The document discusses the process of data science. It begins by defining the typical steps in a data science project as identifying a problem/business question, collecting and cleaning data, performing exploratory data analysis, using algorithms and machine learning, reporting answers/minimum viable products, and getting feedback to review results. It then lists "inconvenient truths" about data science, such as data never being clean and most time being spent on preparation. Finally, it provides an example of using import.io and MonkeyLearn tools for text analysis.