
The Crystal Ball Instruction Manual - version 1.1 Volume One: Introduction to Data Science
Stephen Davies, University of Mary Washington
Copyright Year:
ISBN 13: 9781715320041
Publisher: University of Mary Washington
Language: English
Formats Available
Conditions of Use
Attribution-ShareAlike
CC BY-SA
Reviews





The author has covered the basic information on how to use Python for data analysis, presenting a perspective beneficial for students interested in data science who lack a foundation in data analysis. Additionally, the author recommends Jupyter... read more
Reviewed by Xuan Wang, Assistant Professor, University of Texas Rio Grande Valley on 4/9/24
Comprehensiveness
The author has covered the basic information on how to use Python for data analysis, presenting a perspective beneficial for students interested in data science who lack a foundation in data analysis. Additionally, the author recommends Jupyter Notebook as the integrated development environment (IDE) for running Python code, which is one of the most popular tools for this purpose. Overall, this book is comprehensive for beginners with no coding background and those interested in the field of data science.
Content Accuracy
The author ensures that the content provided is accurate, error-free, and unbiased. For every concept or new material introduced, the author gives an example, making the content very easy to follow and understand.
Relevance/Longevity
The content is up-to-date. Python is considered one of the most popular open-source tools for working with data analysis. It is very important for students to understand and know how to run Python code to execute data analysis. This book provides a great foundation and starting point for students interested in entering the field of data science.
Clarity
The text is very accessible and easy to understand, perfectly suited for beginners. There are no difficult terms to understand in the textbook.
Consistency
The text is internally consistent, with all chapters relating to Python and providing examples of how to use Python for data analysis.
Modularity
I think the author might consider adding more sections on machine learning since this concept has already been introduced. Machine learning encompasses many different methodologies, so I would suggest adding a couple of new chapters to the textbook. Alternatively, the author could consider writing a book dedicated solely to machine learning with Python.
Organization/Structure/Flow
The overall organization of the book is quite easy to follow and understand. The only concern is the absence of a conclusion chapter, appendix, and references for this book. The last chapter, which evaluates a classifier, leaves the impression that the book has not fully concluded.
Interface
The book is very easy to navigate. The examples, figures and tables are also easy to follow and understand.
Grammatical Errors
I did not find the grammatical issues in the textbook.
Cultural Relevance
There is no insensitive or offensive way in this textbook.
CommentsN/A





I found the text to be complete and sufficient for an introduction to data science with python. This was remarkable as there are OER textbook for python, but few on data science "using" python. read more
Reviewed by Thomas Blamey, Math Faculty, University of Hawaii Maui College on 2/8/22
Comprehensiveness
I found the text to be complete and sufficient for an introduction to data science with python. This was remarkable as there are OER textbook for python, but few on data science "using" python.
Content Accuracy
I found no errors in my readings.
Relevance/Longevity
As I mentioned above, this was a fabulous find for me as I have embarked upon a start up data science cert (and class with python) for our college. Although there are a few publishers with this content (truly not many), this is actually the first OER text to specifically capture my content (data science & python).
Clarity
The text was a clear and easy read, as it should be for an introduction to this area of study.
Consistency
I found the text to be consistent and had an easy structure to follow.
Modularity
The text had many sections, which will make it easy to utilize only the sections I find important to cover in my specific class. This is appreciated as modularity is so important for teachers who have unique courses that might not use all of the text book.
Organization/Structure/Flow
The topics flowed as I expected they should - building in a natural/logical way.
Interface
I found no issues with navigation or distortion in the etext. It was a good read.
Grammatical Errors
I found no grammatical errors or technical errors.
Cultural Relevance
I found no issues with insensitive or offensive content.
CommentsAlthough I am so grateful for this OER text, it was writing from the lens of a computer scientist, which most are. My course is from the lens of a non-computer scientist, more of "user" of python in the area of data science. But, again...I am thankful for this remarkable resource.
Mahalo.





