SNOW-2458028: Add support for copy in faster pandas (#3956)

Author: sfc-gh-helmeleegy

CHANGELOG.md

@@ -35,6 +35,7 @@
   - `groupby.nunique`
   - `groupby.size`
   - `concat`
+  - `copy`
 
 ## 1.41.0 (2025-10-23)
 

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

@@ -1482,6 +1482,16 @@ def from_date_range(
 
     @snowpark_pandas_type_immutable_check
     def copy(self) -> "SnowflakeQueryCompiler":
+        """
+        Wrapper around _copy_internal to be supported in faster pandas.
+        """
+        relaxed_query_compiler = None
+        if self._relaxed_query_compiler is not None:
+            relaxed_query_compiler = self._relaxed_query_compiler._copy_internal()
+        qc = self._copy_internal()
+        return self._maybe_set_relaxed_qc(qc, relaxed_query_compiler)
+
+    def _copy_internal(self) -> "SnowflakeQueryCompiler":
         """
         Make a copy of this object.
 

tests/integ/modin/test_faster_pandas.py

@@ -287,6 +287,35 @@ def test_concat(session):
     assert_frame_equal(snow_result, native_result)
 
 
+@sql_count_checker(query_count=3)
+def test_copy(session):
+    # create tables
+    table_name = Utils.random_name_for_temp_object(TempObjectType.TABLE)
+    session.create_dataframe(
+        native_pd.DataFrame([[2, True], [1, False], [3, False]], columns=["A", "B"])
+    ).write.save_as_table(table_name, table_type="temp")
+
+    # create snow dataframes
+    df = pd.read_snowflake(table_name)
+    snow_result = df.copy()
+
+    # 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.copy()
+
+    # compare results
+    assert_frame_equal(snow_result, native_result)
+
+
 @sql_count_checker(query_count=3)
 def test_drop(session):
     # create tables