Merge branch 'main' into jkew/add-hybrid-precheck

Author: sfc-gh-jkew

CHANGELOG.md

@@ -67,6 +67,7 @@
 - Fixed a bug that `DataFrameReader.dbapi` (PuPr) is not compatible with oracledb 3.4.0.
 - Fixed a bug where `modin` would unintentionally be imported during session initialization in some scenarios.
 - Fixed a bug where `session.udf|udtf|udaf|sproc.register` failed when an extra session argument was passed. These methods do not expect a session argument; please remove it if provided.
+- Fixed a bug in `DataFrameGroupBuy.agg` where func is a list of tuples used to set the names of the output columns.
 
 #### Improvements
 
@@ -83,6 +84,7 @@
 - Added support for the `dtypes` parameter of `pd.get_dummies`
 - Added support for `nunique` in `df.pivot_table`, `df.agg` and other places where aggregate functions can be used.
 - Added support for `DataFrame.interpolate` and `Series.interpolate` with the "linear", "ffill"/"pad", and "backfill"/bfill" methods. These use the SQL `INTERPOLATE_LINEAR`, `INTERPOLATE_FFILL`, and `INTERPOLATE_BFILL` functions (PuPr).
+- Added support for `Dataframe.groupby.rolling()`.
 
 #### Improvements
 
@@ -93,6 +95,16 @@
   - `skew()` with `axis=1` or `numeric_only=False` parameters
   - `round()` with `decimals` parameter as a Series
   - `corr()` with `method!=pearson` parameter
+  - `shift()` with `suffix` or non-integer `periods` parameters
+  - `sort_index()` with `axis=1` or `key` parameters
+  - `sort_values()` with `axis=1`
+  - `melt()` with `col_level` parameter
+  - `apply()` with `result_type` parameter for DataFrame
+  - `pivot_table()` with `sort=True`, non-string `index` list, non-string `columns` list, non-string `values` list, or `aggfunc` dict with non-string values
+  - `fillna()` with `downcast` parameter or using `limit` together with `value`
+  - `dropna()` with `axis=1`
+
+
 - Set `cte_optimization_enabled` to True for all Snowpark pandas sessions.
 - Add support for the following in faster pandas:
   - `isin`
@@ -152,6 +164,9 @@
   - `groupby.median`
   - `groupby.std`
   - `groupby.var`
+  - `groupby.nunique`
+  - `groupby.size`
+  - `groupby.apply`
   - `drop_duplicates`
 - Reuse row count from the relaxed query compiler in `get_axis_len`.
 

docs/source/modin/supported/groupby_supported.rst

@@ -153,7 +153,10 @@ Computations/descriptive stats
 |                             |                                 | will be lost. ``rule`` frequencies 's', 'min',     |
 |                             |                                 | 'h', and 'D' are supported.                        |
 +-----------------------------+---------------------------------+----------------------------------------------------+
-| ``rolling``                 | N                               |                                                    |
+| ``rolling``                 | P                               | Implemented for DataframeGroupby objects. ``N`` for|
+|                             |                                 | ``on``, non-integer ``window``, ``axis = 1``,      |
+|                             |                                 | ``method`` != ``single``, ``min_periods = 0``, or  |
+|                             |                                 | ``closed``  != ``None``.                           |
 +-----------------------------+---------------------------------+----------------------------------------------------+
 | ``sample``                  | N                               |                                                    |
 +-----------------------------+---------------------------------+----------------------------------------------------+

setup.py

@@ -68,7 +68,10 @@
     "lxml",  # used in XML reader unit tests
 ]
 MODIN_DEVELOPMENT_REQUIREMENTS = [
-    "scipy",  # Snowpark pandas 3rd party library testing
+    # Snowpark pandas 3rd party library testing. Cap the scipy version because
+    # Snowflake cannot find newer versions of scipy for python 3.11+. See
+    # SNOW-2452791.
+    "scipy<=1.16.0",
     "statsmodels",  # Snowpark pandas 3rd party library testing
     "scikit-learn",  # Snowpark pandas 3rd party library testing
     # plotly version restricted due to foreseen change in query counts in version 6.0.0+

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

@@ -898,8 +898,10 @@ def _is_supported_snowflake_agg_func(
     """
     if isinstance(agg_func, tuple) and len(agg_func) == 2:
         # For named aggregations, like `df.agg(new_col=("old_col", "sum"))`,
-        # take the second part of the named aggregation.
-        agg_func = agg_func[0]
+        # take the aggregation part of the named aggregation.
+        agg_func = (
+            agg_func.func if isinstance(agg_func, AggFuncWithLabel) else agg_func[1]
+        )
 
     if get_snowflake_agg_func(agg_func, agg_kwargs, axis, _is_df_agg) is None:
         return AggregationSupportResult(
@@ -1381,10 +1383,15 @@ def get_agg_func_to_col_map(
 def get_pandas_aggr_func_name(aggfunc: AggFuncTypeBase) -> str:
     """
     Returns the friendly name for the aggr function.  For example, if it is a callable, it will return __name__
-    otherwise the same string name value.
+    otherwise the same string name value. If aggfunc is a tuple, treat as named aggregation and return
+    the first part of the name.
     """
     return (
-        getattr(aggfunc, "__name__", str(aggfunc))
+        getattr(
+            aggfunc,
+            "__name__",
+            str(aggfunc[0]) if isinstance(aggfunc, tuple) else str(aggfunc),
+        )
         if not isinstance(aggfunc, str)
         else aggfunc
     )
@@ -1536,7 +1543,12 @@ def generate_column_agg_info(
         for func_info, label, identifier in zip(
             agg_func_list, agg_col_labels, agg_col_identifiers
         ):
-            func = func_info.func
+            # If func_info.func is a tuple, treat as named aggregation and return the aggregate function
+            func = (
+                func_info.func[1]
+                if isinstance(func_info.func, tuple)
+                else func_info.func
+            )
             is_dummy_agg = func_info.is_dummy_agg
             agg_func_col = pandas_lit(None) if is_dummy_agg else quoted_identifier
             snowflake_agg_func = get_snowflake_agg_func(func, agg_kwargs, axis=0)