fix: add license header and correct issues in dbt sample (#1931)

Author: jialuoo

samples/dbt/.dbt.yml

@@ -1,3 +1,17 @@
+# Copyright 2019 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.
+
 dbt_sample_project:
   outputs:
     dev:        # The target environment name (e.g., dev, prod)

samples/dbt/dbt_sample_project/dbt_project.yml

@@ -1,3 +1,16 @@
+# Copyright 2019 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.
 
 # Name your project! Project names should contain only lowercase characters
 # and underscores. A good package name should reflect your organization's

samples/dbt/dbt_sample_project/models/example/dbt_bigframes_code_sample_1.py

@@ -1,3 +1,17 @@
+# Copyright 2019 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 example demonstrates one of the most general usages of transforming raw
 # BigQuery data into a processed table using a dbt Python model with BigFrames.
 # See more from: https://cloud.google.com/bigquery/docs/dataframes-dbt.
@@ -32,7 +46,13 @@ def model(dbt, session):
     table = "bigquery-public-data.epa_historical_air_quality.temperature_hourly_summary"
 
     # Define the specific columns to select from the BigQuery table.
-    columns = ["state_name", "county_name", "date_local", "time_local", "sample_measurement"]
+    columns = [
+        "state_name",
+        "county_name",
+        "date_local",
+        "time_local",
+        "sample_measurement",
+    ]
 
     # Read data from the specified BigQuery table into a BigFrames DataFrame.
     df = session.read_gbq(table, columns=columns)
@@ -44,14 +64,16 @@ def model(dbt, session):
     # Group the DataFrame by 'state_name', 'county_name', and 'date_local'. For
     # each group, calculate the minimum and maximum of the 'sample_measurement'
     # column. The result will be a BigFrames DataFrame with a MultiIndex.
-    result = df.groupby(["state_name", "county_name", "date_local"])["sample_measurement"]\
-        .agg(["min", "max"])
+    result = df.groupby(["state_name", "county_name", "date_local"])[
+        "sample_measurement"
+    ].agg(["min", "max"])
 
     # Rename some columns and convert the MultiIndex of the 'result' DataFrame
     # into regular columns. This flattens the DataFrame so 'state_name',
     # 'county_name', and 'date_local' become regular columns again.
-    result = result.rename(columns={'min': 'min_temperature', 'max': 'max_temperature'})\
-        .reset_index()
+    result = result.rename(
+        columns={"min": "min_temperature", "max": "max_temperature"}
+    ).reset_index()
 
     # Return the processed BigFrames DataFrame.
     # In a dbt Python model, this DataFrame will be materialized as a table

samples/dbt/dbt_sample_project/models/example/dbt_bigframes_code_sample_2.py

@@ -1,6 +1,20 @@
+# Copyright 2019 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 example demonstrates how to build an **incremental dbt Python model**
 # using BigFrames.
-# 
+#
 # Incremental models are essential for efficiently processing large datasets by
 # only transforming new or changed data, rather than reprocessing the entire
 # dataset every time. If the target table already exists, dbt will perform a
@@ -13,8 +27,6 @@
 # directly within BigQuery, leveraging BigQuery's scalability.
 
 
-import bigframes.pandas as bpd
-
 def model(dbt, session):
     # Optional: override settings from dbt_project.yml.
     # When both are set, dbt.config takes precedence over dbt_project.yml.
@@ -24,9 +36,9 @@ def model(dbt, session):
         submission_method="bigframes",
         # Materialize this model as an 'incremental' table. This tells dbt to
         # only process new or updated data on subsequent runs.
-        materialized='incremental',
+        materialized="incremental",
         # Use MERGE strategy to update rows during incremental runs.
-        incremental_strategy='merge',
+        incremental_strategy="merge",
         # Define the composite key that uniquely identifies a row in the
         # target table. This key is used by the 'merge' strategy to match
         # existing rows for updates during incremental runs.
@@ -41,7 +53,7 @@ def model(dbt, session):
     # Define a BigFrames UDF to generate a temperature description.
     # BigFrames UDFs allow you to define custom Python logic that executes
     # directly within BigQuery. This is powerful for complex transformations.
-    @bpd.udf(dataset='dbt_sample_dataset', name='describe_udf')
+    @session.udf(dataset="dbt_sample_dataset", name="describe_udf")
     def describe(
         max_temperature: float,
         min_temperature: float,