[SOUND] Welcome to Module 5. A common phrase is a picture is worth a thousand words. We see this at sporting events where replay allow us to review what happened. And statistics about players or teams are often presented in a visually appealing manner. As an example, you can see the score board screen here at the baseball stadium which might display statistics about a batter as he approaches the plate or about a pitcher as he enters the game. This is also true in data analytics, while statistical analysis provides insight into why something might be happening. A visualization conveys more information in a manner that is easily understood without any formal training. A visualization can provide insight beyond the numbers, quickly indicating differences between datasets, highlighting where data are clustered or isolated. Indicate trends or potential correlations, and indicate the quality of a model and its predictions when compared to the generative data. As a specific example, consider the case of data analysts working for an insurance company after a hurricane swept through the southern United States. The insurance company wanted to classify claims quickly as either real or fraudulent. The analytics team took the claims data and generated a heat map visualization by zip code. In a heat map the color of a geographical area is dictated by a third variable, in this case, the value of a financial claim in that area. By comparing this simple visualization with a similar visualization showing the hardest hit areas from the storm, one particular area stood out. This area had a minimal impact from the storm but unusually high number of claims. The resulting investigation uncovered a contractor who was behaving improperly and notifying home owners that they had storm damage in order to increase his business earnings. You can see an example of a heat map visualization on the scoreboard behind me, where the areas are identified by unemployment in this particular heat map visualization. Now, for the case of the data analysts working for the insurance agency, the same information could have been identified by calculating the correlation between the claims and the weather data. But the result would have been harder to identify and communicate. At this point we won't dive into complicated visualizations like the heat map you see behind me. Instead, this module will introduce the basics of data visualization and how to construct plots by using Python to begin communicating data, and analytic results in a visually appealing manner. First, you will learn about what differentiates good and bad visualizations. Second, you will learn specific skills that aid in displaying quantitative information in a clear and convincing manner. Now these first two lessons include readings from well known visualization experts, as well as two excellent TED Talk videos. I hope you enjoy watching them, and I expect you will learn how to be both informative, and inspiring in your visualizations. Next, you will learn how to make basic plot visualizations in Python, and how to specifically control the display of the information via labels, titles and colors. Finally, you will learn about displaying quantitative information for one dimensional data sets including a rug plot, a box plot and a histogram. I expect this module will prove both useful and interesting. Being able to display information, even if it is a single column in a dataset is a very valuable skill, good luck. [SOUND]