From the course: Data Science on Google Cloud Platform: Predictive Analytics

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Creating a prediction dataset

Creating a prediction dataset - Google Cloud Tutorial

From the course: Data Science on Google Cloud Platform: Predictive Analytics

Start my 1-month free trial

Creating a prediction dataset

“

- [Instructor] In order to do predictions, we need to create a dataset that contains the feature of predictive variables required for the model. In this specific website propensity model, we need to provide reviews, bought together, compare similar, warranty, and sponsored links. Each of these values is either a one or zero. Predictions can be done for one or many instances of the entity being predicted. Each record is an array of values. Records are separated by new line characters. We created a file called predict-propensity.json with the values. We have five records in the file, representing five website visitors. We want to predict for each one of them. Each record has five values for either one or zero that represents reviews, bought together, compare similar, warranty, and sponsored links. The prediction dataset can either be passed from a local file, a cloud storage file, or from memory variables when using the SDK.

Contents