This module, you will learn the basics of how to use code to make predictions based on data. After discussing what prediction is, you’ll learn to describe the concepts that underlie predictive algorithms within the context of the K-Nearest Neighbors (KNN) algorithm for both classification and regression. Additionally, you’ll learn to evaluate the accuracy of a predictive algorithm to assess its ability to generalize to new data. You will build your own KNN classification and regression algorithms from scratch and make predictions with each of them. At the end of this module, we’ll have a quiz to give you the opportunity to evaluate your understanding of predictive algorithms and reflect on your experience implementing your own.

This module, you will learn how to describe the differences between prediction and inference, two key Data Science concepts. You’ll learn how to implement linear regressions — one of the most useful tools that data scientists have for inference and prediction — and other statistical models in Python. You’ll apply this knowledge by examining a dataset and regressing multiple variables on each other, and describing the insights on their relationships.

This module, you’ll bring together the concepts and skills you’ve developed throughout the course to create a final project for your data science portfolio. You’ll recreate a now-famous data visualization that illustrates the relationship between the income of countries and their greenhouse gas emissions on a global scale. To do this, you’ll explore and prepare 4 datasets and merge them into a composite dataset that you’ll plot. Creating this merged dataset is an important step, and you’ll validate your merged dataset with a short quiz on the insights within. The end result of this effort will be a publication-quality plot that makes a compelling point about the relationship between emissions and income—an impactful visualization that showcases your growing programming skills for data science applications.