The wealth of Python data visualization libraries makes it hard to decide the best choice for each use case. However, if you're looking for statistical plots that are easy to build and visually appealing, Seaborn is the obvious choice. You'll begin this course by using Seaborn to construct simple univariate histograms and use kernel density estimation, or KDE, to visualize the probability distribution of your data. You'll then work with bivariate histograms and KDE curves. Next, you'll use box plots to concisely represent the median and the inter-quartile range (IQR) and define outliers in data. You'll work with boxen plots, which are conceptually similar to box plots but employ percentile markers rather than whiskers. Finally, you'll use Violin plots to represent the entire probability density function, obtained via a KDE estimation, for your data.

Seaborn's smartly designed interface lets you illuminate data through aesthetically pleasing statistical graphics that are incredibly easy to build. In this course, you'll discover Seaborn's capabilities. You'll begin using strip plots and swarm plots and recognizing how they work together using low-intensity noise. You'll then work with time series data through various techniques, like resampling data at different time frequencies and plotting with confidence intervals and other types of error bars. Next, you'll visualize both logistic and linear regression curves. Moving on, you'll use the pairplot function to visualize the relationships between columns in your data, taken two at a time, in a grid format. You'll change the chart type being visualized and create pair plots with multiple chart types in each plot. Lastly, you'll create and format a heatmap of a correlation matrix to identify relationships between dataset columns.