SQL for data scientists : a beginner's guide for building datasets for analysis
著者
書誌事項
SQL for data scientists : a beginner's guide for building datasets for analysis
Wiley, c2021
- : [pbk.]
大学図書館所蔵 件 / 全1件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
注記
Includes index
内容説明・目次
内容説明
Jump-start your career as a data scientist—learn to develop datasets for exploration, analysis, and machine learning
SQL for Data Scientists: A Beginner's Guide for Building Datasets for Analysis is a resource that’s dedicated to the Structured Query Language (SQL) and dataset design skills that data scientists use most. Aspiring data scientists will learn how to how to construct datasets for exploration, analysis, and machine learning. You can also discover how to approach query design and develop SQL code to extract data insights while avoiding common pitfalls.
You may be one of many people who are entering the field of Data Science from a range of professions and educational backgrounds, such as business analytics, social science, physics, economics, and computer science. Like many of them, you may have conducted analyses using spreadsheets as data sources, but never retrieved and engineered datasets from a relational database using SQL, which is a programming language designed for managing databases and extracting data.
This guide for data scientists differs from other instructional guides on the subject. It doesn’t cover SQL broadly. Instead, you’ll learn the subset of SQL skills that data analysts and data scientists use frequently. You’ll also gain practical advice and direction on "how to think about constructing your dataset."
Gain an understanding of relational database structure, query design, and SQL syntax
Develop queries to construct datasets for use in applications like interactive reports and machine learning algorithms
Review strategies and approaches so you can design analytical datasets
Practice your techniques with the provided database and SQL code
In this book, author Renee Teate shares knowledge gained during a 15-year career working with data, in roles ranging from database developer to data analyst to data scientist. She guides you through SQL code and dataset design concepts from an industry practitioner’s perspective, moving your data scientist career forward!
目次
Introduction xix
Chapter 1 Data Sources 1
Data Sources 1
Tools for Connecting to Data Sources and Editing SQL 2
Relational Databases 3
Dimensional Data Warehouses 7
Asking Questions About the Data Source 9
Introduction to the Farmer’s Market Database 11
A Note on Machine Learning Dataset Terminology 12
Exercises 13
Chapter 2 The SELECT Statement 15
The SELECT Statement 15
The Fundamental Syntax Structure of a SELECT Query 16
Selecting Columns and Limiting the Number of Rows Returned 16
The ORDER BY Clause: Sorting Results 18
Introduction to Simple Inline Calculations 20
More Inline Calculation Examples: Rounding 22
More Inline Calculation Examples: Concatenating Strings 24
Evaluating Query Output 26
SELECT Statement Summary 29
Exercises Using the Included Database 30
Chapter 3 The WHERE Clause 31
The WHERE Clause 31
Filtering SELECT Statement Results 32
Filtering on Multiple Conditions 34
Multi-Column Conditional Filtering 40
More Ways to Filter 41
BETWEEN 41
IN 42
LIKE 43
IS NULL 44
A Warning About Null Comparisons 44
Filtering Using Subqueries 46
Exercises Using the Included Database 47
Chapter 4 CASE Statements 49
CASE Statement Syntax 50
Creating Binary Flags Using CASE 52
Grouping or Binning Continuous Values Using CASE 53
Categorical Encoding Using CASE 56
CASE Statement Summary 59
Exercises Using the Included Database 60
Chapter 5 SQL JOINs 61
Database Relationships and SQL JOINs 61
A Common Pitfall when Filtering Joined Data 71
JOINs with More than Two Tables 74
Exercises Using the Included Database 76
Chapter 6 Aggregating Results for Analysis 79
GROUP BY Syntax 79
Displaying Group Summaries 80
Performing Calculations Inside Aggregate Functions 84
MIN and MAX 88
COUNT and COUNT DISTINCT 90
Average 91
Filtering with HAVING 93
CASE Statements Inside Aggregate Functions 94
Exercises Using the Included Database 96
Chapter 7 Window Functions and Subqueries 97
ROW NUMBER 98
RANK and DENSE RANK 101
NTILE 102
Aggregate Window Functions 103
LAG and LEAD 108
Exercises Using the Included Database 111
Chapter 8 Date and Time Functions 113
Setting datetime Field Values 114
EXTRACT and DATE_PART 115
DATE_ADD and DATE_SUB 116
DATEDIFF 118
TIMESTAMPDIFF 119
Date Functions in Aggregate Summaries and Window Functions 119
Exercises 126
Chapter 9 Exploratory Data Analysis with SQL 127
Demonstrating Exploratory Data Analysis with SQL 128
Exploring the Products Table 128
Exploring Possible Column Values 131
Exploring Changes Over Time 134
Exploring Multiple Tables Simultaneously 135
Exploring Inventory vs. Sales 138
Exercises 142
Chapter 10 Building SQL Datasets for Analytical Reporting 143
Thinking Through Analytical Dataset Requirements 144
Using Custom Analytical Datasets in SQL:
CTEs and Views 149
Taking SQL Reporting Further 153
Exercises 157
Chapter 11 More Advanced Query Structures 159
UNIONs 159
Self-Join to Determine To-Date Maximum 163
Counting New vs. Returning Customers by Week 167
Summary 171
Exercises 171
Chapter 12 Creating Machine Learning Datasets Using SQL 173
Datasets for Time Series Models 174
Datasets for Binary Classification 176
Creating the Dataset 178
Expanding the Feature Set 181
Feature Engineering 185
Taking Things to the Next Level 189
Exercises 189
Chapter 13 Analytical Dataset Development Examples 191
What Factors Correlate with Fresh Produce Sales? 191
How Do Sales Vary by Customer Zip Code,
Market Distance, and Demographic Data? 211
How Does Product Price Distribution Affect
Market Sales? 217
Chapter 14 Storing and Modifying Data 229
Storing SQL Datasets as Tables and Views 229
Adding a Timestamp Column 232
Inserting Rows and Updating Values in Database Tables 233
Using SQL Inside Scripts 236
In Closing 237
Exercises 238
Appendix Answers to Exercises 239
Index 255
「Nielsen BookData」 より