What you need for this book

To complete the projects in this book, you will need a version of Python 3.5 or higher. I recommend using Anaconda Python, but any Python distribution will do as long as it is updated and contains the following packages: Numpy, Matplotlib, NetworkX, PyMySQL, Gensim, and NLTK. In Chapter 1, Expanding Your Data Mining Toolbox, we will walk through an easy installation of Python and all these libraries, and each time a library is used later in the book, we will install it or upgrade it together.

Because data mining is obviously data-centric, and because the data sets we are working with are sometimes large or require some type of persistent data storage, I chose to implement some of the data mining algorithms alongside a relational database system. I chose MySQL for accomplishing this since it is an established, easy-to-download and install piece of infrastructure. The chapters where MySQL comes into play are in working with the memory-intensive algorithms in Chapter 2, Association Rule Mining, and Chapter 3, Entity Matching. I also use MySQL for some of the examples in Chapter 9, Mining for Data Anomalies, but it is possible to go through that chapter without MySQL.