Feature Engineering: Missing Data and Standardization

This lecture covers techniques for dealing with missing data, such as dropping data points or filling missing values. It also explains standardization, a method to scale data by shifting its mean to 0 and standardizing its deviation to 1. The lecture further explores transformations of input and output data, including feature engineering, vector features, and transformations to handle categorical predictors. Examples are provided to illustrate the impact of these techniques on linear regression models.