I also walk through the most important function in my classifier - the "fit" function - and explain step by step what the code does.
Build-InfoGAN-From-Scratch
GANs are widely used for synthesizing new data, especially images. However, one drawback of normal GANs is that we have no control over the images GANs produce. For instance, a GAN that is trained to produce fake hand-written digit images may be able to generate very real hand-written digit images, but we have no control over which number it generates. InfoGAN solved this problem: the network can learn to produce images with specific categorical features (such as digits 0 to 9) and continuous features (such as the rotational angle of the digits), in an unsupervised manner. In addition, because the learning is unsupervised, it is able to find the patterns hidden among the images, and generate images that follow these hidden patterns. Sometimes the model can learn very interesting patterns that are beyond your imagination (for example, one of my models learns to transit from number 2 to number 8. You will see it later!). In this notebook, I will introduce how InfoGAN achieves the control of the images being produced, and how to build an InfoGAN from scratch to synthesize feature-specific MNIST hand-written digits.
Project-Web-Scraping-Indeed-Data-Science-Jobs
Data Scientists and statisticians have recently become one of the most fast growing jobs in the last couple of years, due to the increasing value in utilizing big data. Many different companies across various of fields are seeking for data scientists in the job market. Out of curiosity, I want to know what are the most important skills that companies are looking for as data scientists. In this project, I created my own web scrapper and scraped the qualification information from 105 data scientist related job posts near Toronto, ON, Canada on Indeed.com.
Binary-Decimal-Converter
This repository contains the converter I designed that can convert the following:
Connect-Four-Game
This project contains the HTML code and the JavaScript for a web app that allows the users to play "Connect Four"
Algorithms
This repository lists some famous algorithms I reproduced in my own way.
BigJavaPracticeProblems
This repository contains code for all practice problems I attempt in Big Java Early Object 7th edition
Data-Science-Challenge
This repository is for Shopify Summer 2021 Data Science Challenge.
Data-Structures
This is a repository that contains the data structures built from strach
eBay-Predict-Used-Car-Prices
eBay Kleinanzeigen is a classfied advertising section of the German eBay website. Here I will work with a dataset which was orinigally scraped from eBay Kleinanzeigen, for the used car sell information. My goals are to: 1. identify which brand should a customer consider first, based on the popularity and the price. 2. generate a predictive model using linear regression to predict the prices of used cars with most popular brands.
Few-Shot-Learner-vs-Fine-Tuned-Learner-Which-Performs-Better-Across-Domains
This repository contains source code used for the McGill COMP550 Final Project, produced by Kuan Wei, Ze Dian Xiao, and Jon Xu. In this project, we studied in depth two state-of-the-art models for relation extraction - BERT-PAIR and REDN, and developed rigorous experiments to train the models and compare their performances across various domains of relation extraction tasks.
HackerrankCertifications
Here are solutions and databases from Hackerrank Certification Tests.
PySpark-Udemy
This is the PySpark codes for exercises in Udemy PySpark course
Python-Practice
This repository is my solution for the practice questions in Python
solutions
Solutions for projects.
SQL-Practice-
This repository is for SQL practice solutions
stanford-algs
Example Test Cases for Stanford's Algorithms Coursera Specialization
Sudoku_Solver
This is a Sudoku Solver that I designed. It uses backtrack and recursion to solve the Sudoku problems