Merge branch 'main' into main_chelsealin_sqlglotbug

Author: chelsea-lin

bigframes/operations/ai.py

@@ -612,8 +612,11 @@ def sim_join(
             >>> df1 = bpd.DataFrame({'animal': ['monkey', 'spider']})
             >>> df2 = bpd.DataFrame({'animal': ['scorpion', 'baboon']})
 
-            >>> df1.ai.sim_join(df2, left_on='animal', right_on='animal', model=model, top_k=1)
-            animal  animal_1
+            >>> res = df1.ai.sim_join(df2, left_on='animal', right_on='animal', model=model, top_k=1)
+            >>> print("---"); print(res) # doctest: +ELLIPSIS
+            ---
+            ...
+               animal  animal_1
             0  monkey    baboon
             1  spider  scorpion
             <BLANKLINE>

bigframes/session/__init__.py

@@ -664,9 +664,11 @@ def read_gbq_query(
             ...     WHERE year = 2016
             ...     GROUP BY pitcherFirstName, pitcherLastName
             ... ''', index_col="rowindex")
-            >>> df.head(2)
+            >>> print("START_OF_OUTPUT"); df.head(2) # doctest: +ELLIPSIS,+NORMALIZE_WHITESPACE
+            START_OF_OUTPUT
+            ...
                      pitcherFirstName pitcherLastName  averagePitchSpeed
-            rowindex
+            ...
             1                Albertin         Chapman          96.514113
             2                 Zachary         Britton          94.591039
             <BLANKLINE>

tests/system/small/test_session.py

@@ -1380,6 +1380,9 @@ def test_read_csv_for_gcs_wildcard_path(session, df_and_gcs_csv):
     bigframes.testing.utils.assert_frame_equal(bf_df.to_pandas(), pd_df.to_pandas())
 
 
+@pytest.mark.skip(
+    reason="Unstable test blocking PR submissions. Tracking bug b/497970577"
+)
 def test_read_csv_for_names(session, df_and_gcs_csv_for_two_columns):
     _, path = df_and_gcs_csv_for_two_columns
 

third_party/bigframes_vendored/pandas/io/gbq.py

@@ -86,9 +86,11 @@ def read_gbq(
             ...     WHERE year = 2016
             ...     GROUP BY pitcherFirstName, pitcherLastName
             ... ''', index_col="rowindex")
-            >>> df.head(2)
+            >>> print("START_OF_OUTPUT"); df.head(2) # doctest: +ELLIPSIS,+NORMALIZE_WHITESPACE
+            START_OF_OUTPUT
+            ...
                      pitcherFirstName pitcherLastName  averagePitchSpeed
-            rowindex
+            ...
             1                Albertin         Chapman          96.514113
             2                 Zachary         Britton          94.591039
             <BLANKLINE>