rkaiwang Goto Github PK

basic-neural-net-

This is a basic single-hidden-layer neural net that takes in an array of 3 binary digits and classifies it as 1 or 0.

codewithxero2018

datacamp_candycrush

This is contains data and code created following a datacamp tutorial to analyse candy crush level difficulty

eda-0118

The exploratory data analysis done by club members during Semester 01, 2018.

hello-world-

A repository for storing files of interest

imdb-webscraper-nathan-for-you-

This code pulls ratings from the 'Nathan For You' imdb page and cleans the data in R so that a graph detailing the ratings by season is produced

iowa_housing_data_analysis

Analysis of Ames, Iowa Housing dataset as described in https://ww2.amstat.org/publications/jse/v19n3/decock.pdf

k-nearest-neighbours

This is a KNN model that takes in data from iris flowers and predicts which species of iris the flower belongs to. It uses the features sepal length, sepal width, petal length and petal width to predict the target variable species. The 3 different species are setosa, versicolor and virginica.

machine-learning-notes

My online shared notebook for Machine Learning notes

phyllotaxis_visualisation-

This is a visualisation made in R, inspired by patterns given by phyllotaxis. The ggplot2 package is used to map points onto a plot diagram, with plot labels removed, to form a visualisation.

python-blockchain-

This is simple blockchain which you can use to create basic transactions and verifications. It creates a local server to host the blockchain, and uses Postman to submit POST and GET requests in order to create transactions.

roguelike-experiments

Basic build for a rogue-like. Made following the Python 3 'Complete Rogue-like Tutorial' at RogueBasin. Source: http://www.roguebasin.com/index.php?title=Complete_Roguelike_Tutorial,_using_python3%2Blibtcod

simple-twitter-webscraper

This is a webscraper that uses Selenium webdriver to open a new window in Chrome and scrape tweets after selecting a search query. Currently set to search the keywords 'artificial intelligence'. It then uses the NLTK toolkit to tokenize the tweet data, remove stopwords, and produce a frequency distribution graph of the most commonly used words.