Digest of articles on data analysis No. 2 (05/26/2014 - 06/08/2014)

Good afternoon, dear readers.
I present to you the digest of news and useful materials from the world of data analysis. The previous digest was very popular and so I decided to make them regular. The frequency of such selections will be 1 time in 2 weeks.

In today's compilation, you will learn what is common between statistics and data analysis, how to identify a false correlation, and what algorithms rule the modern world. In addition, you will receive small cheat sheets on methods of machine learning and NoSQL databases, well, and a lot more interesting.

Theory

• List of NoSQL Databases (EN)
  A complete list of NoSQL DB, broken down by category and brief description.
• 10 things from the statistics applicable in the analysis of big data (EN)
  The article describes the general approaches used in statistics and analysis of big data.
• False Correlations in Big Data
  Another article on the difference between false correlations from the true. We consider 6 types of correlations.
• Evolution in data analysis (EN)
  The main milestones in the development of yourself as a data analyst are highlighted. In my opinion, the article will be useful to those who have recently begun to engage in data analysis, but already have a basic understanding of this.
• Will Python become a leader in data analysis languages?
  The article shows the dynamics of the development of Python, as a tool for data analysis, and also provides reflections on why it is now very popular.
• 3 interesting, but little-known, programming languages (EN)
  Brief descriptions of languages ​​are given: Julia, Scala, Erlang.
• 3 trends in data warehouses for observation (EN)
  The article highlights the following trends: taking data from various sources, direct access of analysts to the data and speed of working with them.
• 7 basic rules for a project with big data (EN)
  Lists moments that need attention when starting to work with big data.
• Building a team of data analysts
  The article shows which specialists should go to the team and why. Basically, it’s about 3 people: a customer service specialist, context analyst, visualizer.
• 5 questions to ask before measuring anything (EN)
  Showing questions that you need to ask yourself or download, before analyzing any indicator.
• Life data analytics in small countries
  The article describes a number of difficulties, as well as ways to solve them, when working as an analyst in small countries, such as Belgium, Switzerland, etc.
• The Graphviz Cookbook (EN)
  Collection of recipes for using Graphviz to visualize data.
• 10 tips for analysts
  Experts in the field of analytics share tips that will help you in the analysis.
• Difficulties in using SQL when running OLAP
  The article describes the problems that can be encountered when creating a business analyst system.
• A priori probabilities and prevalence of “unexpected” effects (EN)
  An interesting article on the evaluation of p-value and its interpretation.
• Simple Bayesian network based on Markov chains (EN)
  The use of PyMC for building such a network is shown.
• Help with data structures
• Data analysts: stop looking, start using.
  An interesting article that explains how you can replace the data analyst if it is not in the state.
• Build analytic models on a normal distribution (EN)
  The article describes the advantages of this approach.
• SAS makes its courses free.
  Good news for those wishing to familiarize themselves with SAS.
• BigML makes machine learning easier
• 5 excellent resources for learning linear algebra (EN)
• 4 important applications of distribution kurtosis (EN)
• Informatization of language confrontation for data analysis
• 4 things you can get from customer data
  Briefly discussed, what benefits can bring the collection and analysis of data about your customers.
• 20 tutorials for data analytics
• What do neural networks hide? (Ru)
• And what really neural networks hide? (Ru)
• Cheat Sheet on Machine Learning Techniques (EN)
  Cheat sheet created for scikit-learn.
• What is deep learning (en)
• Tips for building an analytics system from scratch (EN)

')

Literature

• Analytics in a Big Data World
  Guide to analyzing data in various industries.
• Outlier Detection for Temporal Data (EN)
• A selection of 15 books on machine learning and data analysis (EN)
• Practical Data Science with R (EN)
• Big Data Computing (EN)
• Predictive Analytics, Data Mining and Big Data: Myths, Misconceptions and Methods (EN)
• Data Mining and Analysis - Fundamental Concepts and Algorithms
• Predictive Analytics
• Practical Machine Learning - Innovations in Recommendation
• Books that the analyst should have

Practice using different tools

• Examining statistics with IPython Notebook
  Selection of IPython consoles demonstrating the basic techniques of data analysis. And all this is done in the form of a textbook. For beginners to learn data analysis using Python, I highly recommend.
• Brazil's victory at the home world championship (EN)
  Another article devoted to predicting the winner of the future World Cup, this time with the help of R.
• Speech Recognition with Hidden Markov Chains (EN)
  It shows how Python and its packages can be used for this task.
• Defining Primary Image Colors Using Clustering
  Described how to accomplish this task using OpenCV and Python.
• Introduction to using Node.js and MongoDB
  A small, simple example of working with Mongo using Node.js tools.
• Work with GDELT from Python (EN)
  The official tutorial on working with GDELT from Python.
• IPython and plotly
  An example of using plotly with ipython. The article is designed as a console ipython notebook.
• Building a recommendation system using R (EN)
  A small article on how to make a simple recommendation system with a few lines of code on R.
• More than 100 data sets for analysis (EN)
  A small selection of data sets.
• R-Hadoop Step-by-Step Guide (EN)
• Compilation of training materials on data analysis (EN)

Educational videos

• Python for Big Data Analytics
  A compilation of videos describing how Python can be used to analyze big data.
• Introduction to Business Analysis (EN)
  Online lectures on business intelligence basics.
• Real-time forecasting with scikit-learn and RabbitMQ (EN)

Various related articles

• 10 algorithms that rule the world (RU)
  The story of the algorithms that are most often used in the present.
• List of abbreviations used in analyzing big data
  The article contains the abbreviations that are most often found in articles on large data.
• How data analysis helps improve health
  Interview with the director of science service MyFitnessPal.
• Prediction of the world champion 2014 (EN)
  The article describes the concept of prediction, as well as a link to the description of the methodology (which, by the way, is very beautifully visualized).
• Chess Evolution Study
  The article examines the question of how the beginning of chess games has changed from 1850 to the present day.
• Disaster Simulation with Machine Learning
  Interview with Dag Lohmann CEO KatRisk, which is engaged in modeling disasters.
• Data analysis and statistics are the same? (En)
  Interesting thoughts of the author when answering the question “how does data analysis differ from statistics?”.
• Why banks are still against “big data”
  The article provides a series of answers to the questions of various bankers on how to apply “big data” in their business.
• Performance Comparison for Revolution R Enterprise and SAS
  Presented a comparison of the capabilities of the above analytical systems.
• 250 million international events in one place (RU)
• Confrontation between analysts and statisticians (EN)
  Quite an entertaining article about how these two camps are fighting among themselves.
• The Data Revolution in the Digital Era
  Reflections of Eric Schmidt on how big data can change the world.