Testing Your Models in the Real World

How do you know that your models will do a good job making predictions on new, unseen data?

This lab will discuss the fundamentals of splitting your data into training, validation, and test data sets and demonstrate the dangers of overreliance on training data to make predictions.

Learning Objectives

Upon completion of this lab you will be able to:

• Import data using pandas
• Prepare data for modeling
• Split the dataset into training and test data
• Tune models using validation data
• Evaluating models on a test dataset

Intended Audience

This lab is intended for:

• Machine learning engineers
• Anyone interested in evaluating machine learning model performance

Prerequisites

You should possess:

• A basic understanding of Python