The ML.FEATURE_INFO function


The ML.FEATURE_INFO function allows you to see information about the input features used to train a model.

ML.FEATURE_INFO returns the following columns:

  • input — The name of the column in the input training data.
  • min — The sample minimum. This column is NULL for non-numeric inputs.
  • max — The sample maximum. This column is NULL for non-numeric inputs.
  • mean — The average. This column is NULL for non-numeric inputs.
  • stddev — The standard deviation. This column is NULL for non-numeric inputs.
  • category_count — The number of categories. This column is NULL for non-categorical columns.
  • null_count — The number of NULLs.

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

ML.FEATURE_INFO permissions

Both bigquery.models.create and bigquery.models.getData are required to run ML.FEATURE_INFO.

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


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


  • project_id is your project ID.
  • dataset is the BigQuery dataset that contains the model.
  • model is the name of the model.


The following example retrieves feature information from mymodel in mydataset. The dataset is in your default project.

  ML.FEATURE_INFO(MODEL `mydataset.mymodel`)

ML.FEATURE_INFO limitations

The ML.FEATURE_INFO function is subject to the following limitations: