Merge branch 'main' into helmeleegy-SNOW-2338542

Author: sfc-gh-helmeleegy

CHANGELOG.md

@@ -12,7 +12,9 @@
 
 #### Improvements
 
+- Hybrid execution mode is now enabled by default. Certain operations on smaller data will now automatically execute in native pandas in-memory. Use `from modin.config import AutoSwitchBackend; AutoSwitchBackend.disable()` to turn this off and force all execution to occur in Snowflake.
 - Added a session parameter `pandas_hybrid_execution_enabled` to enable/disable hybrid execution as an alternative to using `AutoSwitchBackend`.
+- Removed an unnecessary `SHOW OBJECTS` query issued from `read_snowflake` under certain conditions.
 
 ## 1.39.0 (YYYY-MM-DD)
 
@@ -81,7 +83,6 @@
 
 #### Improvements
 
-- Hybrid execution mode is now enabled by default. Certain operations on smaller data will now automatically execute in native pandas in-memory. Use `from modin.config import AutoSwitchBackend; AutoSwitchBackend.disable()` to turn this off and force all execution to occur in Snowflake.
 - Downgraded to level `logging.DEBUG - 1` the log message saying that the
   Snowpark `DataFrame` reference of an internal `DataFrameReference` object
   has changed.

src/snowflake/snowpark/modin/plugin/_internal/utils.py

@@ -322,7 +322,9 @@ def _create_read_only_table(
 def create_initial_ordered_dataframe(
     table_name_or_query: Union[str, Iterable[str]],
     enforce_ordering: bool,
+    *,
     dummy_row_pos_mode: bool = False,
+    row_count_hint: Optional[int] = None,
 ) -> tuple[OrderedDataFrame, str]:
     """
     create read only temp table on top of the existing table or Snowflake query if required, and create a OrderedDataFrame
@@ -334,6 +336,11 @@ def create_initial_ordered_dataframe(
         enforce_ordering: If True, create a read only temp table on top of the existing table or Snowflake query,
             and create the OrderedDataFrame using the read only temp table created.
             Otherwise, directly using the existing table.
+        dummy_row_pos_mode: If True, uses "dummy" row position columns to avoid a potentially
+            expensive ROW_NUMBER() query.
+        row_count_hint: An optional hint for the exact row count of the frame. This is used in scenarios
+            where we have already performed a query for the size of the underlying data, and can re-use
+            the value.
 
     Returns:
         OrderedDataFrame with row position column.
@@ -502,8 +509,10 @@ def create_initial_ordered_dataframe(
             ordered_dataframe.row_position_snowflake_quoted_identifier
         )
 
-    materialized_row_count = None
-    if not is_query:
+    if row_count_hint is not None:
+        ordered_dataframe.row_count = row_count_hint
+        ordered_dataframe.row_count_upper_bound = row_count_hint
+    elif not is_query:
         materialized_row_count = get_object_metadata_row_count(table_name_or_query)
         ordered_dataframe.row_count = materialized_row_count
         ordered_dataframe.row_count_upper_bound = materialized_row_count

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

@@ -1479,6 +1479,11 @@ def from_snowflake(
             table_name_or_query=name_or_query,
             enforce_ordering=enforce_ordering,
             dummy_row_pos_mode=dummy_row_pos_mode,
+            row_count_hint=(
+                relaxed_query_compiler._modin_frame.ordered_dataframe.row_count
+                if relaxed_query_compiler is not None
+                else None
+            ),
         )
         pandas_labels_to_snowflake_quoted_identifiers_map = {
             # pandas labels of resulting Snowpark pandas dataframe will be snowflake identifier