Part 8: Data Science: Process & Practice
The end-to-end data science workflow: framing problems, acquiring and wrangling data, exploring it, engineering features, and communicating results.
Chapters in This Part
Chapter 28: The Data Science Lifecycle
Data science projects fail far more often from poor problem framing than from inadequate algorithms. A team can spend weeks building a sophisticated g...
Chapter 29: Data Acquisition & Wrangling
Data rarely arrives in the form you need. In practice, data scientists spend the majority of their time — commonly cited at 60–80% — not building mode...
Chapter 30: Exploratory Data Analysis
Exploratory Data Analysis (EDA) is the detective work that precedes every serious modeling effort. Before you fit a single parameter or write a single...
Chapter 31: Feature Engineering & Selection
Feature engineering is the craft of transforming raw data into representations that machine learning algorithms can exploit effectively. A model is ul...
Chapter 32: Data Visualization & Storytelling
Data visualization sits at the intersection of statistics, design, and communication. A model that cannot be explained is a model that cannot be trust...