From the course: Data Warehousing on Google Cloud Platform

Unlock this course with a free trial

Join today to access over 25,300 courses taught by industry experts.

Demo: Predictive analytics using SQL and BigQuery

Demo: Predictive analytics using SQL and BigQuery - Google Cloud Platform Tutorial

From the course: Data Warehousing on Google Cloud Platform

Demo: Predictive analytics using SQL and BigQuery

- [Instructor] Let's use BigQuery ML to create a model to predict the number of orders. We'll use a Jupyter Notebook and CoLab to go through the steps for creating a model. You can, again, access CoLab at colab.research.google.com. You can start by opening the Create Sales Forecast model file from our GitHub repository and upload the file to CoLab. You'll need to have your Google Cloud account and project set up, as well as the sales data, data set, and the sales table created before starting this exercise. Let's first get authenticated, set your project ID, and we're going to import the library and set our project ID. We'll run the following Python code to create a function that will help us plot the historic and predicted values. Here we'll create a model called Orders underscore Forecast. We'll use the Create Model statement to begin creating the model. I'll use the ARIMA-model type with order date for our timestamp, and the number of orders for the predicted value. Our model's now…

Contents