tdszyman

shap

A game theoretic approach to explain the output of any machine learning model.

applied-ml

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

COVID-19

Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE

tfx

TFX is an end-to-end platform for deploying production ML pipelines

DataflowTemplates

Cloud Dataflow Google-provided templates for solving in-Cloud data tasks

Visualization

algorithms

Minimal examples of data structures and algorithms in Python

whitehouse

scripts to scrape and analyze data from whitehouse.gov, comparing pre- and post-inauguration versions in 2017

political_twitter_archive

twitter archives of political figures

feedsucker

Tool for collecting texts from a set of feeds and storing them in a relational database

fastText

Library for fast text representation and classification.

nltk

NLTK Source

pigeo

An Easy to Use, Accurate Python Geolocation Library

histwords

Collection of tools for building diachronic/historical word vectors

retrofitting

Retrofitting Word Vectors to Semantic Lexicons

langchangetrack

Package for Statistically significant linguistic change

bist-parser

Graph-based and Transition-based dependency parsers based on BiLSTMs

Spearmint

Spearmint Bayesian optimization codebase

models

Models and examples built with TensorFlow

word2phrase

Python port of Mikolov's word2phrase.c from the word2vec toolkit

neural-doodle

Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there's more! (An implementation of Semantic Style Transfer.)

feather

Feather: fast, interoperable binary data frame storage for Python, R, and more powered by Apache Arrow

awesome-public-datasets

A topic-centric list of HQ open datasets.

ucrdtw

Python extension for UCR Suite highly optimized subsequence search using Dynamic Time Warping (DTW)

rstWeb

Repository for rstWeb, a browser based annotation interface for Rhetorical Structure Theory

Theano_EC2

berkeley-entity

The Berkeley Entity Resolution System jointly solves the problems of named entity recognition, coreference resolution, and entity linking with a feature-rich discriminative model.

disambiguation

Efficient word sense disambiguation tools based on large RDF datasets

transorthogonal-linguistics

Uses a distributed word representation to finds words along the hyperchord of two input words.

lima

The Libre Multilingual Analyzer, a Natural Language Processing (NLP) C++ toolkit.