surfcao

2015

AAU2015

Course material for spatstat workshop at Aalborg University

AlibabaRecommand

Alibaba 2015 mobile recommending algorithm competition.

architecture

What are we building?

BreakoutDetection

Breakout Detection via Robust E-Statistics

carmen

Geolocation for Twitter.

census

Source for census.ire.org, including data processing scripts.

deepdream

destin

Deep SpatioTemporal Inference Network (DeSTIN) for vision processing

EBOV-Cases

firefox-debloat

Stop Firefox leaking data about you

franc

Detect the language of text

gis-tools-for-hadoop

The GIS Tools for Hadoop are a collection of GIS tools for spatial analysis of big data.

h2o

h2o = fast statistical, machine learning & math runtime for bigdata

home

hotnews

Hot stories discovery based on wikipedia!

linux-insides

A little bit about a linux kernel

NBA_cron

Task scheduler that automatically runs scripts after each NBA game

neuraln

openaddresses

A repository of address data.

openstreetmap-website

Mirror of the Rails application powering http://www.openstreetmap.org (hosted at git://git.openstreetmap.org/rails.git)

opentraffic.github.io

pmtk3

Probabilistic Modeling Toolkit for Matlab/Octave.

PyDataNYC2014

"Analyzing Satellite Images With Python Scientific Stack" by Milos Miljkovic

r-census-tutorial-2015-05

Slides and installation instructions for my May 2015 tutorial on analyzing census data in R

R2Time

R connector for OpenTSDB: Analyzing large time-series data in R environment using data-intensive capabilities.

UmatiCodebase

The Umati Codebase is suite of analysis code built in R and Python for purposes of studying the propagation of inflammatory speech online. It also represents the machine translation of the Umati methodology on factors for identifying dangerous speech in Kenya

us-address-parser

US address parsing

WebPlotDigitizer

HTML5 based online tool to extract numerical data from plot images.

yenlp

NLP on Yelp's DataSet Challenge