هنر علم داده: راهنمایی برای هر کسی که با داده‌ها کار می‌کند

Data analysis is a difficult process largely because few people can describe exactly how to do it. It's not that there aren't any people doing data analysis on a regular basis. It's that the process by which we state a question, explore data, conduct formal modeling, interpret results, and communicate findings, is a difficult process to generalize and abstract. Fundamentally, data analysis is an art. It is not yet something that we can easily automate. Data analysts have many tools at their disposal, from linear regression to classification trees to random forests, and these tools have all been carefully implemented on computers. But ultimately, it takes a data analyst—a person—to find a way to assemble all of the tools and apply them to data to answer a question of interest to people. This book writes down the process of data analysis with a minimum of technical detail. What we describe is not a specific "formula" for data analysis, but rather is a general process that can be applied in a variety of situations. Through our extensive experience both managing data analysts and conducting our own data analyses, we have carefully observed what produces coherent results and what fails to produce useful insights into data. This book is a distillation of our experience in a format that is applicable to both practitioners and managers in data science. Table of Contents 5 Data Analysis as Art 8 Epicycles of Analysis 11 Setting the Scene 12 Epicycle of Analysis 13 Setting Expectations 15 Collecting Information 16 Comparing Expectations to Data 17 Applying the Epicyle of Analysis Process 18 Stating and Refining the Question 23 Types of Questions 23 Applying the Epicycle to Stating and Refining Your Question 27 Characteristics of a Good Question 27 Translating a Question into a Data Problem 30 Case Study 33 Concluding Thoughts 37 Exploratory Data Analysis 38 Exploratory Data Analysis Checklist: A Case Study 40 Formulate your question 40 Read in your data 42 Check the Packaging 43 Look at the Top and the Bottom of your Data 46 ABC: Always be Checking Your ``n''s 47 Validate With at Least One External Data Source 52 Make a Plot 53 Try the Easy Solution First 56 Follow-up Questions 60 Using Models to Explore Your Data 62 Models as Expectations 64 Comparing Model Expectations to Reality 67 Reacting to Data: Refining Our Expectations 71 Examining Linear Relationships 74 When Do We Stop? 80 Summary 84 Inference: A Primer 85 Identify the population 85 Describe the sampling process 86 Describe a model for the population 86 A Quick Example 87 Factors Affecting the Quality of Inference 91 Example: Apple Music Usage 93 Populations Come in Many Forms 96 Formal Modeling 99 What Are the Goals of Formal Modeling? 99 General Framework 100 Associational Analyses 102 Prediction Analyses 111 Summary 118 Inference vs. Prediction: Implications for Modeling Strategy 119 Air Pollution and Mortality in New York City 120 Inferring an Association 122 Predicting the Outcome 127 Summary 130 Interpreting Your Results 131 Principles of Interpretation 131 Case Study: Non-diet Soda Consumption and Body Mass Index 132 Communication 151 Routine communication 151 The Audience 153 Content 155 Style 158 Attitude 158 Concluding Thoughts 160 About the Authors 162