Data Science Weekly Newsletter

Issue

119

March 3, 2016

‍

Editor's Picks

‍

Analyzing the Language of the Presidential Debates
Viewing the debates through the lens of data science, fascinating and often unexpected insights into the candidates can reveal themselves, many of which might not be immediately apparent through subjective viewing. We’ll look at the candidates’ transcripts from the debates and see what can be gained by applying statistical and natural language processing (NLP) techniques to their words...

Google's Computers Are Making Thousands as Artists
Artificial intelligence was the star of the show at a San Francisco art auction. Google’s artificial intelligence, or shall I say “painters,” raked in thousands for charity over the weekend in San Francisco at an art show called “DeepDream: The art of neural networks.”...

Interactive Map: Hong-Kong through The Lense of Instagram
Interactive map of Hong Kong that visualizes all the Instagram activity of the city. The map is telling a story about life in Hong Kong, by showing who posts what and from which locations. The research is unique because it’s the first and the only one that defines demographic characteristics and income rate of Instagram users in Hong Kong...

‍

‍

RJMetrics Pipeline: All Your Data in Redshift
RJMetrics Pipeline connects to the systems you use and streams that data to Amazon Redshift, ready for you to analyze. Query data from Salesforce, Postgres, Stripe, MongoDB, and 30 more integrations in SQL or in your favorite BI tool. Setup takes five minutes or less, start your free 14-day trial today!

‍

‍

Visualizing the Clinton Email Network in R
This isn’t a post about politics. I do have opinions about the now infamous e-mail server (which will no doubt come out here), but when the WSJ folks made it possible to search the Clinton email releases I though it would be fun to get the data into R to show how well the igraph and ggnetwork packages could work together, and also show how to use svgPanZoom to make it a bit easier to poke around the resulting hairball network...

Pictures combined using Neural networks
Based on the "A Neural Algorithm of Artistic Style"...

An Analysis of the Flint Michigan Water Crisis: Part 1 Initial Corrosivity
In this analysis we will be exploring data from the US Geological Water Quality Survey to analyse the Flint incident starting at the source or pre-treated water as well as nearby streams in Detroit and near Lake Huron...

Data Mining the Next Series to Watch - Part 1
I tried to kind of automate the process of deciding which movie or series to watch next and I ended up writing this instead...

Super Bowl 50 According to Twitter
This is a step-by-step guide to collecting and analysing tweets related to Super Bowl 50. Our original plan was to try and use a combination of data collected from twitter and seasonal performance stats from each team to predict the outcome of Super Bowl 50. While this didn't quite work out it was still quite an interesting use case and application of Text Analysis to large datasets...

Do Brand Colors Translate to Instagram?
Starbucks green. UPS brown. Target red. Some of the most recognized brands have built their visual identity on just one color. We were curious: how does this color-centric visual identity carry over to social media and, more specifically, Instagram? If we boiled down a brand’s Instagram photos to a handful of colors, could you identify the brand?...

The Digg Video Recommender
Here’s the thing about the Internet: there’s a lot of it and not everything is gold. The job of a news aggregator is to sort through each day’s daily dose of Internet and choose the most interesting and relevant stories and videos for you people. Different sites have taken different approaches to this problem...

Google Unveils Neural Network with “Superhuman” Ability to Determine the Location of Almost Any Image
Here’s a tricky task. Pick a photograph from the Web at random. Now try to work out where it was taken using only the image itself. If the image shows a famous building or landmark, such as the Eiffel Tower or Niagara Falls, the task is straightforward. But the job becomes significantly harder when the image lacks specific location cues or is taken indoors or shows a pet or food or some other detail...

TensorFlow for Poets
EC2 for Poets is an explanation of cloud computing that removes a lot of the unnecessary mystery by walking anyone with basic computing knowledge step-by-step through building a simple application on the platform. In the same spirit, I want to show how anyone with a Mac laptop and the ability to use the Terminal can create their own image classifier using TensorFlow, without having to do any coding...

Watch Tiny Neural Nets Learn
In this post I'll show you some animations of tiny neural nets learning. Finding the right neural net for a given problem needs experience and experimentation. I'll show you the steps and missteps it took me to find a good net to predict a noisy sine function...

‍

‍

Data Scientist - PayPal - San Jose, California
Collaborate with architects, engineers, data scientists and PayPal Risk teams to architect and develop strategic and tactical solutions using PayPal´s proprietary technology as well as open source distributed computing technology such as Hadoop. Design, develop and test projects jointly with other team members to deliver and deploy complex applications in PayPal´s production system...

‍

‍

Hacking Jupyter Notebooks with Customized Plugins
Jupyter notebooks have a nascent plugin system that allows users to add new buttons and menu options powered by custom javascript code. This talk will introduce plugins through a real-world example of building a custom button to link notebooks to the cloud-based Civis data science platform...

Two Minute Papers - How To Get Started With Machine Learning?
I get a lot of messages from you Fellow Scholars that you would like to get started in machine learning and are looking for materials. Below you find a ton of resources to get you started!...

How to Code and Understand DeepMind's Neural Stack Machine
I learn best with toy code that I can play with. This tutorial teaches DeepMind's Neural Stack machine via a very simple toy example, a short python implementation. I will also explain my thought process along the way for reading and implementing research papers from scratch, which I hope you will find useful...

‍

‍

Cognitive Computing: A Brief Guide for Game Changers Concise report on the most noteworthy developments in artificial intelligence...
"I loved it- this book that is- but it scared the living (Stuffing) out of me. Very very thought provoking..."... For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page...

‍