Learn data mining languages: R, Python and SQL
– Fantastic set of interactive tutorials for learning different languages. Their SQL tutorial is second to none. You’ll learn how to manipulate data in MySQL, SQL Server, Access, Oracle, Sybase, DB2 and other database systems.
– The best way to learn is to work towards a goal. That’s what this helpful blog series is all about. You’ll learn SQL from scratch by following along with a simple, but common, data analysis scenario.
– This course is recommended for the intermediate SQL-er who wants to brush up on his/her skills. It’s a series of 10 challenges coupled with forums and external videos to help you improve your SQL knowledge and understanding of the underlying principles.
– Created by Code School, this interactive online tutorial system is designed to step you through R for statistics and data modeling. As you work through their seven modules, you’ll earn badges to track your progress helping you to stay on track.
– If you’re a complete R novice, try Lead’s introduction to R. In their 1 hour 30 min course, they’ll cover installation, basic usage, common functions, data structures, and data types. They’ll even set you up with your own development environment in RStudio.
– Once you’ve mastered the basics of R, bookmark this page. It’s a fantastically comprehensive style guide to using R. We should all strive to write beautiful code, and this resource (based on Google’s R style guide) is your key to that ideal.
– Learn R in R – a radical idea certainly. But that’s exactly what Swirl does. They’ll interactively teach you how to program in R and do some basic data science at your own pace. Right in the R console.
Python for beginners
– The Python website actually has a pretty comprehensive and easy-to-follow set of tutorials. You can learn everything from installation to complex analyzes. It also gives you access to the Python community, who will be happy to answer your questions.
– A complete list of Python tutorials to take you from zero to Python hero. There are tutorials for beginners, intermediate and advanced learners.
Read all about it: data mining books
Data Jujitsu: The Art of Turning Data into Product
– This free book by DJ Patil gives you a brief introduction to the complexity of data problems and how to approach them. He gives nice, understandable examples that cover the most important thought processes of data mining. It’s a great book for beginners but still interesting to the data mining expert. Plus, it’s free!
Data Mining: Concepts and Techniques
– The third (and most recent) edition will give you an understanding of the theory and practice of discovering patterns in large data sets. Each chapter is a stand-alone guide to a particular topic, making it a good resource if you’re not into reading in sequence or you want to know about a particular topic.
Mining of Massive Datasets
– Based on the Stanford Computer Science course, this book is often sighted by data scientists as one of the most helpful resources around. It’s designed at the undergraduate level with no formal prerequisites. It’s the next best thing to actually going to Stanford!
Hadoop: The Definitive Guide
– As a data scientist, you will undoubtedly be asked about Hadoop. So you’d better know how it works. This comprehensive guide will teach you how to build and maintain reliable, scalable, distributed systems with Apache Hadoop. Make sure you get the most recent addition to keep up with this fast-changing service.
Online learning: data mining webinars and courses
– Learn data mining from the comfort of your home with DataCamp’s online courses. They have free courses on R, Statistics, Data Manipulation, Dynamic Reporting, Large Data Sets and much more.
– Coursera brings you all the best University courses straight to your computer. Their online classes will teach you the fundamentals of interpreting data, performing analyzes and communicating insights. They have topics for beginners and advanced learners in Data Analysis, Machine Learning, Probability and Statistics and more.
– With a range of free and pay for data mining courses, you’re sure to find something you like on Udemy no matter your level. There are 395 in the area of data mining! All their courses are uploaded by other Udemy users meaning quality can fluctuate so make sure you read the reviews.
– These courses are handily organized into “Paths” based on the technology you want to learn. You can do everything from build a foundation in Git to take control of a data layer in SQL. Their engaging online videos will take you step-by-step through each lesson and their challenges will let you practice what you’ve learned in a controlled environment.
– Master a new skill or programming language with Udacity’s unique series of online courses and projects. Each class is developed by a Silicon Valley tech giant, so you know what your learning will be directly applicable to the real world.
– Learn from experts in web design, coding, business and more. The video tutorials from Treehouse will teach you the basics and their quizzes and coding challenges will ensure the information sticks. And their UI is pretty easy on the eyes.
