Merge branch 'main' into helmeleegy-SNOW-2676993

Author: sfc-gh-helmeleegy

CHANGELOG.md

@@ -157,6 +157,7 @@
   - `groupby.any`
   - `groupby.all`
   - `groupby.unique`
+  - `to_snowflake`
   - `to_snowpark`
 - Make faster pandas disabled by default (opt-in instead of opt-out).
 - Improve performance of `drop_duplicates` by avoiding joins when `keep!=False` in faster pandas.

src/snowflake/snowpark/dataframe.py

@@ -6171,7 +6171,16 @@ def with_column_renamed(
         else:
             raise TypeError(f"{str(existing)} must be a column name or Column object.")
 
-        to_be_renamed = [x for x in self._output if x.name.upper() == old_name.upper()]
+        from snowflake.snowpark import context
+
+        if context._is_snowpark_connect_compatible_mode:
+            to_be_renamed = [
+                x for x in self._output if quote_name(x.name) == quote_name(old_name)
+            ]
+        else:  # this is wrong, but we need to keep it for backward compatibility. Should be removed in the future when Snowpark Python Client has a major version bump.
+            to_be_renamed = [
+                x for x in self._output if x.name.upper() == old_name.upper()
+            ]
         if not to_be_renamed:
             raise ValueError(
                 f'Unable to rename column "{existing}" because it doesn\'t exist.'

src/snowflake/snowpark/modin/plugin/compiler/snowflake_query_compiler.py

@@ -2282,6 +2282,34 @@ def to_snowflake(
         index: bool = True,
         index_label: Optional[IndexLabel] = None,
         table_type: Literal["", "temp", "temporary", "transient"] = "",
+    ) -> None:
+        """
+        Wrapper around _to_snowflake_internal to be supported in faster pandas.
+        """
+        if self._relaxed_query_compiler is not None and not index:
+            self._relaxed_query_compiler._to_snowflake_internal(
+                name=name,
+                if_exists=if_exists,
+                index=index,
+                index_label=index_label,
+                table_type=table_type,
+            )
+        else:
+            self._to_snowflake_internal(
+                name=name,
+                if_exists=if_exists,
+                index=index,
+                index_label=index_label,
+                table_type=table_type,
+            )
+
+    def _to_snowflake_internal(
+        self,
+        name: Union[str, Iterable[str]],
+        if_exists: Optional[Literal["fail", "replace", "append"]] = "fail",
+        index: bool = True,
+        index_label: Optional[IndexLabel] = None,
+        table_type: Literal["", "temp", "temporary", "transient"] = "",
     ) -> None:
         self._warn_lost_snowpark_pandas_type("to_snowflake")
         handle_if_exists_for_to_snowflake(if_exists=if_exists, name=name)

tests/integ/modin/test_faster_pandas.py

@@ -1752,6 +1752,40 @@ def test_series_to_datetime(session):
         assert_series_equal(snow_result, native_result)
 
 
+@sql_count_checker(query_count=4)
+def test_to_snowflake(session):
+    with session_parameter_override(
+        session, "dummy_row_pos_optimization_enabled", True
+    ):
+        # create tables
+        table_name = Utils.random_name_for_temp_object(TempObjectType.TABLE)
+        session.create_dataframe(
+            native_pd.DataFrame([[2, 12], [1, 11], [3, 13]], columns=["A", "B"])
+        ).write.save_as_table(table_name, table_type="temp")
+
+        # create snow dataframes
+        df = pd.read_snowflake(table_name)
+        df.to_snowflake(table_name, if_exists="replace", index=False)
+        snow_result = pd.read_snowflake(table_name).sort_values(by="A")
+
+        # verify that the input dataframe has a populated relaxed query compiler
+        assert df._query_compiler._relaxed_query_compiler is not None
+        assert df._query_compiler._relaxed_query_compiler._dummy_row_pos_mode is True
+        # verify that the output dataframe also has a populated relaxed query compiler
+        assert snow_result._query_compiler._relaxed_query_compiler is not None
+        assert (
+            snow_result._query_compiler._relaxed_query_compiler._dummy_row_pos_mode
+            is True
+        )
+
+        # create pandas dataframes
+        native_df = df.to_pandas()
+        native_result = native_df.sort_values(by="A")
+
+        # compare results
+        assert_frame_equal(snow_result, native_result)
+
+
 @sql_count_checker(query_count=3)
 def test_to_snowpark(session):
     with session_parameter_override(

tests/integ/scala/test_dataframe_suite.py

@@ -2686,6 +2686,24 @@ def test_rename_function_multiple(session):
     Utils.check_answer(df2, [Row(1, 2)])
 
 
+@pytest.mark.skipif(
+    "config.getoption('local_testing_mode', default=False)",
+    reason="DataFrame.rename is not supported in Local Testing",
+)
+def test_rename_with_case_sensitive_column_name(session):
+    from snowflake.snowpark import context
+    from unittest.mock import patch
+
+    with patch.object(context, "_is_snowpark_connect_compatible_mode", True):
+        df = session.create_dataframe([[1, 2]], schema=["ab", '"ab"'])
+        df2 = df.rename('"ab"', "ab1")
+        assert df2.schema.names == ["AB", "AB1"]
+        Utils.check_answer(df2, [Row(1, 2)])
+        df3 = df.rename({"ab": "ab1"})
+        assert df3.schema.names == ["AB1", '"ab"']
+        Utils.check_answer(df3, [Row(1, 2)])
+
+
 @pytest.mark.skipif(
     "config.getoption('local_testing_mode', default=False)",
     reason="DataFrame.rename is not supported in Local Testing",