docs: address lint errors in code samples (#665)

Towards internal issue 332735129

test: move samples tests to their own kokoro jobs

Author: tswast

.kokoro/continuous/e2e.cfg

@@ -3,7 +3,7 @@
 # Only run this nox session.
 env_vars: {
     key: "NOX_SESSION"
-    value: "unit_prerelease system_prerelease system_noextras e2e notebook samples"
+    value: "unit_prerelease system_prerelease system_noextras e2e notebook"
 }
 
 env_vars: {

.kokoro/presubmit/e2e-gerrit.cfg

@@ -3,5 +3,5 @@
 # Only run this nox session.
 env_vars: {
     key: "NOX_SESSION"
-    value: "system_noextras e2e notebook samples"
+    value: "system_noextras e2e notebook"
 }

.kokoro/presubmit/e2e.cfg

@@ -3,7 +3,7 @@
 # Only run this nox session.
 env_vars: {
     key: "NOX_SESSION"
-    value: "unit_prerelease system_prerelease system_noextras e2e notebook samples"
+    value: "unit_prerelease system_prerelease system_noextras e2e notebook"
 }
 
 env_vars: {

noxfile.py

@@ -402,26 +402,6 @@ def load(session: nox.sessions.Session):
     )
 
 
-@nox.session(python=SYSTEM_TEST_PYTHON_VERSIONS)
-def samples(session):
-    """Run the samples test suite."""
-
-    constraints_path = str(
-        CURRENT_DIRECTORY / "testing" / f"constraints-{session.python}.txt"
-    )
-
-    # TODO(b/332735129): Remove this session and use python_samples templates
-    # where each samples directory has its own noxfile.py file, instead.
-    install_test_extra = True
-    install_systemtest_dependencies(session, install_test_extra, "-c", constraints_path)
-
-    session.run(
-        "py.test",
-        "samples",
-        *session.posargs,
-    )
-
-
 @nox.session(python=DEFAULT_PYTHON_VERSION)
 def cover(session):
     """Run the final coverage report.

owlbot.py

@@ -74,7 +74,7 @@
         import pandas
         import pyarrow
         import sqlglot
-        
+
         print(f"Python: {sys.version}")
         print(f"bigframes=={bigframes.__version__}")
         print(f"google-cloud-bigquery=={google.cloud.bigquery.__version__}")
@@ -83,7 +83,7 @@
         print(f"pyarrow=={pyarrow.__version__}")
         print(f"sqlglot=={sqlglot.__version__}")
         ```
-        
+
         #### Steps to reproduce
         """,
     ),
@@ -148,3 +148,5 @@
 # ----------------------------------------------------------------------------
 
 s.shell.run(["nox", "-s", "format"], hide_output=False)
+for noxfile in REPO_ROOT.glob("samples/**/noxfile.py"):
+    s.shell.run(["nox", "-s", "format"], cwd=noxfile.parent, hide_output=False)

samples/snippets/bqml_getting_started_test.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-def test_bqml_getting_started(random_model_id):
+def test_bqml_getting_started(random_model_id: str) -> None:
     your_model_id = random_model_id  # for example: bqml_tutorial.sample_model
 
     # [START bigquery_dataframes_bqml_getting_started_tutorial]

samples/snippets/clustering_model_test.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-def test_clustering_model():
+def test_clustering_model() -> None:
     # [START bigquery_dataframes_clustering_model]
     from bigframes.ml.cluster import KMeans
     import bigframes.pandas as bpd

samples/snippets/conftest.py

@@ -46,7 +46,7 @@ def project_id(bigquery_client: bigquery.Client) -> str:
 
 
 @pytest.fixture(autouse=True)
-def reset_session():
+def reset_session() -> None:
     """An autouse fixture ensuring each sample runs in a fresh session.
 
     This allows us to have samples that query data in different locations.

samples/snippets/create_kmeans_model_test.py

@@ -13,12 +13,14 @@
 # limitations under the License.
 
 
-def test_kmeans_sample(project_id: str, random_model_id_eu: str):
+def test_kmeans_sample(project_id: str, random_model_id_eu: str) -> None:
     your_gcp_project_id = project_id
     your_model_id = random_model_id_eu
     # [START bigquery_dataframes_bqml_kmeans]
     import datetime
 
+    import pandas as pd
+
     import bigframes
     import bigframes.pandas as bpd
 
@@ -92,7 +94,9 @@ def test_kmeans_sample(project_id: str, random_model_id_eu: str):
     stationstats = merged_df.groupby(["station_name", "isweekday"]).agg(
         {"duration": ["mean", "count"], "distance_from_city_center": "max"}
     )
-    stationstats.columns = ["duration", "num_trips", "distance_from_city_center"]
+    stationstats.columns = pd.Index(
+        ["duration", "num_trips", "distance_from_city_center"]
+    )
     stationstats = stationstats.sort_values(
         by="distance_from_city_center", ascending=True
     ).reset_index()

samples/snippets/create_multiple_timeseries_forecasting_model.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-def test_multiple_timeseries_forecasting_model(random_model_id):
+def test_multiple_timeseries_forecasting_model(random_model_id: str) -> None:
     your_model_id = random_model_id
 
     # [START bigquery_dataframes_bqml_arima_multiple_step_2_visualize]

samples/snippets/create_single_timeseries_forecasting_model_test.py

@@ -13,8 +13,7 @@
 # limitations under the License.
 
 
-def test_create_single_timeseries():
-
+def test_create_single_timeseries() -> None:
     # [START bigquery_dataframes_single_timeseries_forecasting_model_tutorial]
     import bigframes.pandas as bpd
 

samples/snippets/explore_query_result_test.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-def test_bigquery_dataframes_explore_query_result():
+def test_bigquery_dataframes_explore_query_result() -> None:
     import bigframes.pandas as bpd
 
     # [START bigquery_dataframes_explore_query_result]

samples/snippets/gemini_model_test.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-def test_gemini_text_generator_model():
+def test_gemini_text_generator_model() -> None:
     # Determine project id, in this case prefer the one set in the environment
     # variable GOOGLE_CLOUD_PROJECT (if any)
     import os

samples/snippets/gen_ai_model_test.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-def test_llm_model():
+def test_llm_model() -> None:
     # Determine project id, in this case prefer the one set in the environment
     # variable GOOGLE_CLOUD_PROJECT (if any)
     import os

samples/snippets/load_data_from_bigquery_test.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-def test_bigquery_dataframes_load_data_from_bigquery():
+def test_bigquery_dataframes_load_data_from_bigquery() -> None:
     # [START bigquery_dataframes_load_data_from_bigquery]
     # Create a DataFrame from a BigQuery table:
     import bigframes.pandas as bpd

samples/snippets/load_data_from_biquery_job_test.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-def test_bigquery_dataframes_load_data_from_bigquery_job():
+def test_bigquery_dataframes_load_data_from_bigquery_job() -> None:
     # Determine project id, in this case prefer the one set in the environment
     # variable GOOGLE_CLOUD_PROJECT (if any)
     import os

samples/snippets/load_data_from_csv_test.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-def test_bigquery_dataframes_load_data_from_csv():
+def test_bigquery_dataframes_load_data_from_csv() -> None:
     # [START bigquery_dataframes_load_data_from_csv]
     import bigframes.pandas as bpd