Data Analysis with Open Source Tools: A Hands-On Guide for Programmers and Data Scientists

by Philipp Janert

Overview

Collecting data is relatively easy, but turning raw information into something useful requires that you know how to extract precisely what you need. With this insightful book, intermediate to experienced programmers interested in data analysis will learn techniques for working with data in a business environment. You'll learn how to look at data to discover what it contains, how to capture those ideas in conceptual models, and then feed your understanding back into the organization through business plans, metrics dashboards, and other applications.

Along the way, you'll experiment with concepts through hands-on workshops at the end of each chapter. Above all, you'll learn how to think about the results you want to achieve — rather than rely on tools to think for you.

• Use graphics to describe data with one, two, or dozens of variables
• Develop conceptual models using back-of-the-envelope calculations, as well as scaling and probability arguments
• Mine data with computationally intensive methods such as simulation and clustering
• Make your conclusions understandable through reports, dashboards, and other metrics programs
• Understand financial calculations, including the time-value of money
• Use dimensionality reduction techniques or predictive analytics to conquer challenging data analysis situations
• Become familiar with different open source programming environments for data analysis

"Finally, a concise reference for understanding how to conquer piles of data." —Austin King, Senior Web Developer, Mozilla

"An indispensable text for aspiring data scientists." —Michael E. Driscoll, CEO/Founder, Dataspora

Product Details

ISBN-13:	9780596802356
Publisher:	O'Reilly Media, Incorporated
Publication date:	11/18/2010
Pages:	509
Product dimensions:	7.00(w) x 9.10(h) x 1.20(d)

About the Author

After previous careers in physics and software development, Philipp K. Janert currently provides consulting services for data analysis,
algorithm development, and mathematical modeling.
He has worked for small start-ups and in large corporate environments, both in the U.S. and overseas. He prefers simple solutions that work to complicated ones that don't, and thinks that purpose is more important than process. Philipp is the author of "Gnuplot in Action - Understanding
Data with Graphs" (Manning Publications), and has written for the O'Reilly Network, IBM developerWorks,
and IEEE Software. He is named inventor on a handful of patents, and is an occasional contributor to CPAN.
He holds a Ph.D. in theoretical physics from the
Universityof Washington. Visit his company website at www.principal-value.com.

