Think Stats: Exploratory Data Analysis 2nd Edition by Allen B. Downey (PDF)

Description

If you know how to program, you have the skills to turn data into knowledge, using tools of probability and statistics. This concise introduction shows you how to perform statistical analysis computationally, rather than mathematically, with programs written in Python.By working with a single case study throughout this thoroughly revised book, you’ll learn the entire process of exploratory data analysis—from collecting data and generating statistics to identifying patterns and testing hypotheses. You’ll explore distributions, rules of probability, visualization, and many other tools and concepts.New chapters on regression, time series analysis, survival analysis, and analytic methods will enrich your discoveries.Develop an understanding of probability and statistics by writing and testing codeRun experiments to test statistical behavior, such as generating samples from several distributionsUse simulations to understand concepts that are hard to grasp mathematicallyImport data from most sources with Python, rather than rely on data that’s cleaned and formatted for statistics toolsUse statistical inference to answer questions about real-world data

User’s Reviews

Reviews from Amazon users which were colected at the time this book was published on the website:

⭐I really liked this book. The author did a really good job. It’s a mixture of Python and statistics so some previous background in both will allowing you to benefit entirely from reading this book. Especially prior experience with Python will help you understand the code used by the author, as it is not a simple one. He often uses wrapper functions and class inheritance, so if this doesn’t ring a bell, I suggest learning a bit of Python first. Otherwise you can skip the programming parts, but I think you will lose a large part of the book’s value.Statistics here is more basic than Python code, for sure. But it does serve well as a introduction to statistical analysis. A software developer wanting to start learning statistics is probably a good candidate for this book. But not the other way around. After reading it I think I still prefer to use R to generate probability density plot, than Python.Anyway, it is almost a must read for anyone on their patch to data scientist career. It not long or super expensive, so if you are interested in stats and Python, just read it.

⭐The book generally explains the concepts well, but could provide more details and more examples. I found the code actually very hard to understand, because the function and variable names are often missing clarity. If the code were improved, it would facilitate the reader’s learning greatly.That being said, for the price on Kindle, I found the content and format extremely useful to start getting practical experience via the exercises. Since this is based on a very friendly and popular tool, Jupyter, it is a great introduction to that application.

⭐This book is a great introduction to statistics for any person with basic programming skills. The main issue, when you tackle any math-heavy stuff – is that you are bombarded with a huge amount of formulas, but can’t “feel” the practical side of the subject.In this book, you have a simple way to practically and swiftly try each new concept through Jupyter Notebook interactive examples. Transform the data, draw a chart – observe results. The fastest feedback loop you can get learning any math stuff.If you want to get the best results from the book, spend some time and setup Jupyter Notebook, or just run them directly in Google Collab service. Just reading the book without practically running all the examples just a waste of time.

⭐I ordered the new edition and I thought it would be in color print. There are many graphs in the book that show data distribution and it is necessary to visualize in color to understand the result (see attached pictures). I think the price is not fair for the black and white color. However, the content is interesting and I liked it.

⭐I love this book. Not only does it illustrate the concepts well, but it’s well-written (funny even) and very concise and informative. I bought it to review stats concepts and see the python programming examples, but I think it could serve as a first/ introduction to stats book as well. The author has a wonderful ability to really distill information and teach via examples. This book served me well and I still use it as a reference all the time.

⭐this book covers all points nicely like multivariate analysis, graphics and others Code examples are given in all cases and data sets are carefully selected I benefitted a lot from this book in kaggle competitions thanks.

⭐I should have listened to other reviewers. The author basically writes his own code and refers to it throughout the book. Unfortunately, this code is only available online so when you go to read his code, it’s not very useful. He writes custom code to do things that are available in common libraries.That being said this is a good book to look at how the author might approach certain problems. He also provides some good working examples including how to find data. That can be useful.

⭐The first big hit is that the author uses custom-built functions. Ignoring that fact, the solutions are largely unusable to check your work. At least in 2021. Working through technical exercises to learn without feedback is a complete waste of time, and makes this textbook tough to review well— even if the content offers a valuable perspective on statistics.

⭐As one of the other reviewers mentioned, this is a fantastic book with great insights and ways of thinking/processing in a statistical fashion using Python. But, why oh why are there custom functions written when using the well established numpy, pandas and matplotlib libraries directly would have made for a MUCH better read? To clarify, this is to say the author wrote his own functions for demonstration whose code is not available in the book, but can be viewed on Github. Also, a perfectionist might cringe a bit at all custom written functions beginning with a capital letter (typically reserved for classes).Otherwise, the book introduces a good number of principles and practices which I will no doubt include more of in my daily work; thank you. 🙂

⭐This book is an instruction manual for functions that the author wrote. The actual statistical contents in this book is minimal at best. I would recommend learning statistics from a another book and how to apply these separately in python. Total waste of money. One of the explanations even includes a reference to wikipedia!

⭐Great book for intro on statistics, probably the best out there. But I do have one major criticism in that they built and reference their own custom python library thinkstats2 rather than using the standard ones used in the field. For example pmf & cdf code examples should be using scipy or numpy.

⭐Useful book, which does what is says: teaches statistics through coding. It helped me revisit/refresh basic statistics, dropping insightful (and more advanced) comments occasionally. My one criticism is the implementation in Python: the author provides pre-defined functions and classes which, whilst they greatly help learning concepts, sometimes overlook the teaching of coding. That same aspect, I suppose, would be welcome to many readers.

⭐A very good and clean approach to the subject of statistics. It surely helps a lot to better understand certain topics in a very simple way.

Keywords

Free Download Think Stats: Exploratory Data Analysis 2nd Edition in PDF format
Think Stats: Exploratory Data Analysis 2nd Edition PDF Free Download
Download Think Stats: Exploratory Data Analysis 2nd Edition 2014 PDF Free
Think Stats: Exploratory Data Analysis 2nd Edition 2014 PDF Free Download
Download Think Stats: Exploratory Data Analysis 2nd Edition PDF
Free Download Ebook Think Stats: Exploratory Data Analysis 2nd Edition