You're reading from Machine Learning with BigQuery ML Create, execute, and improve machine learning models in BigQuery using standard SQL queries

Product type Paperback

Published in Jun 2021

Publisher Packt

ISBN-13 9781800560307

Length 344 pages

Edition 1st Edition

Languages

Python

Tools

BigQuery

Concepts

Machine Learning

Author (1):

Alessandro Marrandino

View More author details

Table of Contents (20) Chapters

Preface

1. Section 1: Introduction and Environment Setup

2. Chapter 1: Introduction to Google Cloud and BigQuery FREE CHAPTER

3. Chapter 2: Setting Up Your GCP and BigQuery Environment

4. Chapter 3: Introducing BigQuery Syntax

5. Section 2: Deep Learning Networks

6. Chapter 4: Predicting Numerical Values with Linear Regression

7. Chapter 5: Predicting Boolean Values Using Binary Logistic Regression

8. Chapter 6: Classifying Trees with Multiclass Logistic Regression

9. Section 3: Advanced Models with BigQuery ML

10. Chapter 7: Clustering Using the K-Means Algorithm

11. Chapter 8: Forecasting Using Time Series

12. Chapter 9: Suggesting the Right Product by Using Matrix Factorization

13. Chapter 10: Predicting Boolean Values Using XGBoost

14. Chapter 11: Implementing Deep Neural Networks

15. Section 4: Further Extending Your ML Capabilities with GCP

16. Chapter 12: Using BigQuery ML with AI Notebooks

17. Chapter 13: Running TensorFlow Models with BigQuery ML

18. Chapter 14: BigQuery ML Tips and Best Practices

19. Other Books You May Enjoy

Running TensorFlow models with BigQuery ML

In this section, we'll import the TensorFlow model that we exported in the Converting BigQuery ML models into TensorFlow section. Once the model has been imported, we'll use it through the BigQuery ML syntax.

First, we need to remember that our BigQuery ML model has been exported into the folder of a Google Cloud storage bucket. The ML model is stored in the TensorFlow SavedModel format and is in the same format as any other ML model that's been developed by a data scientist using TensorFlow.

If we want to use a TensorFlow model in BigQuery ML, we need to perform the following steps:

First, let's run the CREATE OR REPLACE MODEL SQL statement. Keep in mind that the path of the bucket – 'gs://<PROJECT_NAME>-us-bigqueryml-export-tf/bqml_exported_model/*' – is based on the name of your current project, so you need to replace the <PROJECT_NAME> placeholder with the...