Merge branch 'main' into helmeleegy-SNOW-2022698

Author: sfc-gh-helmeleegy

CHANGELOG.md

@@ -8,6 +8,11 @@
 
 - Added support for `restricted caller` permission of `execute_as` argument in `StoredProcedure.regsiter()`
 
+#### Improvements
+
+- Renamed the `relaxed_ordering` param into `enforce_ordering` for `DataFrame.read_snowflake`. Also the new default values is `enforce_ordering=False` which has the opposite effect of the previous default value, `relaxed_ordering=False`.
+
+
 #### Bug Fixes
 
 - Fixed a bug in `DataFrame.group_by().pivot().agg` when the pivot column and aggregate column are the same.
@@ -25,9 +30,21 @@
 
 ### Snowpark pandas API Updates
 
+#### New Features
+
+- Added support for `DataFrame.create_or_replace_view` and `Series.create_or_replace_view`.
+- Added support for `DataFrame.create_or_replace_dynamic_table` and `Series.create_or_replace_dynamic_table`.
+- Added support for `DataFrame.to_view` and `Series.to_view`.
+- Added support for `DataFrame.to_dynamic_table` and `Series.to_dynamic_table`.
+
 #### Improvements
 
 - Improve performance of `DataFrame.groupby.apply` and `Series.groupby.apply` by avoiding expensive pivot step.
+- Renamed the `relaxed_ordering` param into `enforce_ordering` for `pd.read_snowflake`. Also the new default values is `enforce_ordering=False` which has the opposite effect of the previous default value, `relaxed_ordering=False`.
+
+#### Bug Fixes
+
+- Fixed a bug for `pd.read_snowflake` when reading iceberg tables and `enforce_ordering=True`.
 
 ## 1.30.0 (2024-03-27)
 
@@ -73,8 +90,6 @@
 - Added support for list values in `Series.str.__getitem__` (`Series.str[...]`).
 - Added support for `pd.Grouper` objects in group by operations. When `freq` is specified, the default values of the `sort`, `closed`, `label`, and `convention` arguments are supported; `origin` is supported when it is `start` or `start_day`.
 - Added support for relaxed consistency and ordering guarantees in `pd.read_snowflake` for both named data sources (e.g., tables and views) and query data sources by introducing the new parameter `relaxed_ordering`.
-- Added support for `DataFrame.create_or_replace_view` and `Series.create_or_replace_view`.
-- Added support for `DataFrame.create_or_replace_dynamic_table` and `Series.create_or_replace_dynamic_table`.
 
 #### Improvements
 

docs/source/modin/dataframe.rst

@@ -40,6 +40,8 @@ DataFrame
     DataFrame.cache_result
     DataFrame.create_or_replace_view
     DataFrame.create_or_replace_dynamic_table
+    DataFrame.to_view
+    DataFrame.to_dynamic_table
 
 .. rubric:: Conversion
 

docs/source/modin/series.rst

@@ -46,6 +46,8 @@ Series
     Series.cache_result
     Series.create_or_replace_view
     Series.create_or_replace_dynamic_table
+    Series.to_view
+    Series.to_dynamic_table
 
 .. rubric:: Conversion
 

src/snowflake/snowpark/_internal/udf_utils.py

@@ -1311,6 +1311,19 @@ def create_python_udf_or_sp(
         raise ValueError(
             "artifact_repository must be specified when artifact_repository_packages has been specified"
         )
+    if all_packages and artifact_repository_packages:
+        package_names = [
+            pack.strip("\"'").split("==")[0] for pack in all_packages.split(",")
+        ]
+        artifact_repository_package_names = [
+            pack.strip("\"'").split("==")[0] for pack in artifact_repository_packages
+        ]
+
+        for package in package_names:
+            if package in artifact_repository_package_names:
+                raise ValueError(
+                    f"Cannot create a function with duplicates between packages and artifact repository packages. packages: {all_packages}, artifact_repository_packages: {','.join(artifact_repository_packages)}"
+                )
 
     artifact_repository_in_sql = (
         f"ARTIFACT_REPOSITORY={artifact_repository}" if artifact_repository else ""

src/snowflake/snowpark/dataframe.py

@@ -1394,7 +1394,10 @@ def to_snowpark_pandas(
             self._ast_id = ast_id  # reset the AST ID.
 
             snowpandas_df = pd.read_snowflake(
-                name_or_query=temporary_table_name, index_col=index_col, columns=columns
+                name_or_query=temporary_table_name,
+                index_col=index_col,
+                columns=columns,
+                enforce_ordering=True,
             )  # pragma: no cover
         else:
             if len(self.queries["queries"]) > 1:

src/snowflake/snowpark/dataframe_analytics_functions.py

@@ -13,8 +13,8 @@
 from snowflake.snowpark._internal.utils import experimental, publicapi
 from snowflake.snowpark.column import Column, _to_col_if_str
 from snowflake.snowpark.functions import (
+    _call_function,
     add_months,
-    builtin,
     col,
     dateadd,
     from_unixtime,
@@ -262,9 +262,9 @@ def _perform_window_aggregations(
                     if col_formatter
                     else f"{column}_{func}{rename_suffix}"
                 )
-                agg_expression = builtin(func)(col(column + rename_suffix)).alias(
-                    agg_column_name
-                )
+                agg_expression = _call_function(
+                    func, col(column + rename_suffix, _emit_ast=False), _emit_ast=False
+                ).alias(agg_column_name, _emit_ast=False)
                 agg_df = input_df.group_by(group_by_cols, _emit_ast=False).agg(
                     agg_expression, _emit_ast=False
                 )
@@ -369,7 +369,9 @@ def moving_agg(
                     )
 
                     # Apply the user-specified aggregation function directly. Snowflake will handle any errors for invalid functions.
-                    agg_col = builtin(agg_func)(col(column)).over(window_spec)
+                    agg_col = _call_function(
+                        agg_func, col(column, _emit_ast=False), _emit_ast=False
+                    ).over(window_spec, _emit_ast=False)
 
                     formatted_col_name = col_formatter(column, agg_func, window_size)
                     if (
@@ -479,7 +481,9 @@ def cumulative_agg(
         for column, agg_funcs in aggs.items():
             for agg_func in agg_funcs:
                 # Apply the user-specified aggregation function directly. Snowflake will handle any errors for invalid functions.
-                agg_col = builtin(agg_func)(col(column)).over(window_spec)
+                agg_col = _call_function(
+                    agg_func, col(column, _emit_ast=False), _emit_ast=False
+                ).over(window_spec, _emit_ast=False)
 
                 formatted_col_name = col_formatter(column, agg_func)