feat: Add BigQuery ML CREATE MODEL support

- Refactor `bigframes.core.sql` to a package.
- Add `bigframes.core.sql.ml` for DDL generation.
- Add `bigframes.bigquery.ml` module with `create_model` function.
- Add unit tests for SQL generation.
- Use `_start_query_ml_ddl` for execution.

Author: google-labs-jules[bot]

bigframes/bigquery/_operations/ml.py

@@ -0,0 +1,83 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import typing
+from typing import Mapping, Optional, Union
+
+import bigframes.core.sql.ml
+import bigframes.core.log_adapter as log_adapter
+import bigframes.dataframe as dataframe
+import bigframes.session
+
+@log_adapter.method_logger(custom_base_name="bigquery_ml")
+def create_model(
+    model_name: str,
+    *,
+    replace: bool = False,
+    if_not_exists: bool = False,
+    transform: Optional[list[str]] = None,
+    input_schema: Optional[Mapping[str, str]] = None,
+    output_schema: Optional[Mapping[str, str]] = None,
+    connection_name: Optional[str] = None,
+    options: Optional[Mapping[str, Union[str, int, float, bool, list]]] = None,
+    query: Optional[Union[dataframe.DataFrame, str]] = None,
+    training_data: Optional[Union[dataframe.DataFrame, str]] = None,
+    custom_holiday: Optional[Union[dataframe.DataFrame, str]] = None,
+    session: Optional[bigframes.session.Session] = None,
+) -> None:
+    """
+    Creates a BigQuery ML model.
+    """
+    import bigframes.pandas as bpd
+
+    # Helper to convert DataFrame to SQL string
+    def _to_sql(df_or_sql: Union[dataframe.DataFrame, str]) -> str:
+        if isinstance(df_or_sql, str):
+            return df_or_sql
+        # It's a DataFrame
+        sql, _, _ = df_or_sql._to_sql_query(include_index=True)
+        return sql
+
+    query_statement = _to_sql(query) if query is not None else None
+    training_data_sql = _to_sql(training_data) if training_data is not None else None
+    custom_holiday_sql = _to_sql(custom_holiday) if custom_holiday is not None else None
+
+    # Determine session from DataFrames if not provided
+    if session is None:
+        # Try to get session from inputs
+        dfs = [obj for obj in [query, training_data, custom_holiday] if hasattr(obj, "_session")]
+        if dfs:
+            session = dfs[0]._session
+
+    sql = bigframes.core.sql.ml.create_model_ddl(
+        model_name=model_name,
+        replace=replace,
+        if_not_exists=if_not_exists,
+        transform=transform,
+        input_schema=input_schema,
+        output_schema=output_schema,
+        connection_name=connection_name,
+        options=options,
+        query_statement=query_statement,
+        training_data=training_data_sql,
+        custom_holiday=custom_holiday_sql,
+    )
+
+    if session is None:
+        session = bpd.get_global_session()
+
+    # Use _start_query_ml_ddl which is designed for this
+    session._start_query_ml_ddl(sql)

bigframes/bigquery/ml.py

@@ -0,0 +1,21 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""This module integrates BigQuery ML functions."""
+
+from bigframes.bigquery._operations.ml import create_model
+
+__all__ = [
+    "create_model",
+]

bigframes/core/sql.py bigframes/core/sql/__init__.pybigframes/core/sql.py renamed to bigframes/core/sql/__init__.py

