Python Machine Learning

CHAPTER 4Data Visualization Using matplotlib

What Is matplotlib?

As the adage goes, “A picture is worth a thousand words.” This is probably most true in the world of machine learning. No matter how large or how small your dataset, it is often very useful (and many times, essential) that you are able to visualize the data and see the relationships between the various features within it. For example, given a dataset containing a group of students with their family details (such as examination results, family income, educational background of parents, and so forth), you might want to establish a relationship between the students' results with their family income. The best way to do this would be to plot a chart displaying the related data. Once the chart is plotted, you can then use it to draw your own conclusions and determine whether the results have a positive relationship to family income.

In Python, one of the most commonly used tools for plotting is matplotlib. Matplotlib is a Python 2D plotting library that you can use to produce publication‐quality charts and figures. Using matplotlib, complex charts and figures can be generated with ease, and its integration with Jupyter Notebook makes it an ideal tool for machine learning.

In this chapter, you will learn the basics of matplotlib. In addition, you will also learn about Seaborn, a complementary data visualization library that is based on matplotlib.

Plotting Line Charts

To see how easy it is to use matplotlib, let's plot ...