Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://developers.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-xgboost below:

The CREATE MODEL statement for importing XGBoost models | BigQuery

Stay organized with collections Save and categorize content based on your preferences.

This document describes the CREATE MODEL statement for importing XGBoost models into BigQuery by using SQL. Alternatively, you can use the Google Cloud console user interface to create a model by using a UI (Preview) instead of constructing the SQL statement yourself.

For information about the supported SQL statements and functions for each model type, see End-to-end user journey for each model.

{CREATE MODEL | CREATE MODEL IF NOT EXISTS | CREATE OR REPLACE MODEL}
model_name
[INPUT(field_name field_type, …)
 OUTPUT(field_name field_type, …)]
OPTIONS(MODEL_TYPE = 'XGBOOST', MODEL_PATH = string_value
  [, KMS_KEY_NAME = string_value ]
);

Creates and trains a new model in the specified dataset. If the model name exists, CREATE MODEL returns an error.

Creates and trains a new model only if the model doesn't exist in the specified dataset.

Creates and trains a model and replaces an existing model with the same name in the specified dataset.

The name of the model you're creating or replacing. The model name must be unique in the dataset: no other model or table can have the same name. The model name must follow the same naming rules as a BigQuery table. A model name can:

• Contain up to 1,024 characters
• Contain letters (upper or lower case), numbers, and underscores

model_name is not case-sensitive.

If you don't have a default project configured, then you must prepend the project ID to the model name in the following format, including backticks:

`[PROJECT_ID].[DATASET].[MODEL]`

For example, `myproject.mydataset.mymodel`.

The INPUT OUTPUT clause lets you specify the model input output schema information when you create the XGBoost model.

INPUT OUTPUT is optional only if feature_names and feature_types are both specified in the model file. For more information about how to store feature_names and feature_types in the XGBoost model file, see Introduction to Model IO.

Use field_name to define the name of an input feature or a model output.

If the feature_names field is populated in the XGBoost model file, the input field names must be identical to the names in the feature_names field. For more information, see the XGBoost model JSON Schema.

Use field_type to specify the data type of an input feature or a model output. Input data types must be one of the supported numeric types. The output data type must be FLOAT64.

Example

INPUT(f1 INT64, f2 FLOAT64, f3 FLOAT64)
OUTPUT(predicted_label FLOAT64)

Syntax

MODEL_TYPE = 'XGBOOST'

Description

Specifies the model type. This option is required.

Syntax

MODEL_PATH = string_value

Description

Specifies the Cloud Storage URI of the XGBoost model to import. This option is required.

Arguments

A STRING value specifying the URI of a Cloud Storage bucket that contains the model to import.

BigQuery ML imports the model from Cloud Storage by using the credentials of the user who runs the CREATE MODEL statement.

Example

MODEL_PATH = 'gs://bucket/path/to/xgboost_model/*'

Syntax

KMS_KEY_NAME = string_value

Description

The Cloud Key Management Service customer-managed encryption key (CMEK) to use to encrypt the model.

Arguments

A STRING value containing the fully-qualified name of the CMEK. For example,

'projects/my_project/locations/my_location/keyRings/my_ring/cryptoKeys/my_key'

For information about supported locations, see Locations for non-remote models.

Imported XGBoost models have the following limitations:

• The XGBoost model must already exist before it can be imported into BigQuery.
• Models must be stored in Cloud Storage.
• XGBoost models must be in BST or JSON format.
• You can only use XGBoost models with the ML.PREDICT and ML.FEATURE_IMPORTANCE functions.
• Models are limited to 250 MB in size.
• The memory limit to load and run the XGBoost model is 840 MB. You can reduce the model size by using fewer trees or shallower tree depth, or by using the XGBoost library's default save_model method to save the models.
• BigQuery ML uses the XGBoost 1.5.1 library to load and make predictions on XGBoost models. Forward compatibility for models saved with XGBoost version 1.6.0 or newer is not guaranteed.
• BigQuery XGBoost models only support numeric types as input data types and FLOAT64 as the output data type.
• Categorical features that use XGBoost built-in categorical data support are treated as integer inputs.
• BigQuery XGBoost models only support a single scalar or array output. Multiple outputs aren't supported.
• You can only use an imported XGBoost model with an object table when you use capacity-based pricing through reservations. On-demand pricing isn't supported.

The following examples show how to create different types of imported XGBoost models.

The following example imports a XGBoost model into BigQuery as a BigQuery model. The example assumes the following:

• There is an existing XGBoost model located at gs://bucket-name/xgboost-model/*.
• The model file is in BST format or inJSON` format.
• The model file doesn't contain information about input feature_names and feature_types.

CREATE OR REPLACE
  MODEL
    `project_id.mydataset.mymodel`
      INPUT(f1 float64, f2 float64, f3 float64, f4 float64)
      OUTPUT(predicted_label float64)
  OPTIONS (
    MODEL_TYPE = 'XGBOOST',
    MODEL_PATH = 'gs://bucket-name/xgboost-model/*')

The following example imports a XGBoost model into BigQuery as a BigQuery model. The example assumes the following:

• There is an existing XGBoost model located at gs://bucket-name/xgboost-model/*.
• The model file is in BST format or in JSON format.
• The model file contains information about input feature_names and feature_types.

CREATE OR REPLACE
  MODEL
    `project_id.mydataset.mymodel`
  OPTIONS (
    MODEL_TYPE = 'XGBOOST',
    MODEL_PATH = 'gs://bucket-name/xgboost-model/*')

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-08-11 UTC.

[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-11 UTC."],[[["The `CREATE MODEL` statement enables the import of pre-existing XGBoost models into BigQuery, using options to specify the model type, path, and input/output schema."],["You can choose between `CREATE MODEL`, `CREATE MODEL IF NOT EXISTS`, or `CREATE OR REPLACE MODEL` to manage model creation and replacement, ensuring uniqueness within the dataset."],["The `INPUT` and `OUTPUT` clauses are used to define the model's schema, but are optional if the XGBoost model file already includes `feature_names` and `feature_types`."],["Imported XGBoost models must be in `.bst` or `.json` format, stored in Cloud Storage, and have certain limitations such as a maximum size of 250 MB and constraints on input/output data types, only supporting the `ML.PREDICT` and `ML.FEATURE_IMPORTANCE` functions."],["`MODEL_PATH` and `MODEL_TYPE` options are mandatory, specifying the Cloud Storage URI of the model and defining it as an 'XGBOOST' model type, while `KMS_KEY_NAME` is optional for customer-managed encryption."]]],[]]

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4