Data Science Bookcamp: Ten case studies

Data science often begins with a question that does not come with a tidy recipe. This Manning Early Access edition of Data Science Bookcamp: Ten case studies uses ten such problems to introduce the Python tools and ways of thinking that help make them answerable. Rather than treating concepts as isolated theory, it places them in practical scenarios—from a card-game probability puzzle to analyzing product tweets and forecasting stock movements.

Designed for readers who already know basic Python, the book develops the skills needed for each case and then encourages readers to work through the problem themselves before comparing their approach with the included solution.

Ten problems, many ways to think with data

The case studies span probability and statistics, machine learning, text analysis, networks, time series, and optimization. The contents move from assessing online ad clicks and tracking disease outbreaks in news headlines to studying scientific abstracts, social circles, purchase patterns, marketing decisions, and sales territories. Each scenario gives the techniques a concrete purpose: the question comes first, and the relevant tools follow.

Python as a way into the mathematics

Probability, statistical testing, Bayesian methods, and regression appear alongside Python libraries including NumPy, SciPy, Pandas, Matplotlib, and scikit-learn. Mathematical ideas are introduced through coding examples, making the computational steps part of the explanation rather than a separate layer of abstraction.

Practice the open-ended part

A key feature of the case-study format is the invitation to try solving each problem before reading the worked solution. That pause matters: it gives readers room to make choices, test assumptions, and see how a solution takes shape—not just follow a sequence of finished steps.

Who may find it useful?

This edition is suited to Python programmers who want to explore data science through varied examples and guided problem solving. Familiarity with basic Python is the stated starting point; the book introduces the mathematical and analytical techniques as they become relevant to the cases.

For readers who learn best by asking a question, working through the evidence, and checking their reasoning, these ten case studies offer a structured introduction to data science in practice.