Jakob Aungiers's repositories
LSTM-Neural-Network-for-Time-Series-Prediction
LSTM built using Keras Python package to predict time series steps and sequences. Includes sin wave and stock market data
Multidimensional-LSTM-BitCoin-Time-Series
Using multidimensional LSTM neural networks to create a forecast for Bitcoin price
TensorFlow-Intro
Introduction to TensorFlow. Basic operators, linear and logistic regression and Tensorboard
Tinder-py_auto_liker
Short and dirty Python script to auto "swipe right" all Tinder profiles.
Random-Portfolio-vs-Benchmark-Strategy
Python Monte Carlo Simulation to model returns from randomly generated portfolios against a benchmark index.
Yahoo-Finance-Stocklist-Scraper
Converts the full Yahoo Finance stocks list into a .csv file with ticker symbol, company name, exchange and country mapped.
MvTAe-Multivariate-Temporal-Autoencoder
This code demonstrates a multi-branch deep neural network approach to tackling the problem of multivariate temporal sequence prediction by modelling a latent state vector representation of data windows through the use of a recurrent autoencoder and predictive model.
Code-Line-Counter
Python script for iterating directory and outputting total line counts for all file types
ImgResizeApi
Web API utilizing Python Flask, OpenCV & Numpy to dynamically re-size images.
keras-tools
A collection of tools and helper functions I've made for the Keras machine learning framework
R-Datastream
Simple framework library for communicating between Thompson Reuters Datastream service API and R
Neural-Network-OCR
A multi-layer neural network in Python to recognise characters from the MNIST dataset
Perceptron-Linear-Classifier
A simple single layer perceptron neural network classifier for linear classification
Websocket-Market-Data-Collector
Java based websocket data collector for crypto L2 market data saving to HDF5 files
zerow-motion-cam
Simple motion detection code for use with Raspberry Pi ZeroW and PiCamera