Data Today: Spark, more Spark, Paxos + more

Can you tease apart cause and effect?  View in browser >

1. The best Strata 2014 talks From data privacy to real-world problem solving, O’Reilly’s data editors highlight thebest of the best talks from Strata 2014 (Did you miss them? You can watch the videos.) 2. Can you tease apart cause and effect? A new statistical test from Cornell University, the additive noise model, has accurately separated cause from effect in observational data up to 80% of the time. This could be pretty useful, although there is a disclaimer: "provided there are no confounding factors or selection effects." And aren’t there always confounding factors? (via KentuckyFC on Slashdot.) 3. Understanding Paxos Here's an introduction (complete with animations) to a key consensus algorithm in distributed systems. 4. Physical data visualizations The Mesopotamians had their data visualizations, we have ours. Here’s achronological list of physical visualizations and related artifacts. 5. Strata + Hadoop World 2015 Early Price ends Friday The deadline for Strata + Hadoop World 2015 Early Price is Jan 9. To get the early price—and to ensure your spot (Strata + Hadoop World sells out every year)—check out the amazing line-up of speakers and the jam-packed agenda, and reserve now. It's coming to San Jose Feb 17-20. Find out more → Sponsored Content Automated data curation Understanding relationships and curating a massive variety of siloed data manually can take extraordinary time and effort. Learn how to drastically reduce the heavy-lifting when unifying and enriching data from disparate sources with Tamr, Inc., using human-guided machine learning. 6. Spark Certification Demand for Apache Spark skills is exploding. O'Reilly has partnered with Databricks, creators of Spark, to offer Developer Certification for Apache Spark. There will be a Spark certification exam held on Friday, February 20, 2015 at Strata + Hadoop World in San Jose. You can easily combine certification with your trip to Strata, but you don't have to be registered at Strata & Hadoop World to take the exam. If you'd like to add Spark Development certification to your resume, register soon—there will only be 50 seats available for this exam. Learn more → 7. How to create viral visualizations David McCandless makes data visualizations that go viral. Here’s how he does it. 8. Apache Spark: academia to industry In this O'Reilly Data Show podcast, Ion Stoica talks about the rise of Apache Spark and Apache Mesos. Sponsored Content Data science in the cloud with Microsoft Azure Machine Learning and R The Microsoft Azure Machine Learning cloud platform provides simplified yet powerful data management, transformation, and machine learning tools. Using an in-depth data science example, this free webcast (Jan. 20) will show you how to perform data science tasks including: Data management with Azure ML Data transformation with Azure ML and R Data I/O between Azure ML and the R Scripts R graphics with Azure ML Building and evaluating machine learning models with Azure ML and R Publishing Azure ML models as a web service Register (and get the example code and dataset) 9. Building an algorithm to prevent suicide In 2012, more soldiers committed suicide than died while fighting in Afghanistan. Now the Army is building an algorithm to prevent suicide. 10. Freebie of the week Get the report Data: Emerging Trends and Technologies: How sensors, fast networks, AI, and distributed computing are affecting the data landscape, by Alistair Croll, free. It covers the emerging trends and technologies that will transform the data landscape in coming months. Download free report →

Thank You to Our Sponsors Presented by Elite Sponsors Strategic Sponsors