Data Visualization Made Easy with Seaborn and Python

The word 'graph' covers many areas, so before we get into the course, we'll pin down some important terms that are used throughout the course.

A good graph clearly shows a story such as a relationship, a distribution or an event changing over time. In this session we'll discuss how to do this.

Over this course we'll cover a broad range of graphs, in this session you'll cover a basic intro as to what the different types of graphs are used for.

This video explains how to use and navigate the datasets contained within this section, and how to use them for the remainder of the course.

In this session we'll dive into arguably the most commonly seen graph, the Barplot!

Following on from the basics of Barplots, we'll dive into some neat customisation features!

A Pointplot is an alternative, and visually appealing way to plot categorical data, and in this session we'll look at how to set them up.

The Boxplot is an alternative way to plot categorical data. In this session we'll learn how to build them.

Time series data is data where we use a measure of time on the X-axis, let's take a look at some data before we plot it.

In this session we'll plot a single variable from the dataset against time, to see how the data changes.

Following on from plotting a single variable, we can also plot multiple variables to track how they change in respect to each other, over time.

In this session we'll take a look at a number of ways to add style to your line plots.

To introduce this section, we'll discuss what a distribution is, and why they are important.

A simple histogram shows the frequency of numerical data using rectangles, and in this session we'll walk through the basics of how to create them.

Showing the distribution of two or more variables in the same plot is known as a Bivariate Plot, and in this session we'll cover a number of ways to do this.

Unlike a histogram which uses a number of discrete bins to show distribution, a Kernel Density Estimation (KDE) produces a curve to smooth the observations.

In this session, we'll look at the rather funky looking Violin plot. A novel way to view the distribution of data.

In this session we'll look at perhaps the most basic way to compare the relationship between two variables.

In some situations when showing relationships between more than 2 variables, it is clearer to use multiple plots, and in this session we'll examine how this is done with the facetgrid.

A heatmap clearly shows the correlation between different variables in a dataset. In this session we'll look at the basics of heatmap construction.

Using a JointGrid we can combine the scatterplot seen at the start of this section, with a histogram. This allows for greater insight into the data we are showing.

Linear Regression is a commonly used term in Machine Learning which. We can use it to learn how a dependant variable is 'caused' by an independent variable. In this session we'll cover the basics of this popular term before moving on to creating the graph.

The Regplot (Regression plot) is closely linked to the linear model plot. In this session we'll create some regression plots with a regression line.

The Linear Model plot combines a Regplot with a Facetgrid to create a rather visually appealing plot, in this session we'll cover how to create and interpret these graphs.

The Residplot is used to plot the residuals of a regression model. In this session we'll look at why they are used, and how to create them.