kohjiaxuan
Follow
Stars
Python package to scrape stock prices, descriptions, and news from Google Finance
Data Project of Predicting HDB Resale Flat Prices with data cleaning, feature engineering and machine learning. Models used: Random Forest, XGBoost, Neural Networks, Decision Tree, Support Vector R…
Anomaly detection tutorial on univariate time series with an auto-encoder
Thio - a playground for real-time anomaly detection
📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.
Perspective recovery of text using transformed ellipses
This is yet simple logic based program which uses python language and opencv module to measure speed of object without requiring any expensive hardware.
A python wrapper for Alpha Vantage API for financial data.
A structured data science pipeline for classification problems that does scaling, sampling, k-fold cross validation with evaluation metrics
Python assignments for the machine learning class by andrew ng on coursera with complete submission for grading capability and re-written instructions.
What influences HDB prices? What fluctuations do HDB prices undergo? In this project, I will look at major patterns of HDB resale prices normalized for inflation and flat size, where certain non-in…
An implementation of the Viterbi Algorithm for training Hidden Markov models. This repo accompanies the video found here: https://www.youtube.com/watch?v=kqSzLo9fenk
By visualizing the gradient descent algorithm applied on a set of points that fits a quadratic equation, we understand better how the algorithm works in machine learning
Creating a stock market dashboard from an external API that tracks daily performance of stocks
A complete Python text analytics package that allows users to search for a Wikipedia article, scrape it, conduct basic text analytics and integrate it to a data pipeline without writing excessive c…
Data Science Competition that challenged teams to come up with creative ways to increase the revenue of an e-commerce company. Won 1st place! Write-up in repository
A NLP algorithm I developed to determine the similarity or relation between two documents/Wikipedia articles. Inspired by the cosine similarity algorithm and built from WordNet.