The book provides a great introduction to the world of data science, using Python as the main driver. Python is a good choice as it has become the de facto programming language used in the field with its many libraries that fit the bill. read more
Reviewed by Patrick Earl, Instructor, Kutztown University on 12/31/20
Comprehensiveness
The book provides a great introduction to the world of data science, using Python as the main driver. Python is a good choice as it has become the de facto programming language used in the field with its many libraries that fit the bill.
Content Accuracy
Book is accurate to current information in the field of data science.
Relevance/Longevity
The book is relevant since it seemingly uses Python 3. Pandas (and NumPy) dropped support for Python 2 at the start of 2020. Unless something more popular than pandas comes along, this book will be relevant for the foreseeable future. The text is organized in a way that appears to make it simple to update.
Clarity
Concepts are introduced and explained as necessary. Readers with no experience should have no problem when starting at the beginning of the book.
Consistency
Book uses consistent terms and doesn't appear to blindside the user with any new information or undefined terms.
Modularity
This book would be useful for people who are versed in Python programming, but the chapter structure feels a bit off. Concepts related to the programming side (like functions) are found in later chapters. The author has their reasons which are explained in the book, but to an outsider it may be off putting. This book still offers a modular view where certain sections can be extracted as needed.
Organization/Structure/Flow
Book is organized well and topics are introduced as needed. Only complaint was about the ordering of the chapters, which I commented on in the "Modularity" section.
Interface
Table of Contents works as expected in the PDF version. Images appear fine and the book is free of any distracting display issues.
My only gripe is that I couldn't find a table of contents that included the subsections found within the chapters.
Grammatical Errors
I saw no glaring grammatical errors while reviewing this text. I found the author's writing to be quite enjoyable at times.
Cultural Relevance
I didn't see any issues with statements that could be seen as culturally insensitive.
CommentsI've enjoyed this book and plan to use it as the main or supplemental textbook in one of my future courses.
Table of Contents
- 1 Introduction
- 2 A trip to Jupyter
- 3 Three kinds of atomic data
- 4 Memory pictures
- 5 Calculations
- 6 Scales of measure
- 7 Three kinds of aggregate data
- 8 Arrays in Python (1 of 2)
- 9 Arrays in Python (2 of 2)
- 10 Interpreting Data
- 11 Assoc. arrays in Python (1 of 3)
- 12 Assoc. arrays in Python (2 of 3)
- 13 Assoc. arrays in Python (3 of 3)
- 14 Loops
- 15 EDA: univariate
- 16 Tables in Python (1 of 3)
- 17 Tables in Python (2 of 3)
- 18 Tables in Python (3 of 3)
- 19 EDA: bivariate (1 of 2)
- 20 EDA: bivariate (2 of 2)
- 21 Branching
- 22 Functions (1 of 2)
- 23 Functions (2 of 2)
- 24 Recoding and transforming
- 25 Machine Learning: concepts
- 26 Classification: concepts
- 27 Decision trees (1 of 2)
- 28 Decision trees (2 of 2)
- 29 Evaluating a classifier
Ancillary Material
Submit ancillary resourceAbout the Book
A perfect introduction to the exploding field of Data Science for the curious, first-time student. The author brings his trademark conversational tone to the important pillars of the discipline: exploratory data analysis, choices for structuring data, causality, machine learning principles, and introductory Python programming using open-source Jupyter Notebooks. This engaging read will allow any dedicated learner to build the skills necessary to contribute to the Data Science revolution, regardless of background.
About the Contributors
Author
Stephen Davies, Associate Professor of Computer Science, earned a Ph.D. (2005) in Computer Science from the University of Colorado, Boulder, after having received an M.S. (1995) in Electrical Engineering from Colorado and a B.S. (1992) in Electrical Engineering from Rice University. He joined the UMW faculty in 2006, and has taught courses in database schema theory, Web application development, computational science, data mining, and object-oriented analysis & design, among other topics.