Hello everyone and welcome to the first module of the data visualization with
Python course. In this video, we're gonna introduce data visualization and go over
an example of transforming a given visual into one which is more effective
attractive and impactive. So let's get started. Now one might ask why would I
need to learn how to visualize data. Well data visualization is a way to show a
complex data in a form that is graphical and easy to understand. This can be
especially useful when one is trying to explore the data and getting acquainted
with it. Also since a picture is worth a thousand words, then plots and graphs can
be very effective in conveying a clear description of the data especially when
disclosing findings to an audience or sharing the data with other peer data
scientists. Also, they can be very valuable when it comes to supporting any
recommendations you make to clients managers or other decision-makers in
your field. Darkhorse Analytics is a company that spun out of a research lab
at the University of Alberta in 2008 and has done fascinating work on data
visualization. Darkhorse Analytics specializes in quantitative consulting
in several areas including data visualization and geo spatial analysis.
Their approach when creating a visual revolves around three key points: less is
more effective, it is more attractive, and it is more impactive. In other words, any
feature or design you incorporate in your plot to make it more attractive or
pleasing should support the message that the plot is meant to get across and not
distract from it. Let's take a look at an example. So here is a pie chart of what
looks like people's preferences when it comes to different types of pig meat. The
charts message is almost half of the people surveyed preferred bacon over the
other types of pig meat. But I'm sure that almost all of you agree that there
is a lot going on in this pie chart and we're not even sure it features such as
the blue background or 3d orientation are meant to convey
anything. In fact, these additional unnecessary features distract from the
main message and can be confusing to the audience. So let's apply Darkhorse
Analytics approach to transform this into a visual that's more effective,
attractive, and impactive. As I mentioned earlier, the message here is that people
are most likely to choose bacon over other types of pig meat, so let's get rid
of everything that can be distracting from this core message. The first thing
is let's get rid of the blue background and the gray background. Let's also get
rid of borders as they do not convey any extra information. Also let's drop the
redundant legend since the pie chart is already color coded. 3D isn't adding any
extra information so let's say bye to it. Text bolding is also unnecessary and
let's get rid of the different colors and the wedges.
But let's thicken the lines to make them more meaningful. Now this looks a
little familiar. Yes! This is a bar graph after all, one with horizontal bars. And
finally, let's emphasize bacon so that it stands out among the other types of pig
meat. Now let's juxtapose the pie chart and the bar graph and compare which is
better and easy to understand. I hope that we unanimously agree that the bar
graph is the better of the two. It is simple, cleaner, less distracting, and much
easier to read. In fact, pie charts have recently come under fire from data
visualization experts who argue that they are relevant only in the rarest of
circumstances. Bar graphs and charts on the other hand are argued to be far
superior ways to quickly get a message across. But don't worry about this for
now, we will come back to this point when we learn how to create pie charts and
bar graphs with Matplotlib. For more similar and interesting
examples, check out Darkhorse Analytics website. They have a couple more examples
on how to clean bar graphs and maps of geospatial data. All these examples
reinforce the concept of less is more effective, attractive, and impactive.
Alex AklsonPh.D., Data Scientist