Learn from the best: top data miners to follow
– Chief Data Scientist at MailChimp and author of Data Smart, John is worth a follow for his witty yet poignant tweets on data science.
– Author and Chief Data Scientist at The White House OSTP, DJ tweets everything you’ve ever wanted to know about data in politics.
– He’s Editor-in-Chief of FiveThirtyEight, a blog that uses data to analyze news stories in Politics, Sports, and Current Events.
– As the Chief Data Scientist at Baidu, Andrew is responsible for some of the most groundbreaking developments in Machine Learning and Data Science.
– He might know pretty much everything there is to know about Big Data.
– He’s the author of popular data science blog KDNuggets
, the leading newsletter on data mining and knowledge discovery.
– As the Co-founder of OKCupid, Christian has access to one of the most unique datasets on the planet and he uses it to give fascinating insight into human nature, love, and relationships
– He’s contributed to a number of data blogs and authored his own book on Applied Predictive Analytics. At the moment, Dean is Chief Data Scientist at SmarterHQ
Practice what you’ve learned: data mining competitions
– This is the ultimate data mining competition. The world’s biggest corporations offer big prizes for solving their toughest data problems.
– The best way to learn is to teach. Stackoverflow offers the perfect forum for you to prove your data mining know-how by answering fellow enthusiast’s questions.
– With a live leaderboard and interactive participation, TunedIT offers a great platform to flex your data mining muscles.
– You can find a number of nonprofit data mining challenges on DataDriven. All of your mining efforts will go towards a good cause.
– Another great site to answer questions on just about everything. There are plenty of curious data lovers on there asking for help with data mining and data science.
Meet your fellow data miner: social networks, groups and meetups
– As with many social media platforms, Facebook is a great place to meet and interact with people who have similar interests. There are a number of very active data mining groups you can join.
– If you’re looking for data mining experts in a particular field, look no further than LinkedIn. There are hundreds of data mining groups ranging from the generic to the hyper-specific. In short, there’s sure to be something for everyone.
– Want to meet your fellow data miners in person? Attend a meetup! Just search for data mining in your city and you’re sure to find an awesome group near you.
8 fantastic examples of data storytelling
8 fantastic examples of data storytelling
Data storytelling is the realization of great data visualization. We’re seeing data that’s been analyzed well and presented in a way that someone who’s never even heard of data science can get it.
Google’s Cole Nussbaumer provides a friendly reminder of what data storytelling actually is, it’s straightforward, strategic, elegant, and simple.
more on text and data mining in this IMS blog
Researchers use an app to predict GPA based on smartphone use
Dartmouth College and the University of Texas at Austin have developed an app that tracks smartphone activity to compute a grade point average that’s within 0.17 of a point.
More on Big Data in education in this blog:
Why Girls Tend to Get Better Grades Than Boys Do
New research shows that girls are ahead in every subject, including math and science. Do today’s grading methods skew in their favor?
The latest data from the Pew Research Center uses U.S. Census Bureau data to show that in 2012, 71 percent of female high school graduates went on to college, compared to 61 percent of their male counterparts. In 1994 the figures were 63 and 61 percent, respectively.
Girls succeed over boys in school because they are more apt to plan ahead, set academic goals, and put effort into achieving those goals.
The weaker sex
For all the data and feedback they provide, student information systems interfere with learning.
“School isn’t about learning. It’s about doing well.”
The singular focus on grades that these systems encourage turns learning into a competitive, zero-sum game for students.
the parallel with the online grades systems at K12 is the Big Data movement at Higher Ed. Big Data must be about assisting teaching, not about determining teaching and instructors must be very well aware and very carefully navigating in this nebulous areas of assisting versus determining.
This article about quantifying management of teaching and learning in K12 reminds me the big hopes put on technocrats governing counties and economies in the 70s of the last centuries when the advent of the computers was celebrated as the solution of all our problems. Haven’t we, as civilization learned anything from that lesson?
Very short video of Bryan Alexander, senior fellow at the National Institute for Technology in Liberal Education, discussing the issues and opportunities facing mobile technology, badges, flipped classrooms, and learning analytics: