allentran

pca-magic

PCA that iteratively replaces missing data

graph2vec

Theano implementation of GloVe for graphs

golds-rl-gym

Cont. control RL algorithms and multi-agent environments

trust-rank

Overcoming sparsity in collaborative filtering via trust measures

vae-autocomplete

Varitational Autoencoder for completing short time series

deep-iv

Deep Learning + Instrumental Variables

reuters-nlp

Articles from Reuters Archive

allentran.github.io

Personal webpage

fed-rates-bot

Federal Reserve LSTM translator

keras-nmf

Keras Non-Negative Matrix Factorization

long-term-ate-orl

Code for "Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments"

euler-tran

Project Euler solutions

deep-regex

Magic for RegEx

dotty-dot-dot

secret dot files

finetune

Scikit-learn style model finetuning for NLP

gumbel-max-scm

Code for "Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models" (ICML 2019)

gym

A toolkit for developing and comparing reinforcement learning algorithms.

hackforla-maps

Mapbox Fun

HereOrThere

Django front-end for Instagram rankings

lambda-packs

Precompiled packages for AWS Lambda

ml-agents

Unity Machine Learning Agents

Newstitles

Script to get all titles found in www.nytimes.com and others

pacer_lib

reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

rl-l2t

Reinforcement learning paper + code: L2T

tennis-parser

Parser for Tennis Match Charting Project

tensorflow

Open source software library for numerical computation using data flow graphs.

util-rollercoaster

Utils

wordsegment

WordSegment is an Apache2 licensed module for English word segmentation, written in pure-Python, and based on a trillion-word corpus.

yelp-demeaning

Normalize Yelp ratings