Chapter 1
Introduction
If this marks your first exposure to the new and exciting discipline
of data science, you occupy an enviable position. Still in front of
you is all the cool stuff, even the first few sparks of magic when you
learn how to plug data into electrical sockets, perform automated
prediction, and write the first gems of code to probe the depths of
an interesting data set. I’m a bit jealous, tbh, but am also excited
to explore it all again with you, which is the next best thing!
This field has changed the world like hardly any other has, and
on an incredibly short time scale, too. Just a couple decades ago,
businesses and organizations were routinely making major decisions
based on gut feelings and anecdotal observations. Doctors eyeballed
sets of symptoms and diagnosed patients largely based on what conditions they themselves had seen before, or seen recently. Online
sellers gave product recommendations that made sense to them,
completely missing patterns and trends that would become apparent if the characteristics and purchasing patterns of past customers
were taken into account.
Part of the reason decision makers made these suboptimal choices
was because it wasn’t yet clear how much punch data science would
pack. Another reason was that the technology wasn’t there yet: the
processing power and storage capacity to work with extremely large
data sets wasn’t commonly available, and of course the data itself
hadn’t all been gathered yet. No more! All these parts are here
SEE THE FILES:
this is a comment