@@ -0,0 +1,100 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import typing
+from typing import Mapping, Optional, Union
+
+import bigframes.core.compile.googlesql as googlesql
+import bigframes.core.sql
+
+def create_model_ddl(
+    model_name: str,
+    *,
+    replace: bool = False,
+    if_not_exists: bool = False,
+    transform: Optional[list[str]] = None,
+    input_schema: Optional[Mapping[str, str]] = None,
+    output_schema: Optional[Mapping[str, str]] = None,
+    connection_name: Optional[str] = None,
+    options: Optional[Mapping[str, Union[str, int, float, bool, list]]] = None,
+    query_statement: Optional[str] = None,
+    training_data: Optional[str] = None,
+    custom_holiday: Optional[str] = None,
+) -> str:
+    """Encode the CREATE MODEL statement."""
+
+    if replace:
+        create = "CREATE OR REPLACE MODEL "
+    elif if_not_exists:
+        create = "CREATE MODEL IF NOT EXISTS "
+    else:
+        create = "CREATE MODEL "
+
+    ddl = f"{create}{googlesql.identifier(model_name)}\n"
+
+    # [TRANSFORM (select_list)]
+    if transform:
+        ddl += f"TRANSFORM ({', '.join(transform)})\n"
+
+    # [INPUT (field_name field_type) OUTPUT (field_name field_type)]
+    if input_schema:
+        inputs = [f"{k} {v}" for k, v in input_schema.items()]
+        ddl += f"INPUT ({', '.join(inputs)})\n"
+
+    if output_schema:
+        outputs = [f"{k} {v}" for k, v in output_schema.items()]
+        ddl += f"OUTPUT ({', '.join(outputs)})\n"
+
+    # [REMOTE WITH CONNECTION {connection_name | DEFAULT}]
+    if connection_name:
+        if connection_name.upper() == "DEFAULT":
+             ddl += "REMOTE WITH CONNECTION DEFAULT\n"
+        else:
+             ddl += f"REMOTE WITH CONNECTION {googlesql.identifier(connection_name)}\n"
+
+    # [OPTIONS(model_option_list)]
+    if options:
+        rendered_options = []
+        for option_name, option_value in options.items():
+            if isinstance(option_value, (list, tuple)):
+                # Handle list options like model_registry="vertex_ai"
+                # wait, usually options are key=value.
+                # if value is list, it is [val1, val2]
+                rendered_val = bigframes.core.sql.simple_literal(list(option_value))
+            else:
+                 rendered_val = bigframes.core.sql.simple_literal(option_value)
+
+            rendered_options.append(f"{option_name} = {rendered_val}")
+
+        ddl += f"OPTIONS({', '.join(rendered_options)})\n"
+
+    # [AS {query_statement | ( training_data AS (query_statement), custom_holiday AS (holiday_statement) )}]
+
+    if query_statement and (training_data or custom_holiday):
+        raise ValueError("Cannot specify both `query_statement` and (`training_data` or `custom_holiday`).")
+
+    if query_statement:
+        ddl += f"AS {query_statement}"
+    elif training_data:
+        # specialized AS clause
+        parts = []
+        parts.append(f"training_data AS ({training_data})")
+        if custom_holiday:
+            parts.append(f"custom_holiday AS ({custom_holiday})")
+
+        ddl += f"AS (\n  {', '.join(parts)}\n)"
+
+    return ddl

bigframes/core/sql/ml.py

@@ -0,0 +1,3 @@
+CREATE MODEL `my_project.my_dataset.my_model`
+OPTIONS(model_type = 'LINEAR_REG', input_label_cols = ['label'])
+AS SELECT * FROM my_table

tests/unit/core/sql/snapshots/test_ml/test_create_model_basic/create_model_basic.sql

@@ -0,0 +1,3 @@
+CREATE MODEL IF NOT EXISTS `my_model`
+OPTIONS(model_type = 'KMEANS')
+AS SELECT * FROM t

tests/unit/core/sql/snapshots/test_ml/test_create_model_if_not_exists/create_model_if_not_exists.sql

@@ -0,0 +1,3 @@
+CREATE MODEL `my_model`
+OPTIONS(hidden_units = [32, 16], dropout = 0.2)
+AS SELECT * FROM t

tests/unit/core/sql/snapshots/test_ml/test_create_model_list_option/create_model_list_option.sql

@@ -0,0 +1,5 @@
+CREATE MODEL `my_remote_model`
+INPUT (prompt STRING)
+OUTPUT (content STRING)
+REMOTE WITH CONNECTION `my_project.us.my_connection`
+OPTIONS(endpoint = 'gemini-pro')

tests/unit/core/sql/snapshots/test_ml/test_create_model_remote/create_model_remote.sql

@@ -0,0 +1,3 @@
+CREATE MODEL `my_remote_model`
+REMOTE WITH CONNECTION DEFAULT
+OPTIONS(endpoint = 'gemini-pro')

tests/unit/core/sql/snapshots/test_ml/test_create_model_remote_default/create_model_remote_default.sql

@@ -0,0 +1,3 @@
+CREATE OR REPLACE MODEL `my_model`
+OPTIONS(model_type = 'LOGISTIC_REG')
+AS SELECT * FROM t