Data Smart - Using Data Science to Transform Information Into Insight

Want to jump into data science but don't know where to start?
 
Let's be real, data science is presented as something mystical and unattainable without the most powerful software, hardware, and data expertise. Real data science isn't about technology. It's about how you approach the problem.
 
In this updated edition of Data Smart: Using Data Science to Transform Information into Insight, award-winning data scientist and bestselling author Jordan Goldmeier shows you how to implement data science problems using Excel while exposing how things work behind the scenes.
 
Data Smart is your field guide to building statistics, machine learning, and powerful artificial intelligence concepts right inside your spreadsheet.
 
Inside you'll find:
* Four-color data visualizations that highlight and illustrate the concepts discussed in the book
* Tutorials explaining complicated data science using just Microsoft Excel
* How to take what you've learned and apply it to everyday problems at work and life
* Advice for using formulas, Power Query, and some of Excel's latest features to solve tough data problems
* Smart data science solutions for common business challenges
* Explanations of what algorithms do, how they work, and what you can tweak to take your Excel skills to the next level
 
Data Smart is a must-read for students, analysts, and managers ready to become data science savvy and share their findings with the world.

List of contents

Introduction xix
 
1 Everything You Ever Needed to Know About Spreadsheets but Were Too Afraid to Ask 1
 
Some Sample Data 2
 
Accessing Quick Descriptive Statistics 3
 
Excel Tables 4
 
Filtering and Sorting 5
 
Table Formatting 7
 
Structured References 7
 
Adding Table Columns 10
 
Lookup Formulas 11
 
VLOOKUP 11
 
INDEX/MATCH 13
 
XLOOKUP 15
 
PivotTables 16
 
Using Array Formulas 19
 
Solving Stuff with Solver 20
 
2 Set It and Forget It: An Introduction to Power Query 27
 
What Is Power Query? 27
 
Sample Data 28
 
Starting Power Query 29
 
Filtering Rows 32
 
Removing Columns 33
 
Find & Replace 34
 
Close & Load to Table 35
 
3 Naïve Bayes and the Incredible Lightness of Being an Idiot 39
 
The World's Fastest Intro to Probability Theory 39
 
Totaling Conditional Probabilities 40
 
Joint Probability, the Chain Rule, and Independence 40
 
What Happens in a Dependent Situation? 41
 
Bayes Rule 42
 
Separating the Signal and the Noise 43
 
Using the Bayes Rule to Create an AI Model 44
 
High-Level Class Probabilities Are Often Assumed to Be Equal 45
 
A Couple More Odds and Ends 46
 
Let's Get This Excel Party Started 47
 
Cleaning the Data with Power Query 48
 
Splitting on Spaces: Giving Each Word Its Due 50
 
Counting Tokens and Calculating Probabilities 55
 
We Have a Model! Let's Use It 58
 
4 Cluster Analysis Part 1: Using K-Means to Segment Your Customer Base 65
 
Dances at Summer Camp 65
 
Getting Real: K-Means Clustering Subscribers in Email Marketing 70
 
The Initial Dataset 71
 
Determining What to Measure 72
 
Start with Four Clusters 75
 
Euclidean Distance: Measuring Distances as the Crow Flies 76
 
Solving for the Cluster Centers 80
 
Making Sense of the Results 82
 
Getting the Top Deals by Cluster 83
 
The Silhouette: A Good Way to Let Different K Values Duke It Out 86
 
How About Five Clusters? 95
 
Solving for Five Clusters 96
 
Getting the Top Deals for All Five Clusters 96
 
Computing the Silhouette for 5-Means Clustering 99
 
K-Medians Clustering and Asymmetric Distance Measurements 100
 
Using K-Medians Clustering 100
 
Getting a More Appropriate Distance Metric 100
 
Putting It All in Excel 102
 
The Top Deals for the 5-Medians Clusters 104
 
5 Cluster Analysis Part II: Network Graphs and Community Detection 109
 
What Is a Network Graph? 110
 
Visualizing a Simple Graph 110
 
Beyond GiGraph and Adjacency Lists 115
 
Building a Graph from the Wholesale Wine Data 117
 
Creating a Cosine Similarity Matrix 118
 
Producing an R-Neighborhood Graph 121
 
Introduction to Gephi 123
 
Creating a Static Adjacency Matrix 124
 
Bringing in Your R-Neighborhood Adjacency Matrix into Gephi 124
 
Node Degree 128
 
Touching the Graph Data 130
 
How Much Is an Edge Worth? Points and Penalties in Graph Modularity 132
 
What's a Point, and What's a Penalty? 133
 
Setting Up the Score Sheet 136
 
Let's Get Clustering! 138
 
Split Number 1 138
 
Split 2: Electric Boogaloo 143
 
And. . .Split3: Split with a Vengeance 145
 
Encoding and Analyzing the Communities 146
 
There and Back Again: A Gephi Tale 151
 
6 Regression: The Granddaddy of Supervised Artifici

About the author

JORDAN GOLDMEIER is an award-winning author in analytics, data science, and data visualization, and 11-time Microsoft MVP winner. Jordan has served analytics solutions for global organizations like NATO, The World Bank and Habitat for Humanity, and Fortune 500 companies likes Principal Financial and H&M. He has taught as an instructor for Wake Forest University, and served as a volunteer Emergency Medical Technician in New York City.

Summary

Want to jump into data science but don't know where to start?

Let's be real, data science is presented as something mystical and unattainable without the most powerful software, hardware, and data expertise. Real data science isn't about technology. It's about how you approach the problem.

In this updated edition of Data Smart: Using Data Science to Transform Information into Insight, award-winning data scientist and bestselling author Jordan Goldmeier shows you how to implement data science problems using Excel while exposing how things work behind the scenes.

Data Smart is your field guide to building statistics, machine learning, and powerful artificial intelligence concepts right inside your spreadsheet.

Inside you'll find:
* Four-color data visualizations that highlight and illustrate the concepts discussed in the book
* Tutorials explaining complicated data science using just Microsoft Excel
* How to take what you've learned and apply it to everyday problems at work and life
* Advice for using formulas, Power Query, and some of Excel's latest features to solve tough data problems
* Smart data science solutions for common business challenges
* Explanations of what algorithms do, how they work, and what you can tweak to take your Excel skills to the next level

Data Smart is a must-read for students, analysts, and managers ready to become data science savvy and share their findings with the world.

Product details

• Authors: Jordan Goldmeier, Jordan (Wake Forest University) Goldmeier, Goldmeier Jordan
• Publisher: Wiley, John and Sons Ltd
• Languages: English
• Product format: Paperback / Softback
• Released: 07.11.2023
• EAN: 9781119931386
• ISBN: 978-1-119-93138-6
• No. of pages: 448
• Subjects: Natural sciences, medicine, IT, technology > IT, data processing > IT; Informatik, Netzwerk, computer science, Data Mining & Knowledge Discovery, Data Mining u. Knowledge Discovery, Database & Data Warehousing Technologies, Datenbanken u. Data Warehousing