The ML.FEATURE_INFO function

This document describes the ML.FEATURE_INFO function, which lets you see information about the input features that are used to train a model.

Syntax

ML.FEATURE_INFO(MODEL `project_id.dataset.model`)

Arguments

ML.FEATURE_INFO takes the following arguments:

Output

ML.FEATURE_INFO returns the following columns:

For matrix factorization models, only category_count is calculated for the user and item columns.

If you used the TRANSFORM clause in the CREATE MODEL statement that created the model, ML.FEATURE_INFO outputs the information of the pre-transform columns from the query_statement argument.

Permissions

You must have the bigquery.models.create and bigquery.models.getData Identity and Access Management (IAM) permissions in order to run ML.FEATURE_INFO.

Limitations

ML.FEATURE_INFO doesn't support imported TensorFlow models.

Example

The following example retrieves feature information from the model mydataset.mymodel in your default project:

SELECT
  *
FROM
  ML.FEATURE_INFO(MODEL `mydataset.mymodel`)

What's next