Table of Contents

; Preface; Before We Begin; Conventions Used in This Book; Using Code Examples; Safari® Books Online; How to Contact Us; Acknowledgments; Chapter 1: Introduction; 1.1 Data Analysis; 1.2 What’s in This Book; 1.3 What’s with the Workshops?; 1.4 What’s with the Math?; 1.5 What You’ll Need; 1.6 What’s Missing; Graphics: Looking at Data; Chapter 2: A Single Variable: Shape and Distribution; 2.1 Dot and Jitter Plots; 2.2 Histograms and Kernel Density Estimates; 2.3 The Cumulative Distribution Function; 2.4 Rank-Order Plots and Lift Charts; 2.5 Only When Appropriate: Summary Statistics and Box Plots; 2.6 Workshop: NumPy; 2.7 Further Reading; Chapter 3: Two Variables: Establishing Relationships; 3.1 Scatter Plots; 3.2 Conquering Noise: Smoothing; 3.3 Logarithmic Plots; 3.4 Banking; 3.5 Linear Regression and All That; 3.6 Showing What’s Important; 3.7 Graphical Analysis and Presentation Graphics; 3.8 Workshop: matplotlib; 3.9 Further Reading; Chapter 4: Time As a Variable: Time-Series Analysis; 4.1 Examples; 4.2 The Task; 4.3 Smoothing; 4.4 Don’t Overlook the Obvious!; 4.5 The Correlation Function; 4.6 Optional: Filters and Convolutions; 4.7 Workshop: scipy.signal; 4.8 Further Reading; Chapter 5: More Than Two Variables: Graphical Multivariate Analysis; 5.1 False-Color Plots; 5.2 A Lot at a Glance: Multiplots; 5.3 Composition Problems; 5.4 Novel Plot Types; 5.5 Interactive Explorations; 5.6 Workshop: Tools for Multivariate Graphics; 5.7 Further Reading; Chapter 6: Intermezzo: A Data Analysis Session; 6.1 A Data Analysis Session; 6.2 Workshop: gnuplot; 6.3 Further Reading; Analytics: Modeling Data; Chapter 7: Guesstimation and the Back of the Envelope; 7.1 Principles of Guesstimation; 7.2 How Good Are Those Numbers?; 7.3 Optional: A Closer Look at Perturbation Theory and Error Propagation; 7.4 Workshop: The Gnu Scientific Library (GSL); 7.5 Further Reading; Chapter 8: Models from Scaling Arguments; 8.1 Models; 8.2 Arguments from Scale; 8.3 Mean-Field Approximations; 8.4 Common Time-Evolution Scenarios; 8.5 Case Study: How Many Servers Are Best?; 8.6 Why Modeling?; 8.7 Workshop: Sage; 8.8 Further Reading; Chapter 9: Arguments from Probability Models; 9.1 The Binomial Distribution and Bernoulli Trials; 9.2 The Gaussian Distribution and the Central Limit Theorem; 9.3 Power-Law Distributions and Non-Normal Statistics; 9.4 Other Distributions; 9.5 Optional: Case Study—Unique Visitors over Time; 9.6 Workshop: Power-Law Distributions; 9.7 Further Reading; Chapter 10: What You Really Need to Know About Classical Statistics; 10.1 Genesis; 10.2 Statistics Defined; 10.3 Statistics Explained; 10.4 Controlled Experiments Versus Observational Studies; 10.5 Optional: Bayesian Statistics—The Other Point of View; 10.6 Workshop: R; 10.7 Further Reading; Chapter 11: Intermezzo: Mythbusting—Bigfoot, Least Squares, and All That; 11.1 How to Average Averages; 11.2 The Standard Deviation; 11.3 Least Squares; 11.4 Further Reading; Computation: Mining Data; Chapter 12: Simulations; 12.1 A Warm-Up Question; 12.2 Monte Carlo Simulations; 12.3 Resampling Methods; 12.4 Workshop: Discrete Event Simulations with SimPy; 12.5 Further Reading; Chapter 13: Finding Clusters; 13.1 What Constitutes a Cluster?; 13.2 Distance and Similarity Measures; 13.3 Clustering Methods; 13.4 Pre- and Postprocessing; 13.5 Other Thoughts; 13.6 A Special Case: Market Basket Analysis; 13.7 A Word of Warning; 13.8 Workshop: Pycluster and the C Clustering Library; 13.9 Further Reading; Chapter 14: Seeing the Forest for the Trees: Finding Important Attributes; 14.1 Principal Component Analysis; 14.2 Visual Techniques; 14.3 Kohonen Maps; 14.4 Workshop: PCA with R; 14.5 Further Reading; Chapter 15: Intermezzo: When More Is Different; 15.1 A Horror Story; 15.2 Some Suggestions; 15.3 What About Map/Reduce?; 15.4 Workshop: Generating Permutations; 15.5 Further Reading; Applications: Using Data; Chapter 16: Reporting, Business Intelligence, and Dashboards; 16.1 Business Intelligence; 16.2 Corporate Metrics and Dashboards; 16.3 Data Quality Issues; 16.4 Workshop: Berkeley DB and SQLite; 16.5 Further Reading; Chapter 17: Financial Calculations and Modeling; 17.1 The Time Value of Money; 17.2 Uncertainty in Planning and Opportunity Costs; 17.3 Cost Concepts and Depreciation; 17.4 Should You Care?; 17.5 Is This All That Matters?; 17.6 Workshop: The Newsvendor Problem; 17.7 Further Reading; Chapter 18: Predictive Analytics; 18.1 Topics in Predictive Analytics; 18.2 Some Classification Terminology; 18.3 Algorithms for Classification; 18.4 The Process; 18.5 The Secret Sauce; 18.6 The Nature of Statistical Learning; 18.7 Workshop: Two Do-It-Yourself Classifiers; 18.8 Further Reading; Chapter 19: Epilogue: Facts Are Not Reality; Programming Environments for Scientific Computation and Data Analysis; Software Tools; A Catalog of Scientific Software; Writing Your Own; Further Reading; Results from Calculus; Common Functions; Calculus; Useful Tricks; Notation and Basic Math; Where to Go from Here; Further Reading; Working with Data; Sources for Data; Cleaning and Conditioning; Sampling; Data File Formats; The Care and Feeding of Your Data Zoo; Skills; Terminology; Further Reading; About the Author; Colophon;