You're reading from Machine Learning with Amazon SageMaker Cookbook 80 proven recipes for data scientists and developers to perform machine learning experiments and deployments

Product type Paperback

Published in Oct 2021

Publisher Packt

ISBN-13 9781800567030

Length 762 pages

Edition 1st Edition

Languages

Python

Tools

AWS

Concepts

Machine Learning

Author (1):

Joshua Arvin Lat

View More author details

Table of Contents (11) Chapters

Preface

1. Chapter 1: Getting Started with Machine Learning Using Amazon SageMaker

2. Chapter 2: Building and Using Your Own Algorithm Container Image FREE CHAPTER

3. Chapter 3: Using Machine Learning and Deep Learning Frameworks with Amazon SageMaker

4. Chapter 4: Preparing, Processing, and Analyzing the Data

5. Chapter 5: Effectively Managing Machine Learning Experiments

6. Chapter 6: Automated Machine Learning in Amazon SageMaker

7. Chapter 7: Working with SageMaker Feature Store, SageMaker Clarify, and SageMaker Model Monitor

8. Chapter 8: Solving NLP, Image Classification, and Time-Series Forecasting Problems with Built-in Algorithms

9. Chapter 9: Managing Machine Learning Workflows and Deployments

10. Other Books You May Enjoy

Training your first model in Python

In the previous recipe, we generated a scatter plot diagram to explore the relationship between the two variables in the dataset. In this recipe, we will use the SageMaker Linear Learner built-in algorithm to build a linear regression model that predicts a professional's salary using the number of months of relevant managerial experience. This recipe aims to demonstrate how a SageMaker built-in algorithm is used in a ML experiment that involves the train-test split and running the training job:

Figure 1.37 – Performing the train-test split and then running the training jobs to generate a model

Figure 1.37 shows us what we will do in this recipe. Using the DataFrame loaded from the Visualizing and understanding your data in Python recipe, we will perform the train-test split and use the training dataset to train and build the model.