Data Science Programming All-in-One For Dummies

Chapter 5

Developing Consistent Strategies

IN THIS CHAPTER

Obtaining data correctly

Performing automatic data collection

Keeping data relevant

Interacting with data correctly

Some people view data merely as a disorganized collection of unkempt information from various sources. Throughout this book, you have seen strategies for organizing and manicuring data prior to performing analysis on it. All these strategies see use in business today because data scientists spend an inconceivable amount of time just obtaining, organizing, and manicuring data. Unfortunately, the output of these efforts is often lacking in usefulness because the data simply won’t be tamed. The problem is one of consistency in obtaining, organizing, and manicuring the data. If consistency is absent, it’s reasonable to assume that the output of an analysis will be suspect. The purpose of this chapter is to define methods of making the act of interacting with raw data more consistent so that the outcome of an analysis is more predictable and, therefore more reliable.

Standardizing Data Collection Techniques